{"arxivqa_subsampled": {"ndcg_at_1": 0.846, "ndcg_at_3": 0.88724, "ndcg_at_5": 0.89464, "ndcg_at_10": 0.90262, "ndcg_at_20": 0.90655, "ndcg_at_100": 0.91016, "ndcg_at_1000": 0.91096, "map_at_1": 0.846, "map_at_3": 0.87667, "map_at_5": 0.88077, "map_at_10": 0.88419, "map_at_20": 0.88522, "map_at_100": 0.88582, "map_at_1000": 0.88586, "recall_at_1": 0.846, "recall_at_3": 0.918, "recall_at_5": 0.936, "recall_at_10": 0.96, "recall_at_20": 0.976, "recall_at_100": 0.994, "recall_at_1000": 1.0, "precision_at_1": 0.846, "precision_at_3": 0.306, "precision_at_5": 0.1872, "precision_at_10": 0.096, "precision_at_20": 0.0488, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.846, "mrr_at_3": 0.8763333333333332, "mrr_at_5": 0.8814333333333333, "mrr_at_10": 0.8845722222222221, "mrr_at_20": 0.885592790130406, "mrr_at_100": 0.8862097092529907, "mrr_at_1000": 0.8862427513676859, "naucs_at_1_max": 0.7479507415456175, "naucs_at_1_std": -0.2812281571288769, "naucs_at_1_diff1": 0.9258454382553668, "naucs_at_3_max": 0.8387761608708549, "naucs_at_3_std": -0.24216027874564358, "naucs_at_3_diff1": 0.8901755824280918, "naucs_at_5_max": 0.8996265172735749, "naucs_at_5_std": -0.2175390989729223, "naucs_at_5_diff1": 0.8941555788982243, "naucs_at_10_max": 0.9303221288515416, "naucs_at_10_std": -0.2065126050420224, "naucs_at_10_diff1": 0.8937908496732003, "naucs_at_20_max": 0.928804855275447, "naucs_at_20_std": -0.11896981014628347, "naucs_at_20_diff1": 0.9114923747276666, "naucs_at_100_max": 1.0, "naucs_at_100_std": 0.18643012760655897, "naucs_at_100_diff1": 0.9128540305010608, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.53437, "ndcg_at_3": 0.60632, "ndcg_at_5": 0.62646, "ndcg_at_10": 0.64874, "ndcg_at_20": 0.65909, "ndcg_at_100": 0.67792, "ndcg_at_1000": 0.6888, "map_at_1": 0.53437, "map_at_3": 0.58832, "map_at_5": 0.59952, "map_at_10": 0.60875, "map_at_20": 0.61173, "map_at_100": 0.61445, "map_at_1000": 0.61488, "recall_at_1": 0.53437, "recall_at_3": 0.65854, "recall_at_5": 0.70732, "recall_at_10": 0.77605, "recall_at_20": 0.81596, "recall_at_100": 0.91574, "recall_at_1000": 1.0, "precision_at_1": 0.53437, "precision_at_3": 0.21951, "precision_at_5": 0.14146, "precision_at_10": 0.07761, "precision_at_20": 0.0408, "precision_at_100": 0.00916, "precision_at_1000": 0.001, "mrr_at_1": 0.5365853658536586, "mrr_at_3": 0.5901699926090171, "mrr_at_5": 0.6021433850702144, "mrr_at_10": 0.6104872769506914, "mrr_at_20": 0.6132983422271759, "mrr_at_100": 0.6160294924799838, "mrr_at_1000": 0.6163830410583075, "naucs_at_1_max": 0.5973701491411594, "naucs_at_1_std": 0.15100454385637924, "naucs_at_1_diff1": 0.8982591944341096, "naucs_at_3_max": 0.4757723580757023, "naucs_at_3_std": 0.22070278027542517, "naucs_at_3_diff1": 0.8195064617583738, "naucs_at_5_max": 0.4575723188898858, "naucs_at_5_std": 0.3134827125035666, "naucs_at_5_diff1": 0.8072241700536605, "naucs_at_10_max": 0.4266102606041783, "naucs_at_10_std": 0.4518654327173679, "naucs_at_10_diff1": 0.7860743297872201, "naucs_at_20_max": 0.3739263641054462, "naucs_at_20_std": 0.5739789303935408, "naucs_at_20_diff1": 0.7911193147059952, "naucs_at_100_max": 0.07709889473305605, "naucs_at_100_std": 0.9164818709731807, "naucs_at_100_diff1": 0.7582525989589187, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "infovqa_subsampled": {"ndcg_at_1": 0.88462, "ndcg_at_3": 0.9157, "ndcg_at_5": 0.92136, "ndcg_at_10": 0.92762, "ndcg_at_20": 0.92974, "ndcg_at_100": 0.93344, "ndcg_at_1000": 0.93371, "map_at_1": 0.88462, "map_at_3": 0.90823, "map_at_5": 0.91127, "map_at_10": 0.91407, "map_at_20": 0.91469, "map_at_100": 0.91517, "map_at_1000": 0.91519, "recall_at_1": 0.88462, "recall_at_3": 0.93725, "recall_at_5": 0.95142, "recall_at_10": 0.96964, "recall_at_20": 0.97773, "recall_at_100": 0.99798, "recall_at_1000": 1.0, "precision_at_1": 0.88462, "precision_at_3": 0.31242, "precision_at_5": 0.19028, "precision_at_10": 0.09696, "precision_at_20": 0.04889, "precision_at_100": 0.00998, "precision_at_1000": 0.001, "mrr_at_1": 0.8846153846153846, "mrr_at_3": 0.9078947368421051, "mrr_at_5": 0.9119433198380564, "mrr_at_10": 0.9141242529400422, "mrr_at_20": 0.9149161960396777, "mrr_at_100": 0.9153930732357304, "mrr_at_1000": 0.9154058852072365, "naucs_at_1_max": 0.6190259976448219, "naucs_at_1_std": -0.3264770605196707, "naucs_at_1_diff1": 0.9262796600708453, "naucs_at_3_max": 0.781416166586695, "naucs_at_3_std": -0.12104903138475114, "naucs_at_3_diff1": 0.9081894684511614, "naucs_at_5_max": 0.8767035503045449, "naucs_at_5_std": 0.10481623478693029, "naucs_at_5_diff1": 0.9038671319947321, "naucs_at_10_max": 0.9354592911852186, "naucs_at_10_std": 0.25907731302868264, "naucs_at_10_diff1": 0.9390526547697702, "naucs_at_20_max": 0.9238628019857293, "naucs_at_20_std": 0.30347513687216277, "naucs_at_20_diff1": 0.928762843237398, "naucs_at_100_max": 0.8693985459351681, "naucs_at_100_std": 0.12265766416441783, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.90357, "ndcg_at_3": 0.94405, "ndcg_at_5": 0.95127, "ndcg_at_10": 0.95365, "ndcg_at_20": 0.95365, "ndcg_at_100": 0.9544, "ndcg_at_1000": 0.9544, "map_at_1": 0.90357, "map_at_3": 0.93452, "map_at_5": 0.93845, "map_at_10": 0.93947, "map_at_20": 0.93947, "map_at_100": 0.93961, "map_at_1000": 0.93961, "recall_at_1": 0.90357, "recall_at_3": 0.97143, "recall_at_5": 0.98929, "recall_at_10": 0.99643, "recall_at_20": 0.99643, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.90357, "precision_at_3": 0.32381, "precision_at_5": 0.19786, "precision_at_10": 0.09964, "precision_at_20": 0.04982, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.9035714285714286, "mrr_at_3": 0.9345238095238096, "mrr_at_5": 0.9384523809523809, "mrr_at_10": 0.9394090136054422, "mrr_at_20": 0.9394090136054422, "mrr_at_100": 0.9395463762428049, "mrr_at_1000": 0.9395463762428049, "naucs_at_1_max": 0.5883217484524678, "naucs_at_1_std": 0.046685340802988085, "naucs_at_1_diff1": 0.8713559497873212, "naucs_at_3_max": 0.822945845004673, "naucs_at_3_std": 0.5123716153127884, "naucs_at_3_diff1": 0.9305555555555513, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.9128540305011011, "naucs_at_5_diff1": 0.9074074074074161, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.8692810457516478, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 0.8692810457516478, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.66221, "ndcg_at_3": 0.7618, "ndcg_at_5": 0.78695, "ndcg_at_10": 0.80524, "ndcg_at_20": 0.81008, "ndcg_at_100": 0.81541, "ndcg_at_1000": 0.81634, "map_at_1": 0.66221, "map_at_3": 0.73815, "map_at_5": 0.75204, "map_at_10": 0.75983, "map_at_20": 0.7612, "map_at_100": 0.76198, "map_at_1000": 0.76203, "recall_at_1": 0.66221, "recall_at_3": 0.82989, "recall_at_5": 0.89125, "recall_at_10": 0.94654, "recall_at_20": 0.96537, "recall_at_100": 0.99332, "recall_at_1000": 1.0, "precision_at_1": 0.66221, "precision_at_3": 0.27663, "precision_at_5": 0.17825, "precision_at_10": 0.09465, "precision_at_20": 0.04827, "precision_at_100": 0.00993, "precision_at_1000": 0.001, "mrr_at_1": 0.6591737545565006, "mrr_at_3": 0.7368367760226815, "mrr_at_5": 0.750901174564602, "mrr_at_10": 0.7581910933672786, "mrr_at_20": 0.7596198059062583, "mrr_at_100": 0.7604221238767853, "mrr_at_1000": 0.7604672192997383, "naucs_at_1_max": 0.27078275465894486, "naucs_at_1_std": -0.2663234396116274, "naucs_at_1_diff1": 0.8294043992382637, "naucs_at_3_max": 0.330441662626675, "naucs_at_3_std": -0.18926582210411605, "naucs_at_3_diff1": 0.7259080195940506, "naucs_at_5_max": 0.36775785913157905, "naucs_at_5_std": -0.08929087499088985, "naucs_at_5_diff1": 0.7091864349746133, "naucs_at_10_max": 0.5108967532379013, "naucs_at_10_std": 0.10663319614120796, "naucs_at_10_diff1": 0.7206260108568603, "naucs_at_20_max": 0.6726089047927092, "naucs_at_20_std": 0.36289839721701594, "naucs_at_20_diff1": 0.7442189535318923, "naucs_at_100_max": 0.6921321331042545, "naucs_at_100_std": 0.7999774728465878, "naucs_at_100_diff1": 0.6295641820467829, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.75, "ndcg_at_3": 0.86833, "ndcg_at_5": 0.88081, "ndcg_at_10": 0.88382, "ndcg_at_20": 0.88382, "ndcg_at_100": 0.88543, "ndcg_at_1000": 0.88543, "map_at_1": 0.75, "map_at_3": 0.84, "map_at_5": 0.847, "map_at_10": 0.84811, "map_at_20": 0.84811, "map_at_100": 0.84825, "map_at_1000": 0.84825, "recall_at_1": 0.75, "recall_at_3": 0.95, "recall_at_5": 0.98, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.75, "precision_at_3": 0.31667, "precision_at_5": 0.196, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.74, "mrr_at_3": 0.8333333333333331, "mrr_at_5": 0.8423333333333332, "mrr_at_10": 0.8434444444444443, "mrr_at_20": 0.8434444444444443, "mrr_at_100": 0.8435795795795795, "mrr_at_1000": 0.8435795795795795, "naucs_at_1_max": 0.11870225013082168, "naucs_at_1_std": -0.40613291470434393, "naucs_at_1_diff1": 0.8483516483516487, "naucs_at_3_max": 0.09925303454715217, "naucs_at_3_std": -0.3987861811391193, "naucs_at_3_diff1": 0.7955182072829138, "naucs_at_5_max": 0.3384687208216692, "naucs_at_5_std": 0.09337068160597826, "naucs_at_5_diff1": 0.7770774976657324, "naucs_at_10_max": 0.5541549953314738, "naucs_at_10_std": 0.35807656395891135, "naucs_at_10_diff1": 0.5541549953314738, "naucs_at_20_max": 0.5541549953314738, "naucs_at_20_std": 0.35807656395891135, "naucs_at_20_diff1": 0.5541549953314738, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.99, "ndcg_at_3": 0.99631, "ndcg_at_5": 0.99631, "ndcg_at_10": 0.99631, "ndcg_at_20": 0.99631, "ndcg_at_100": 0.99631, "ndcg_at_1000": 0.99631, "map_at_1": 0.99, "map_at_3": 0.995, "map_at_5": 0.995, "map_at_10": 0.995, "map_at_20": 0.995, "map_at_100": 0.995, "map_at_1000": 0.995, "recall_at_1": 0.99, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.99, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.99, "mrr_at_3": 0.995, "mrr_at_5": 0.995, "mrr_at_10": 0.995, "mrr_at_20": 0.995, "mrr_at_100": 0.995, "mrr_at_1000": 0.995, "naucs_at_1_max": 1.0, "naucs_at_1_std": 1.0, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_energy": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.94655, "ndcg_at_5": 0.95428, "ndcg_at_10": 0.95428, "ndcg_at_20": 0.95428, "ndcg_at_100": 0.95636, "ndcg_at_1000": 0.95636, "map_at_1": 0.91, "map_at_3": 0.93833, "map_at_5": 0.94233, "map_at_10": 0.94233, "map_at_20": 0.94233, "map_at_100": 0.9427, "map_at_1000": 0.9427, "recall_at_1": 0.91, "recall_at_3": 0.97, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.32333, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.91, "mrr_at_3": 0.94, "mrr_at_5": 0.9440000000000001, "mrr_at_10": 0.9440000000000001, "mrr_at_20": 0.9440000000000001, "mrr_at_100": 0.9443846153846154, "mrr_at_1000": 0.9443846153846154, "naucs_at_1_max": 0.13269011308227113, "naucs_at_1_std": -0.5395269218798633, "naucs_at_1_diff1": 0.9709513435003629, "naucs_at_3_max": 0.9564270152505466, "naucs_at_3_std": -0.2236227824463119, "naucs_at_3_diff1": 0.9564270152505466, "naucs_at_5_max": 1.0, "naucs_at_5_std": -1.1517273576097316, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": -1.1517273576097316, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": -1.1517273576097316, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.94, "ndcg_at_3": 0.96262, "ndcg_at_5": 0.97079, "ndcg_at_10": 0.97079, "ndcg_at_20": 0.97079, "ndcg_at_100": 0.97079, "ndcg_at_1000": 0.97079, "map_at_1": 0.94, "map_at_3": 0.95667, "map_at_5": 0.96117, "map_at_10": 0.96117, "map_at_20": 0.96117, "map_at_100": 0.96117, "map_at_1000": 0.96117, "recall_at_1": 0.94, "recall_at_3": 0.98, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.94, "precision_at_3": 0.32667, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.9566666666666666, "mrr_at_5": 0.9611666666666666, "mrr_at_10": 0.9611666666666666, "mrr_at_20": 0.9611666666666666, "mrr_at_100": 0.9611666666666666, "mrr_at_1000": 0.9611666666666666, "naucs_at_1_max": 0.8576097105508863, "naucs_at_1_std": 0.32555244319950205, "naucs_at_1_diff1": 0.9101307189542497, "naucs_at_3_max": 0.7770774976657261, "naucs_at_3_std": 0.4143323996265135, "naucs_at_3_diff1": 0.8611111111111119, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.99, "ndcg_at_3": 0.99631, "ndcg_at_5": 0.99631, "ndcg_at_10": 0.99631, "ndcg_at_20": 0.99631, "ndcg_at_100": 0.99631, "ndcg_at_1000": 0.99631, "map_at_1": 0.99, "map_at_3": 0.995, "map_at_5": 0.995, "map_at_10": 0.995, "map_at_20": 0.995, "map_at_100": 0.995, "map_at_1000": 0.995, "recall_at_1": 0.99, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.99, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.99, "mrr_at_3": 0.995, "mrr_at_5": 0.995, "mrr_at_10": 0.995, "mrr_at_20": 0.995, "mrr_at_100": 0.995, "mrr_at_1000": 0.995, "naucs_at_1_max": 0.12278244631185359, "naucs_at_1_std": -1.151727357609709, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}