Update results.json
Browse files- results.json +465 -1
results.json
CHANGED
|
@@ -1 +1,465 @@
|
|
| 1 |
-
{"tatdqa_test": {"ndcg_at_1": 0.55043, "ndcg_at_3": 0.65383, "ndcg_at_5": 0.67972, "ndcg_at_10": 0.70182, "ndcg_at_20": 0.71531, "ndcg_at_100": 0.72798, "ndcg_at_1000": 0.73147, "map_at_1": 0.55043, "map_at_3": 0.6292, "map_at_5": 0.64363, "map_at_10": 0.65292, "map_at_20": 0.6567, "map_at_100": 0.65856, "map_at_1000": 0.65873, "recall_at_1": 0.55043, "recall_at_3": 0.72479, "recall_at_5": 0.78736, "recall_at_10": 0.8548, "recall_at_20": 0.90765, "recall_at_100": 0.97448, "recall_at_1000": 1.0, "precision_at_1": 0.55043, "precision_at_3": 0.2416, "precision_at_5": 0.15747, "precision_at_10": 0.08548, "precision_at_20": 0.04538, "precision_at_100": 0.00974, "precision_at_1000": 0.001, "mrr_at_1": 0.5498177399756987, "mrr_at_3": 0.6287970838396112, "mrr_at_5": 0.6434690157958688, "mrr_at_10": 0.6530902235337229, "mrr_at_20": 0.6567284540447504, "mrr_at_100": 0.658621212229932, "mrr_at_1000": 0.6587698669596878, "naucs_at_1_max": 0.27853365504109656, "naucs_at_1_std": -0.15447634347947511, "naucs_at_1_diff1": 0.7134897043728883, "naucs_at_3_max": 0.2862020499335342, "naucs_at_3_std": -0.1406768618430069, "naucs_at_3_diff1": 0.598287834466956, "naucs_at_5_max": 0.3082772653205975, "naucs_at_5_std": -0.1336535664737251, "naucs_at_5_diff1": 0.5847681853576895, "naucs_at_10_max": 0.4156924004771727, "naucs_at_10_std": -0.012527556044571743, "naucs_at_10_diff1": 0.5762936692610346, "naucs_at_20_max": 0.39150222479435925, "naucs_at_20_std": 0.004434403605241619, "naucs_at_20_diff1": 0.5602018066874601, "naucs_at_100_max": 0.39176268171942447, "naucs_at_100_std": 0.360160411337065, "naucs_at_100_diff1": 0.6304563665269014, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shiftproject_test": {"ndcg_at_1": 0.63, "ndcg_at_3": 0.76488, "ndcg_at_5": 0.79072, "ndcg_at_10": 0.80085, "ndcg_at_20": 0.80877, "ndcg_at_100": 0.81273, "ndcg_at_1000": 0.81415, "map_at_1": 0.63, "map_at_3": 0.735, "map_at_5": 0.75, "map_at_10": 0.75444, "map_at_20": 0.75679, "map_at_100": 0.75742, "map_at_1000": 0.75749, "recall_at_1": 0.63, "recall_at_3": 0.85, "recall_at_5": 0.91, "recall_at_10": 0.94, "recall_at_20": 0.97, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.63, "precision_at_3": 0.28333, "precision_at_5": 0.182, "precision_at_10": 0.094, "precision_at_20": 0.0485, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.65, "mrr_at_3": 0.7483333333333333, "mrr_at_5": 0.7608333333333333, "mrr_at_10": 0.7663888888888889, "mrr_at_20": 0.7679646464646465, "mrr_at_100": 0.768591427091427, "mrr_at_1000": 0.7686683501683501, "naucs_at_1_max": -0.061987809273100325, "naucs_at_1_std": -0.18575972672715027, "naucs_at_1_diff1": 0.7242513984863435, "naucs_at_3_max": 0.18226488773185812, "naucs_at_3_std": -0.19902375528799124, "naucs_at_3_diff1": 0.6877969410999027, "naucs_at_5_max": -0.24074074074073906, "naucs_at_5_std": -0.7552131963896631, "naucs_at_5_diff1": 0.6890756302521003, "naucs_at_10_max": -0.3181605975723611, "naucs_at_10_std": -1.07002801120448, "naucs_at_10_diff1": 0.7005135387488336, "naucs_at_20_max": -0.7791783380018631, "naucs_at_20_std": -0.5961718020541553, "naucs_at_20_diff1": 0.401027077497665, "naucs_at_100_max": 0.554154995331464, "naucs_at_100_std": -0.17133520074697067, "naucs_at_100_diff1": 0.35807656395892007, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98131, "ndcg_at_5": 0.98131, "ndcg_at_10": 0.98131, "ndcg_at_20": 0.98131, "ndcg_at_100": 0.98321, "ndcg_at_1000": 0.98321, "map_at_1": 0.97, "map_at_3": 0.97833, "map_at_5": 0.97833, "map_at_10": 0.97833, "map_at_20": 0.97833, "map_at_100": 0.9786, "map_at_1000": 0.9786, "recall_at_1": 0.97, "recall_at_3": 0.99, "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": 0.97, "precision_at_3": 0.33, "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": 0.97, "mrr_at_3": 0.9783333333333333, "mrr_at_5": 0.9783333333333333, "mrr_at_10": 0.9783333333333333, "mrr_at_20": 0.9783333333333333, "mrr_at_100": 0.9786111111111111, "mrr_at_1000": 0.9786111111111111, "naucs_at_1_max": 0.41518829754123937, "naucs_at_1_std": -1.1517273576097102, "naucs_at_1_diff1": 0.9564270152505465, "naucs_at_3_max": 1.0, "naucs_at_3_std": -1.1517273576097802, "naucs_at_3_diff1": 1.0, "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_test": {"ndcg_at_1": 0.89, "ndcg_at_3": 0.94786, "ndcg_at_5": 0.94786, "ndcg_at_10": 0.95142, "ndcg_at_20": 0.95142, "ndcg_at_100": 0.95142, "ndcg_at_1000": 0.95142, "map_at_1": 0.89, "map_at_3": 0.93333, "map_at_5": 0.93333, "map_at_10": 0.935, "map_at_20": 0.935, "map_at_100": 0.935, "map_at_1000": 0.935, "recall_at_1": 0.89, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.89, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.89, "mrr_at_3": 0.935, "mrr_at_5": 0.937, "mrr_at_10": 0.937, "mrr_at_20": 0.937, "mrr_at_100": 0.937, "mrr_at_1000": 0.937, "naucs_at_1_max": 0.5626234859548148, "naucs_at_1_std": 0.3716175586289838, "naucs_at_1_diff1": 0.834850957821493, "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}, "arxivqa_test_subsampled": {"ndcg_at_1": 0.702, "ndcg_at_3": 0.76743, "ndcg_at_5": 0.77991, "ndcg_at_10": 0.79468, "ndcg_at_20": 0.80462, "ndcg_at_100": 0.8145, "ndcg_at_1000": 0.81657, "map_at_1": 0.702, "map_at_3": 0.75133, "map_at_5": 0.75833, "map_at_10": 0.76436, "map_at_20": 0.767, "map_at_100": 0.76831, "map_at_1000": 0.76839, "recall_at_1": 0.702, "recall_at_3": 0.814, "recall_at_5": 0.844, "recall_at_10": 0.89, "recall_at_20": 0.93, "recall_at_100": 0.984, "recall_at_1000": 1.0, "precision_at_1": 0.702, "precision_at_3": 0.27133, "precision_at_5": 0.1688, "precision_at_10": 0.089, "precision_at_20": 0.0465, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.7, "mrr_at_3": 0.7506666666666666, "mrr_at_5": 0.7575666666666667, "mrr_at_10": 0.76395, "mrr_at_20": 0.7664683712486344, "mrr_at_100": 0.7677856040474413, "mrr_at_1000": 0.767866298103699, "naucs_at_1_max": 0.6661847878465089, "naucs_at_1_std": -0.217519374789405, "naucs_at_1_diff1": 0.9071749220117173, "naucs_at_3_max": 0.697658762809486, "naucs_at_3_std": -0.18659371894467894, "naucs_at_3_diff1": 0.839073335969141, "naucs_at_5_max": 0.7447876108417706, "naucs_at_5_std": -0.17636087316938498, "naucs_at_5_diff1": 0.8526087065738912, "naucs_at_10_max": 0.7873636285542479, "naucs_at_10_std": -0.15812215445408626, "naucs_at_10_diff1": 0.8351945709131511, "naucs_at_20_max": 0.7746565292783784, "naucs_at_20_std": -0.23473389355742383, "naucs_at_20_diff1": 0.8061224489795931, "naucs_at_100_max": 0.8027544351073763, "naucs_at_100_std": 0.2001050420168152, "naucs_at_100_diff1": 0.7639472455648932, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_test_subsampled": {"ndcg_at_1": 0.49446, "ndcg_at_3": 0.54968, "ndcg_at_5": 0.57172, "ndcg_at_10": 0.59184, "ndcg_at_20": 0.60528, "ndcg_at_100": 0.62838, "ndcg_at_1000": 0.64353, "map_at_1": 0.49446, "map_at_3": 0.53585, "map_at_5": 0.54815, "map_at_10": 0.55648, "map_at_20": 0.56018, "map_at_100": 0.56326, "map_at_1000": 0.56389, "recall_at_1": 0.49446, "recall_at_3": 0.5898, "recall_at_5": 0.64302, "recall_at_10": 0.7051, "recall_at_20": 0.75831, "recall_at_100": 0.8847, "recall_at_1000": 1.0, "precision_at_1": 0.49446, "precision_at_3": 0.1966, "precision_at_5": 0.1286, "precision_at_10": 0.07051, "precision_at_20": 0.03792, "precision_at_100": 0.00885, "precision_at_1000": 0.001, "mrr_at_1": 0.49223946784922396, "mrr_at_3": 0.5339985218033999, "mrr_at_5": 0.5473022912047303, "mrr_at_10": 0.5553206278816035, "mrr_at_20": 0.5589821565391849, "mrr_at_100": 0.5619819074681309, "mrr_at_1000": 0.5626456935597429, "naucs_at_1_max": 0.32878731695222985, "naucs_at_1_std": 0.15591990126747984, "naucs_at_1_diff1": 0.8493613636054403, "naucs_at_3_max": 0.23098165064202703, "naucs_at_3_std": 0.1729343384390047, "naucs_at_3_diff1": 0.79653911998206, "naucs_at_5_max": 0.20443193032581358, "naucs_at_5_std": 0.22886452804275878, "naucs_at_5_diff1": 0.7709831107458899, "naucs_at_10_max": 0.11430383031823631, "naucs_at_10_std": 0.3505331687518112, "naucs_at_10_diff1": 0.7655459781075918, "naucs_at_20_max": 0.06375294772557255, "naucs_at_20_std": 0.47875225635393476, "naucs_at_20_diff1": 0.7402047132383933, "naucs_at_100_max": -0.17203513994521832, "naucs_at_100_std": 0.719961371895444, "naucs_at_100_diff1": 0.7516431118242167, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.94, "ndcg_at_3": 0.96262, "ndcg_at_5": 0.96693, "ndcg_at_10": 0.96693, "ndcg_at_20": 0.96948, "ndcg_at_100": 0.96948, "ndcg_at_1000": 0.96948, "map_at_1": 0.94, "map_at_3": 0.95667, "map_at_5": 0.95917, "map_at_10": 0.95917, "map_at_20": 0.95988, "map_at_100": 0.95988, "map_at_1000": 0.95988, "recall_at_1": 0.94, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "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": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.96, "mrr_at_3": 0.9683333333333333, "mrr_at_5": 0.9708333333333333, "mrr_at_10": 0.9708333333333333, "mrr_at_20": 0.971547619047619, "mrr_at_100": 0.971547619047619, "mrr_at_1000": 0.971547619047619, "naucs_at_1_max": 0.4701991907874248, "naucs_at_1_std": -0.2544351073762836, "naucs_at_1_diff1": 0.9319172113289763, "naucs_at_3_max": -0.004668534080301393, "naucs_at_3_std": -0.5088702147525775, "naucs_at_3_diff1": 0.7957516339869218, "naucs_at_5_max": -0.5634920634920767, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.7222222222222276, "naucs_at_10_max": -0.5634920634920767, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.7222222222222276, "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}, "infovqa_test_subsampled": {"ndcg_at_1": 0.76518, "ndcg_at_3": 0.81846, "ndcg_at_5": 0.82779, "ndcg_at_10": 0.84084, "ndcg_at_20": 0.8454, "ndcg_at_100": 0.85306, "ndcg_at_1000": 0.85616, "map_at_1": 0.76518, "map_at_3": 0.80601, "map_at_5": 0.81127, "map_at_10": 0.81663, "map_at_20": 0.81786, "map_at_100": 0.81898, "map_at_1000": 0.81909, "recall_at_1": 0.76518, "recall_at_3": 0.85425, "recall_at_5": 0.87652, "recall_at_10": 0.917, "recall_at_20": 0.93522, "recall_at_100": 0.97571, "recall_at_1000": 1.0, "precision_at_1": 0.76518, "precision_at_3": 0.28475, "precision_at_5": 0.1753, "precision_at_10": 0.0917, "precision_at_20": 0.04676, "precision_at_100": 0.00976, "precision_at_1000": 0.001, "mrr_at_1": 0.7672064777327935, "mrr_at_3": 0.8076923076923077, "mrr_at_5": 0.8130566801619433, "mrr_at_10": 0.8183712486344065, "mrr_at_20": 0.8196021674007504, "mrr_at_100": 0.8207219702130965, "mrr_at_1000": 0.8208340179158132, "naucs_at_1_max": 0.526736932815251, "naucs_at_1_std": -0.08005662601905021, "naucs_at_1_diff1": 0.8906383040101385, "naucs_at_3_max": 0.5628217589502187, "naucs_at_3_std": 0.07419124093710198, "naucs_at_3_diff1": 0.819273316147957, "naucs_at_5_max": 0.6142211700114351, "naucs_at_5_std": 0.13484006376865668, "naucs_at_5_diff1": 0.7974348993177082, "naucs_at_10_max": 0.5107732925204674, "naucs_at_10_std": 0.08282924765220158, "naucs_at_10_diff1": 0.7501472816409511, "naucs_at_20_max": 0.6069714717598735, "naucs_at_20_std": 0.24818260935350467, "naucs_at_20_diff1": 0.7972653744711068, "naucs_at_100_max": 0.7715054503371943, "naucs_at_100_std": 0.6498035527508992, "naucs_at_100_diff1": 0.7627810617053321, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.95155, "ndcg_at_5": 0.95155, "ndcg_at_10": 0.95155, "ndcg_at_20": 0.95425, "ndcg_at_100": 0.95618, "ndcg_at_1000": 0.95745, "map_at_1": 0.92, "map_at_3": 0.945, "map_at_5": 0.945, "map_at_10": 0.945, "map_at_20": 0.94583, "map_at_100": 0.94612, "map_at_1000": 0.94616, "recall_at_1": 0.92, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.945, "mrr_at_5": 0.945, "mrr_at_10": 0.945, "mrr_at_20": 0.9458333333333333, "mrr_at_100": 0.9461190476190476, "mrr_at_1000": 0.9461614205004035, "naucs_at_1_max": 0.5274859943977597, "naucs_at_1_std": -0.6526027077497683, "naucs_at_1_diff1": 0.9673202614379083, "naucs_at_3_max": 0.807812013694371, "naucs_at_3_std": -1.1517273576097098, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.807812013694364, "naucs_at_5_std": -1.1517273576097071, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.807812013694364, "naucs_at_10_std": -1.1517273576097071, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.9346405228758136, "naucs_at_20_std": -0.8576097105508901, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": -0.5634920634920583, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tabfquad_test_subsampled": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.88465, "ndcg_at_5": 0.89664, "ndcg_at_10": 0.90491, "ndcg_at_20": 0.91464, "ndcg_at_100": 0.91464, "ndcg_at_1000": 0.91464, "map_at_1": 0.85, "map_at_3": 0.87679, "map_at_5": 0.88357, "map_at_10": 0.8871, "map_at_20": 0.88966, "map_at_100": 0.88966, "map_at_1000": 0.88966, "recall_at_1": 0.85, "recall_at_3": 0.90714, "recall_at_5": 0.93571, "recall_at_10": 0.96071, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.30238, "precision_at_5": 0.18714, "precision_at_10": 0.09607, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.85, "mrr_at_3": 0.8779761904761905, "mrr_at_5": 0.8838690476190476, "mrr_at_10": 0.8874900793650794, "mrr_at_20": 0.8898663632119514, "mrr_at_100": 0.8900364312391623, "mrr_at_1000": 0.8900364312391623, "naucs_at_1_max": 0.6249012133327131, "naucs_at_1_std": 0.27568453349449135, "naucs_at_1_diff1": 0.851971084561387, "naucs_at_3_max": 0.7154528478057898, "naucs_at_3_std": 0.3263664440135032, "naucs_at_3_diff1": 0.8540364863894296, "naucs_at_5_max": 0.7756769374416456, "naucs_at_5_std": 0.5388525780682669, "naucs_at_5_diff1": 0.8674914410208527, "naucs_at_10_max": 0.7903403785756714, "naucs_at_10_std": 0.6866564807741266, "naucs_at_10_diff1": 0.832187420422716, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "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}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.26923, "ndcg_at_3": 0.3045, "ndcg_at_5": 0.32114, "ndcg_at_10": 0.35676, "ndcg_at_20": 0.38618, "ndcg_at_50": 0.42052, "ndcg_at_100": 0.43636, "map_at_1": 0.18333, "map_at_3": 0.24391, "map_at_5": 0.26139, "map_at_10": 0.27761, "map_at_20": 0.28675, "map_at_50": 0.29345, "map_at_100": 0.29582, "recall_at_1": 0.18333, "recall_at_3": 0.31923, "recall_at_5": 0.37917, "recall_at_10": 0.49423, "recall_at_20": 0.5946, "recall_at_50": 0.73516, "recall_at_100": 0.80377, "precision_at_1": 0.26923, "precision_at_3": 0.16667, "precision_at_5": 0.12308, "precision_at_10": 0.08269, "precision_at_20": 0.05385, "precision_at_50": 0.02846, "precision_at_100": 0.01692, "mrr_at_1": 0.23076923076923078, "mrr_at_3": 0.3269230769230769, "mrr_at_5": 0.34038461538461545, "mrr_at_10": 0.3608669108669108, "mrr_at_20": 0.3674438809054194, "mrr_at_50": 0.37084971190489147, "mrr_at_100": 0.3713579847136337, "naucs_at_1_max": 0.021151055203054405, "naucs_at_1_std": -0.029813730522622425, "naucs_at_1_diff1": 0.25067341614916727, "naucs_at_3_max": -0.04143164067060292, "naucs_at_3_std": 0.00730042874767451, "naucs_at_3_diff1": 0.3380054031613406, "naucs_at_5_max": -0.1347500524905061, "naucs_at_5_std": -0.07424067226444503, "naucs_at_5_diff1": 0.2669507130764703, "naucs_at_10_max": -0.210749971018401, "naucs_at_10_std": -0.21961340947875993, "naucs_at_10_diff1": 0.16640286626959264, "naucs_at_20_max": -0.21891469085057838, "naucs_at_20_std": -0.23005504027592547, "naucs_at_20_diff1": 0.22055505233932227, "naucs_at_50_max": -0.21310892162468298, "naucs_at_50_std": -0.20734986109292497, "naucs_at_50_diff1": 0.09142935454845501, "naucs_at_100_max": -0.22587806170824862, "naucs_at_100_std": -0.21517085450107218, "naucs_at_100_diff1": 0.09673268004702926},
|
| 2 |
+
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
|
| 3 |
+
"ndcg_at_1": 0.51293,
|
| 4 |
+
"ndcg_at_3": 0.49649,
|
| 5 |
+
"ndcg_at_5": 0.47893,
|
| 6 |
+
"ndcg_at_10": 0.48004,
|
| 7 |
+
"ndcg_at_20": 0.51068,
|
| 8 |
+
"ndcg_at_50": 0.59426,
|
| 9 |
+
"ndcg_at_100": 0.63376,
|
| 10 |
+
"map_at_1": 0.10147,
|
| 11 |
+
"map_at_3": 0.15877,
|
| 12 |
+
"map_at_5": 0.19559,
|
| 13 |
+
"map_at_10": 0.25349,
|
| 14 |
+
"map_at_20": 0.30278,
|
| 15 |
+
"map_at_50": 0.36487,
|
| 16 |
+
"map_at_100": 0.39199,
|
| 17 |
+
"recall_at_1": 0.10147,
|
| 18 |
+
"recall_at_3": 0.17902,
|
| 19 |
+
"recall_at_5": 0.23979,
|
| 20 |
+
"recall_at_10": 0.373,
|
| 21 |
+
"recall_at_20": 0.52076,
|
| 22 |
+
"recall_at_50": 0.76023,
|
| 23 |
+
"recall_at_100": 0.88108,
|
| 24 |
+
"precision_at_1": 0.51293,
|
| 25 |
+
"precision_at_3": 0.45259,
|
| 26 |
+
"precision_at_5": 0.41293,
|
| 27 |
+
"precision_at_10": 0.35259,
|
| 28 |
+
"precision_at_20": 0.27909,
|
| 29 |
+
"precision_at_50": 0.18828,
|
| 30 |
+
"precision_at_100": 0.12366,
|
| 31 |
+
"mrr_at_1": 0.4956896551724138,
|
| 32 |
+
"mrr_at_3": 0.6149425287356322,
|
| 33 |
+
"mrr_at_5": 0.6311063218390804,
|
| 34 |
+
"mrr_at_10": 0.6426518883415435,
|
| 35 |
+
"mrr_at_20": 0.6473663956998068,
|
| 36 |
+
"mrr_at_50": 0.6479916726305025,
|
| 37 |
+
"mrr_at_100": 0.6480600908023689,
|
| 38 |
+
"naucs_at_1_max": 0.2909740112601449,
|
| 39 |
+
"naucs_at_1_std": 0.34007231211982364,
|
| 40 |
+
"naucs_at_1_diff1": 0.02010046418675761,
|
| 41 |
+
"naucs_at_3_max": 0.1462981439133328,
|
| 42 |
+
"naucs_at_3_std": 0.23727806279449618,
|
| 43 |
+
"naucs_at_3_diff1": -0.045115704507227815,
|
| 44 |
+
"naucs_at_5_max": 0.16402901891891258,
|
| 45 |
+
"naucs_at_5_std": 0.2788211772941985,
|
| 46 |
+
"naucs_at_5_diff1": -0.03422957119067939,
|
| 47 |
+
"naucs_at_10_max": 0.1304595275607474,
|
| 48 |
+
"naucs_at_10_std": 0.27024887845192075,
|
| 49 |
+
"naucs_at_10_diff1": -0.06184582606627896,
|
| 50 |
+
"naucs_at_20_max": 0.0827755061718375,
|
| 51 |
+
"naucs_at_20_std": 0.32564544404546836,
|
| 52 |
+
"naucs_at_20_diff1": -0.1398291345769381,
|
| 53 |
+
"naucs_at_50_max": 0.024145276015777446,
|
| 54 |
+
"naucs_at_50_std": 0.3093730698130927,
|
| 55 |
+
"naucs_at_50_diff1": -0.16628805756811568,
|
| 56 |
+
"naucs_at_100_max": 0.0009219308736878375,
|
| 57 |
+
"naucs_at_100_std": 0.2960260201661105,
|
| 58 |
+
"naucs_at_100_diff1": -0.16354176688825178
|
| 59 |
+
},
|
| 60 |
+
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
| 61 |
+
"ndcg_at_1": 0.44444,
|
| 62 |
+
"ndcg_at_3": 0.48365,
|
| 63 |
+
"ndcg_at_5": 0.4576,
|
| 64 |
+
"ndcg_at_10": 0.47015,
|
| 65 |
+
"ndcg_at_20": 0.48904,
|
| 66 |
+
"ndcg_at_50": 0.54777,
|
| 67 |
+
"ndcg_at_100": 0.58161,
|
| 68 |
+
"map_at_1": 0.16613,
|
| 69 |
+
"map_at_3": 0.28304,
|
| 70 |
+
"map_at_5": 0.30204,
|
| 71 |
+
"map_at_10": 0.33659,
|
| 72 |
+
"map_at_20": 0.35316,
|
| 73 |
+
"map_at_50": 0.37788,
|
| 74 |
+
"map_at_100": 0.38576,
|
| 75 |
+
"recall_at_1": 0.16613,
|
| 76 |
+
"recall_at_3": 0.4128,
|
| 77 |
+
"recall_at_5": 0.4461,
|
| 78 |
+
"recall_at_10": 0.56445,
|
| 79 |
+
"recall_at_20": 0.62203,
|
| 80 |
+
"recall_at_50": 0.78078,
|
| 81 |
+
"recall_at_100": 0.91945,
|
| 82 |
+
"precision_at_1": 0.44444,
|
| 83 |
+
"precision_at_3": 0.35648,
|
| 84 |
+
"precision_at_5": 0.26944,
|
| 85 |
+
"precision_at_10": 0.18333,
|
| 86 |
+
"precision_at_20": 0.11875,
|
| 87 |
+
"precision_at_50": 0.07028,
|
| 88 |
+
"precision_at_100": 0.04181,
|
| 89 |
+
"mrr_at_1": 0.4305555555555556,
|
| 90 |
+
"mrr_at_3": 0.5486111111111112,
|
| 91 |
+
"mrr_at_5": 0.5625,
|
| 92 |
+
"mrr_at_10": 0.5719907407407407,
|
| 93 |
+
"mrr_at_20": 0.5744107744107745,
|
| 94 |
+
"mrr_at_50": 0.5755691882594056,
|
| 95 |
+
"mrr_at_100": 0.5766185382360561,
|
| 96 |
+
"naucs_at_1_max": -0.10844176576631265,
|
| 97 |
+
"naucs_at_1_std": 0.11984795634852517,
|
| 98 |
+
"naucs_at_1_diff1": 0.34926607045706065,
|
| 99 |
+
"naucs_at_3_max": -0.16882440588261344,
|
| 100 |
+
"naucs_at_3_std": 0.04935292481231464,
|
| 101 |
+
"naucs_at_3_diff1": 0.07094770137246685,
|
| 102 |
+
"naucs_at_5_max": -0.2677975915325592,
|
| 103 |
+
"naucs_at_5_std": -0.013445545910716006,
|
| 104 |
+
"naucs_at_5_diff1": 0.03560103469628687,
|
| 105 |
+
"naucs_at_10_max": -0.2905586858742058,
|
| 106 |
+
"naucs_at_10_std": 0.0024045562548918554,
|
| 107 |
+
"naucs_at_10_diff1": -0.08824087823808019,
|
| 108 |
+
"naucs_at_20_max": -0.40897273226767533,
|
| 109 |
+
"naucs_at_20_std": -0.1138141721108663,
|
| 110 |
+
"naucs_at_20_diff1": -0.10887906242990919,
|
| 111 |
+
"naucs_at_50_max": -0.42683318222629896,
|
| 112 |
+
"naucs_at_50_std": -0.13076918365032622,
|
| 113 |
+
"naucs_at_50_diff1": -0.10724840220966861,
|
| 114 |
+
"naucs_at_100_max": -0.44961995894718576,
|
| 115 |
+
"naucs_at_100_std": -0.1844335335164004,
|
| 116 |
+
"naucs_at_100_diff1": -0.08314001637229608
|
| 117 |
+
},
|
| 118 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
|
| 119 |
+
"ndcg_at_1": 0.5125,
|
| 120 |
+
"ndcg_at_3": 0.54949,
|
| 121 |
+
"ndcg_at_5": 0.5847,
|
| 122 |
+
"ndcg_at_10": 0.61161,
|
| 123 |
+
"ndcg_at_20": 0.64415,
|
| 124 |
+
"ndcg_at_50": 0.66856,
|
| 125 |
+
"ndcg_at_100": 0.67862,
|
| 126 |
+
"map_at_1": 0.31246,
|
| 127 |
+
"map_at_3": 0.4406,
|
| 128 |
+
"map_at_5": 0.48617,
|
| 129 |
+
"map_at_10": 0.51574,
|
| 130 |
+
"map_at_20": 0.53362,
|
| 131 |
+
"map_at_50": 0.54211,
|
| 132 |
+
"map_at_100": 0.54437,
|
| 133 |
+
"recall_at_1": 0.31246,
|
| 134 |
+
"recall_at_3": 0.52965,
|
| 135 |
+
"recall_at_5": 0.6369,
|
| 136 |
+
"recall_at_10": 0.72113,
|
| 137 |
+
"recall_at_20": 0.80597,
|
| 138 |
+
"recall_at_50": 0.88539,
|
| 139 |
+
"recall_at_100": 0.92369,
|
| 140 |
+
"precision_at_1": 0.5125,
|
| 141 |
+
"precision_at_3": 0.34167,
|
| 142 |
+
"precision_at_5": 0.27,
|
| 143 |
+
"precision_at_10": 0.16937,
|
| 144 |
+
"precision_at_20": 0.105,
|
| 145 |
+
"precision_at_50": 0.04938,
|
| 146 |
+
"precision_at_100": 0.02681,
|
| 147 |
+
"mrr_at_1": 0.5375,
|
| 148 |
+
"mrr_at_3": 0.6479166666666667,
|
| 149 |
+
"mrr_at_5": 0.6663541666666666,
|
| 150 |
+
"mrr_at_10": 0.674516369047619,
|
| 151 |
+
"mrr_at_20": 0.6765751027975293,
|
| 152 |
+
"mrr_at_50": 0.6772030349370826,
|
| 153 |
+
"mrr_at_100": 0.677426534298513,
|
| 154 |
+
"naucs_at_1_max": 0.34895314898857854,
|
| 155 |
+
"naucs_at_1_std": -0.07257942064683737,
|
| 156 |
+
"naucs_at_1_diff1": 0.5293978708686925,
|
| 157 |
+
"naucs_at_3_max": 0.18142528545936487,
|
| 158 |
+
"naucs_at_3_std": -0.16137866300838627,
|
| 159 |
+
"naucs_at_3_diff1": -0.0014234288130872189,
|
| 160 |
+
"naucs_at_5_max": 0.014672569636598775,
|
| 161 |
+
"naucs_at_5_std": -0.21002767017155474,
|
| 162 |
+
"naucs_at_5_diff1": -0.1473381294964024,
|
| 163 |
+
"naucs_at_10_max": -0.06629123564607431,
|
| 164 |
+
"naucs_at_10_std": -0.2046018497631402,
|
| 165 |
+
"naucs_at_10_diff1": -0.252293405519212,
|
| 166 |
+
"naucs_at_20_max": -0.16779142727147645,
|
| 167 |
+
"naucs_at_20_std": -0.1998645631632962,
|
| 168 |
+
"naucs_at_20_diff1": -0.3377181009216048,
|
| 169 |
+
"naucs_at_50_max": -0.2319362541617097,
|
| 170 |
+
"naucs_at_50_std": -0.20139508212155197,
|
| 171 |
+
"naucs_at_50_diff1": -0.35750220388740067,
|
| 172 |
+
"naucs_at_100_max": -0.26209531433075695,
|
| 173 |
+
"naucs_at_100_std": -0.19593561386651334,
|
| 174 |
+
"naucs_at_100_diff1": -0.36382106679824544
|
| 175 |
+
},
|
| 176 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
|
| 177 |
+
"ndcg_at_1": 0.47368,
|
| 178 |
+
"ndcg_at_3": 0.48077,
|
| 179 |
+
"ndcg_at_5": 0.51913,
|
| 180 |
+
"ndcg_at_10": 0.55339,
|
| 181 |
+
"ndcg_at_20": 0.58423,
|
| 182 |
+
"ndcg_at_50": 0.62437,
|
| 183 |
+
"ndcg_at_100": 0.63473,
|
| 184 |
+
"map_at_1": 0.22899,
|
| 185 |
+
"map_at_3": 0.33833,
|
| 186 |
+
"map_at_5": 0.38792,
|
| 187 |
+
"map_at_10": 0.4251,
|
| 188 |
+
"map_at_20": 0.44759,
|
| 189 |
+
"map_at_50": 0.46783,
|
| 190 |
+
"map_at_100": 0.47287,
|
| 191 |
+
"recall_at_1": 0.22899,
|
| 192 |
+
"recall_at_3": 0.42834,
|
| 193 |
+
"recall_at_5": 0.54461,
|
| 194 |
+
"recall_at_10": 0.66769,
|
| 195 |
+
"recall_at_20": 0.77688,
|
| 196 |
+
"recall_at_50": 0.90877,
|
| 197 |
+
"recall_at_100": 0.93622,
|
| 198 |
+
"precision_at_1": 0.47368,
|
| 199 |
+
"precision_at_3": 0.32164,
|
| 200 |
+
"precision_at_5": 0.27719,
|
| 201 |
+
"precision_at_10": 0.18772,
|
| 202 |
+
"precision_at_20": 0.12193,
|
| 203 |
+
"precision_at_50": 0.06667,
|
| 204 |
+
"precision_at_100": 0.03702,
|
| 205 |
+
"mrr_at_1": 0.47368421052631576,
|
| 206 |
+
"mrr_at_3": 0.5994152046783625,
|
| 207 |
+
"mrr_at_5": 0.6152046783625732,
|
| 208 |
+
"mrr_at_10": 0.622270955165692,
|
| 209 |
+
"mrr_at_20": 0.6259990253411306,
|
| 210 |
+
"mrr_at_50": 0.6267578992701391,
|
| 211 |
+
"mrr_at_100": 0.6267578992701391,
|
| 212 |
+
"naucs_at_1_max": -0.3156199695209114,
|
| 213 |
+
"naucs_at_1_std": -0.26486119453698037,
|
| 214 |
+
"naucs_at_1_diff1": 0.11795422382927509,
|
| 215 |
+
"naucs_at_3_max": -0.2735188964882074,
|
| 216 |
+
"naucs_at_3_std": -0.23310566021944892,
|
| 217 |
+
"naucs_at_3_diff1": -0.19449853074061657,
|
| 218 |
+
"naucs_at_5_max": -0.2421479017067623,
|
| 219 |
+
"naucs_at_5_std": -0.13869753650963065,
|
| 220 |
+
"naucs_at_5_diff1": -0.3054740364166881,
|
| 221 |
+
"naucs_at_10_max": -0.25873997567219825,
|
| 222 |
+
"naucs_at_10_std": -0.1458966410575204,
|
| 223 |
+
"naucs_at_10_diff1": -0.3032000489911622,
|
| 224 |
+
"naucs_at_20_max": -0.3256819936368209,
|
| 225 |
+
"naucs_at_20_std": -0.21934883184399268,
|
| 226 |
+
"naucs_at_20_diff1": -0.3948318811395443,
|
| 227 |
+
"naucs_at_50_max": -0.3584500031494027,
|
| 228 |
+
"naucs_at_50_std": -0.21644313778125723,
|
| 229 |
+
"naucs_at_50_diff1": -0.4136042140657271,
|
| 230 |
+
"naucs_at_100_max": -0.3530688199691307,
|
| 231 |
+
"naucs_at_100_std": -0.19076877127775468,
|
| 232 |
+
"naucs_at_100_diff1": -0.42236105076593466
|
| 233 |
+
},
|
| 234 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
|
| 235 |
+
"ndcg_at_1": 0.49561,
|
| 236 |
+
"ndcg_at_3": 0.51051,
|
| 237 |
+
"ndcg_at_5": 0.53966,
|
| 238 |
+
"ndcg_at_10": 0.57033,
|
| 239 |
+
"ndcg_at_20": 0.60598,
|
| 240 |
+
"ndcg_at_50": 0.6415,
|
| 241 |
+
"ndcg_at_100": 0.65306,
|
| 242 |
+
"map_at_1": 0.24154,
|
| 243 |
+
"map_at_3": 0.36508,
|
| 244 |
+
"map_at_5": 0.40846,
|
| 245 |
+
"map_at_10": 0.445,
|
| 246 |
+
"map_at_20": 0.46996,
|
| 247 |
+
"map_at_50": 0.48868,
|
| 248 |
+
"map_at_100": 0.49392,
|
| 249 |
+
"recall_at_1": 0.24154,
|
| 250 |
+
"recall_at_3": 0.46057,
|
| 251 |
+
"recall_at_5": 0.5649,
|
| 252 |
+
"recall_at_10": 0.67685,
|
| 253 |
+
"recall_at_20": 0.79962,
|
| 254 |
+
"recall_at_50": 0.91497,
|
| 255 |
+
"recall_at_100": 0.94749,
|
| 256 |
+
"precision_at_1": 0.49561,
|
| 257 |
+
"precision_at_3": 0.34649,
|
| 258 |
+
"precision_at_5": 0.2807,
|
| 259 |
+
"precision_at_10": 0.19079,
|
| 260 |
+
"precision_at_20": 0.12544,
|
| 261 |
+
"precision_at_50": 0.06693,
|
| 262 |
+
"precision_at_100": 0.03737,
|
| 263 |
+
"mrr_at_1": 0.4692982456140351,
|
| 264 |
+
"mrr_at_3": 0.6052631578947368,
|
| 265 |
+
"mrr_at_5": 0.618421052631579,
|
| 266 |
+
"mrr_at_10": 0.6259433305485937,
|
| 267 |
+
"mrr_at_20": 0.630267555040449,
|
| 268 |
+
"mrr_at_50": 0.6310822394721419,
|
| 269 |
+
"mrr_at_100": 0.6311605602741469,
|
| 270 |
+
"naucs_at_1_max": -0.27139902693937923,
|
| 271 |
+
"naucs_at_1_std": -0.28335975541834757,
|
| 272 |
+
"naucs_at_1_diff1": 0.03844931932885215,
|
| 273 |
+
"naucs_at_3_max": -0.2333237939707581,
|
| 274 |
+
"naucs_at_3_std": -0.1653044765750373,
|
| 275 |
+
"naucs_at_3_diff1": -0.10443046117117412,
|
| 276 |
+
"naucs_at_5_max": -0.19561866039792095,
|
| 277 |
+
"naucs_at_5_std": -0.09561859939322022,
|
| 278 |
+
"naucs_at_5_diff1": -0.18423887457809085,
|
| 279 |
+
"naucs_at_10_max": -0.2060244561628858,
|
| 280 |
+
"naucs_at_10_std": -0.08726363088972981,
|
| 281 |
+
"naucs_at_10_diff1": -0.20492069680185956,
|
| 282 |
+
"naucs_at_20_max": -0.25096317818789565,
|
| 283 |
+
"naucs_at_20_std": -0.12216017305154458,
|
| 284 |
+
"naucs_at_20_diff1": -0.26997057451690837,
|
| 285 |
+
"naucs_at_50_max": -0.30710698032302514,
|
| 286 |
+
"naucs_at_50_std": -0.13529052277664438,
|
| 287 |
+
"naucs_at_50_diff1": -0.29528418472148443,
|
| 288 |
+
"naucs_at_100_max": -0.3124105461583974,
|
| 289 |
+
"naucs_at_100_std": -0.11726920470788517,
|
| 290 |
+
"naucs_at_100_diff1": -0.2735365969618431
|
| 291 |
+
},
|
| 292 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
|
| 293 |
+
"ndcg_at_1": 0.50938,
|
| 294 |
+
"ndcg_at_3": 0.53068,
|
| 295 |
+
"ndcg_at_5": 0.55676,
|
| 296 |
+
"ndcg_at_10": 0.58653,
|
| 297 |
+
"ndcg_at_20": 0.61833,
|
| 298 |
+
"ndcg_at_50": 0.64235,
|
| 299 |
+
"ndcg_at_100": 0.6544,
|
| 300 |
+
"map_at_1": 0.31519,
|
| 301 |
+
"map_at_3": 0.42911,
|
| 302 |
+
"map_at_5": 0.46586,
|
| 303 |
+
"map_at_10": 0.49473,
|
| 304 |
+
"map_at_20": 0.51197,
|
| 305 |
+
"map_at_50": 0.52001,
|
| 306 |
+
"map_at_100": 0.52243,
|
| 307 |
+
"recall_at_1": 0.31519,
|
| 308 |
+
"recall_at_3": 0.50707,
|
| 309 |
+
"recall_at_5": 0.59431,
|
| 310 |
+
"recall_at_10": 0.68853,
|
| 311 |
+
"recall_at_20": 0.77673,
|
| 312 |
+
"recall_at_50": 0.8526,
|
| 313 |
+
"recall_at_100": 0.8999,
|
| 314 |
+
"precision_at_1": 0.50938,
|
| 315 |
+
"precision_at_3": 0.325,
|
| 316 |
+
"precision_at_5": 0.25125,
|
| 317 |
+
"precision_at_10": 0.16016,
|
| 318 |
+
"precision_at_20": 0.09891,
|
| 319 |
+
"precision_at_50": 0.04688,
|
| 320 |
+
"precision_at_100": 0.02587,
|
| 321 |
+
"mrr_at_1": 0.5234375,
|
| 322 |
+
"mrr_at_3": 0.6184895833333333,
|
| 323 |
+
"mrr_at_5": 0.6364583333333333,
|
| 324 |
+
"mrr_at_10": 0.6463244047619048,
|
| 325 |
+
"mrr_at_20": 0.6495780415378181,
|
| 326 |
+
"mrr_at_50": 0.6503474764286958,
|
| 327 |
+
"mrr_at_100": 0.6505948135497464,
|
| 328 |
+
"naucs_at_1_max": 0.4131418193131225,
|
| 329 |
+
"naucs_at_1_std": 0.06757995282919683,
|
| 330 |
+
"naucs_at_1_diff1": 0.516900768942945,
|
| 331 |
+
"naucs_at_3_max": 0.18254564757418557,
|
| 332 |
+
"naucs_at_3_std": -0.04347712846310109,
|
| 333 |
+
"naucs_at_3_diff1": 0.03059708341704999,
|
| 334 |
+
"naucs_at_5_max": 0.06972269700281146,
|
| 335 |
+
"naucs_at_5_std": -0.10787077250693489,
|
| 336 |
+
"naucs_at_5_diff1": -0.08493373308302267,
|
| 337 |
+
"naucs_at_10_max": -0.023642522063642934,
|
| 338 |
+
"naucs_at_10_std": -0.11714079374203694,
|
| 339 |
+
"naucs_at_10_diff1": -0.17673365636114774,
|
| 340 |
+
"naucs_at_20_max": -0.09569239071775491,
|
| 341 |
+
"naucs_at_20_std": -0.11183756071235801,
|
| 342 |
+
"naucs_at_20_diff1": -0.241802482460874,
|
| 343 |
+
"naucs_at_50_max": -0.1488266985733028,
|
| 344 |
+
"naucs_at_50_std": -0.11009165758378252,
|
| 345 |
+
"naucs_at_50_diff1": -0.2751290287492702,
|
| 346 |
+
"naucs_at_100_max": -0.18389216502938294,
|
| 347 |
+
"naucs_at_100_std": -0.1152902550355418,
|
| 348 |
+
"naucs_at_100_diff1": -0.2899356806702993
|
| 349 |
+
},
|
| 350 |
+
"vidore/synthetic_axa_filtered_v1.0": {
|
| 351 |
+
"ndcg_at_1": 0.5,
|
| 352 |
+
"ndcg_at_3": 0.59177,
|
| 353 |
+
"ndcg_at_5": 0.56037,
|
| 354 |
+
"ndcg_at_10": 0.56184,
|
| 355 |
+
"ndcg_at_20": 0.56464,
|
| 356 |
+
"ndcg_at_50": 0.62655,
|
| 357 |
+
"ndcg_at_100": 0.64607,
|
| 358 |
+
"map_at_1": 0.18432,
|
| 359 |
+
"map_at_3": 0.35086,
|
| 360 |
+
"map_at_5": 0.37963,
|
| 361 |
+
"map_at_10": 0.4161,
|
| 362 |
+
"map_at_20": 0.42647,
|
| 363 |
+
"map_at_50": 0.45181,
|
| 364 |
+
"map_at_100": 0.45911,
|
| 365 |
+
"recall_at_1": 0.18432,
|
| 366 |
+
"recall_at_3": 0.54724,
|
| 367 |
+
"recall_at_5": 0.58705,
|
| 368 |
+
"recall_at_10": 0.68342,
|
| 369 |
+
"recall_at_20": 0.7113,
|
| 370 |
+
"recall_at_50": 0.88439,
|
| 371 |
+
"recall_at_100": 0.9347,
|
| 372 |
+
"precision_at_1": 0.5,
|
| 373 |
+
"precision_at_3": 0.44444,
|
| 374 |
+
"precision_at_5": 0.33333,
|
| 375 |
+
"precision_at_10": 0.21667,
|
| 376 |
+
"precision_at_20": 0.12222,
|
| 377 |
+
"precision_at_50": 0.07333,
|
| 378 |
+
"precision_at_100": 0.04278,
|
| 379 |
+
"mrr_at_1": 0.5,
|
| 380 |
+
"mrr_at_3": 0.6296296296296297,
|
| 381 |
+
"mrr_at_5": 0.6574074074074074,
|
| 382 |
+
"mrr_at_10": 0.6574074074074074,
|
| 383 |
+
"mrr_at_20": 0.6574074074074074,
|
| 384 |
+
"mrr_at_50": 0.658641975308642,
|
| 385 |
+
"mrr_at_100": 0.658641975308642,
|
| 386 |
+
"naucs_at_1_max": -0.20471943280726257,
|
| 387 |
+
"naucs_at_1_std": 0.18546089088182968,
|
| 388 |
+
"naucs_at_1_diff1": 0.7445083027491819,
|
| 389 |
+
"naucs_at_3_max": -0.5294402069183541,
|
| 390 |
+
"naucs_at_3_std": -0.04763265145855668,
|
| 391 |
+
"naucs_at_3_diff1": 0.253185276095856,
|
| 392 |
+
"naucs_at_5_max": -0.669223474626299,
|
| 393 |
+
"naucs_at_5_std": -0.08636482482813103,
|
| 394 |
+
"naucs_at_5_diff1": 0.2760137984114396,
|
| 395 |
+
"naucs_at_10_max": -0.738950395976398,
|
| 396 |
+
"naucs_at_10_std": -0.1685495451706665,
|
| 397 |
+
"naucs_at_10_diff1": 0.07368539851746013,
|
| 398 |
+
"naucs_at_20_max": -0.7021396616750007,
|
| 399 |
+
"naucs_at_20_std": -0.11462769019487411,
|
| 400 |
+
"naucs_at_20_diff1": 0.07121119110741668,
|
| 401 |
+
"naucs_at_50_max": -0.7063938743299508,
|
| 402 |
+
"naucs_at_50_std": -0.15679147163325738,
|
| 403 |
+
"naucs_at_50_diff1": -0.013733388816798229,
|
| 404 |
+
"naucs_at_100_max": -0.6781868824447755,
|
| 405 |
+
"naucs_at_100_std": -0.16240281161384443,
|
| 406 |
+
"naucs_at_100_diff1": 0.04104876407606115
|
| 407 |
+
},
|
| 408 |
+
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
|
| 409 |
+
"ndcg_at_1": 0.56897,
|
| 410 |
+
"ndcg_at_3": 0.5475,
|
| 411 |
+
"ndcg_at_5": 0.531,
|
| 412 |
+
"ndcg_at_10": 0.51659,
|
| 413 |
+
"ndcg_at_20": 0.5526,
|
| 414 |
+
"ndcg_at_50": 0.62369,
|
| 415 |
+
"ndcg_at_100": 0.66764,
|
| 416 |
+
"map_at_1": 0.10475,
|
| 417 |
+
"map_at_3": 0.17297,
|
| 418 |
+
"map_at_5": 0.22022,
|
| 419 |
+
"map_at_10": 0.27707,
|
| 420 |
+
"map_at_20": 0.33372,
|
| 421 |
+
"map_at_50": 0.39288,
|
| 422 |
+
"map_at_100": 0.4226,
|
| 423 |
+
"recall_at_1": 0.10475,
|
| 424 |
+
"recall_at_3": 0.20237,
|
| 425 |
+
"recall_at_5": 0.26964,
|
| 426 |
+
"recall_at_10": 0.39933,
|
| 427 |
+
"recall_at_20": 0.56307,
|
| 428 |
+
"recall_at_50": 0.77351,
|
| 429 |
+
"recall_at_100": 0.90788,
|
| 430 |
+
"precision_at_1": 0.56897,
|
| 431 |
+
"precision_at_3": 0.5,
|
| 432 |
+
"precision_at_5": 0.46207,
|
| 433 |
+
"precision_at_10": 0.37069,
|
| 434 |
+
"precision_at_20": 0.29569,
|
| 435 |
+
"precision_at_50": 0.19034,
|
| 436 |
+
"precision_at_100": 0.12552,
|
| 437 |
+
"mrr_at_1": 0.5344827586206896,
|
| 438 |
+
"mrr_at_3": 0.6609195402298851,
|
| 439 |
+
"mrr_at_5": 0.6807471264367816,
|
| 440 |
+
"mrr_at_10": 0.6899630541871922,
|
| 441 |
+
"mrr_at_20": 0.6928555224267565,
|
| 442 |
+
"mrr_at_50": 0.6928555224267565,
|
| 443 |
+
"mrr_at_100": 0.6928555224267565,
|
| 444 |
+
"naucs_at_1_max": 0.37666507028529217,
|
| 445 |
+
"naucs_at_1_std": 0.2894204633073516,
|
| 446 |
+
"naucs_at_1_diff1": 0.06680457995462946,
|
| 447 |
+
"naucs_at_3_max": 0.20389557612636244,
|
| 448 |
+
"naucs_at_3_std": 0.31592783637688704,
|
| 449 |
+
"naucs_at_3_diff1": -0.1565134892191965,
|
| 450 |
+
"naucs_at_5_max": 0.1649976619466542,
|
| 451 |
+
"naucs_at_5_std": 0.3042431458723411,
|
| 452 |
+
"naucs_at_5_diff1": -0.1168288609207652,
|
| 453 |
+
"naucs_at_10_max": 0.1138447356410388,
|
| 454 |
+
"naucs_at_10_std": 0.25980112410460104,
|
| 455 |
+
"naucs_at_10_diff1": -0.2068349937437853,
|
| 456 |
+
"naucs_at_20_max": 0.12497036442449745,
|
| 457 |
+
"naucs_at_20_std": 0.35150590656604647,
|
| 458 |
+
"naucs_at_20_diff1": -0.16276015911506578,
|
| 459 |
+
"naucs_at_50_max": 0.04699279255355053,
|
| 460 |
+
"naucs_at_50_std": 0.3178586829010547,
|
| 461 |
+
"naucs_at_50_diff1": -0.14272426503448576,
|
| 462 |
+
"naucs_at_100_max": 0.012556213981472325,
|
| 463 |
+
"naucs_at_100_std": 0.2890479073896453,
|
| 464 |
+
"naucs_at_100_diff1": -0.14921439241536574
|
| 465 |
+
}, "tatdqa_test": {"ndcg_at_1": 0.55043, "ndcg_at_3": 0.65383, "ndcg_at_5": 0.67972, "ndcg_at_10": 0.70182, "ndcg_at_20": 0.71531, "ndcg_at_100": 0.72798, "ndcg_at_1000": 0.73147, "map_at_1": 0.55043, "map_at_3": 0.6292, "map_at_5": 0.64363, "map_at_10": 0.65292, "map_at_20": 0.6567, "map_at_100": 0.65856, "map_at_1000": 0.65873, "recall_at_1": 0.55043, "recall_at_3": 0.72479, "recall_at_5": 0.78736, "recall_at_10": 0.8548, "recall_at_20": 0.90765, "recall_at_100": 0.97448, "recall_at_1000": 1.0, "precision_at_1": 0.55043, "precision_at_3": 0.2416, "precision_at_5": 0.15747, "precision_at_10": 0.08548, "precision_at_20": 0.04538, "precision_at_100": 0.00974, "precision_at_1000": 0.001, "mrr_at_1": 0.5498177399756987, "mrr_at_3": 0.6287970838396112, "mrr_at_5": 0.6434690157958688, "mrr_at_10": 0.6530902235337229, "mrr_at_20": 0.6567284540447504, "mrr_at_100": 0.658621212229932, "mrr_at_1000": 0.6587698669596878, "naucs_at_1_max": 0.27853365504109656, "naucs_at_1_std": -0.15447634347947511, "naucs_at_1_diff1": 0.7134897043728883, "naucs_at_3_max": 0.2862020499335342, "naucs_at_3_std": -0.1406768618430069, "naucs_at_3_diff1": 0.598287834466956, "naucs_at_5_max": 0.3082772653205975, "naucs_at_5_std": -0.1336535664737251, "naucs_at_5_diff1": 0.5847681853576895, "naucs_at_10_max": 0.4156924004771727, "naucs_at_10_std": -0.012527556044571743, "naucs_at_10_diff1": 0.5762936692610346, "naucs_at_20_max": 0.39150222479435925, "naucs_at_20_std": 0.004434403605241619, "naucs_at_20_diff1": 0.5602018066874601, "naucs_at_100_max": 0.39176268171942447, "naucs_at_100_std": 0.360160411337065, "naucs_at_100_diff1": 0.6304563665269014, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shiftproject_test": {"ndcg_at_1": 0.63, "ndcg_at_3": 0.76488, "ndcg_at_5": 0.79072, "ndcg_at_10": 0.80085, "ndcg_at_20": 0.80877, "ndcg_at_100": 0.81273, "ndcg_at_1000": 0.81415, "map_at_1": 0.63, "map_at_3": 0.735, "map_at_5": 0.75, "map_at_10": 0.75444, "map_at_20": 0.75679, "map_at_100": 0.75742, "map_at_1000": 0.75749, "recall_at_1": 0.63, "recall_at_3": 0.85, "recall_at_5": 0.91, "recall_at_10": 0.94, "recall_at_20": 0.97, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.63, "precision_at_3": 0.28333, "precision_at_5": 0.182, "precision_at_10": 0.094, "precision_at_20": 0.0485, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.65, "mrr_at_3": 0.7483333333333333, "mrr_at_5": 0.7608333333333333, "mrr_at_10": 0.7663888888888889, "mrr_at_20": 0.7679646464646465, "mrr_at_100": 0.768591427091427, "mrr_at_1000": 0.7686683501683501, "naucs_at_1_max": -0.061987809273100325, "naucs_at_1_std": -0.18575972672715027, "naucs_at_1_diff1": 0.7242513984863435, "naucs_at_3_max": 0.18226488773185812, "naucs_at_3_std": -0.19902375528799124, "naucs_at_3_diff1": 0.6877969410999027, "naucs_at_5_max": -0.24074074074073906, "naucs_at_5_std": -0.7552131963896631, "naucs_at_5_diff1": 0.6890756302521003, "naucs_at_10_max": -0.3181605975723611, "naucs_at_10_std": -1.07002801120448, "naucs_at_10_diff1": 0.7005135387488336, "naucs_at_20_max": -0.7791783380018631, "naucs_at_20_std": -0.5961718020541553, "naucs_at_20_diff1": 0.401027077497665, "naucs_at_100_max": 0.554154995331464, "naucs_at_100_std": -0.17133520074697067, "naucs_at_100_diff1": 0.35807656395892007, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98131, "ndcg_at_5": 0.98131, "ndcg_at_10": 0.98131, "ndcg_at_20": 0.98131, "ndcg_at_100": 0.98321, "ndcg_at_1000": 0.98321, "map_at_1": 0.97, "map_at_3": 0.97833, "map_at_5": 0.97833, "map_at_10": 0.97833, "map_at_20": 0.97833, "map_at_100": 0.9786, "map_at_1000": 0.9786, "recall_at_1": 0.97, "recall_at_3": 0.99, "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": 0.97, "precision_at_3": 0.33, "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": 0.97, "mrr_at_3": 0.9783333333333333, "mrr_at_5": 0.9783333333333333, "mrr_at_10": 0.9783333333333333, "mrr_at_20": 0.9783333333333333, "mrr_at_100": 0.9786111111111111, "mrr_at_1000": 0.9786111111111111, "naucs_at_1_max": 0.41518829754123937, "naucs_at_1_std": -1.1517273576097102, "naucs_at_1_diff1": 0.9564270152505465, "naucs_at_3_max": 1.0, "naucs_at_3_std": -1.1517273576097802, "naucs_at_3_diff1": 1.0, "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_test": {"ndcg_at_1": 0.89, "ndcg_at_3": 0.94786, "ndcg_at_5": 0.94786, "ndcg_at_10": 0.95142, "ndcg_at_20": 0.95142, "ndcg_at_100": 0.95142, "ndcg_at_1000": 0.95142, "map_at_1": 0.89, "map_at_3": 0.93333, "map_at_5": 0.93333, "map_at_10": 0.935, "map_at_20": 0.935, "map_at_100": 0.935, "map_at_1000": 0.935, "recall_at_1": 0.89, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.89, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.89, "mrr_at_3": 0.935, "mrr_at_5": 0.937, "mrr_at_10": 0.937, "mrr_at_20": 0.937, "mrr_at_100": 0.937, "mrr_at_1000": 0.937, "naucs_at_1_max": 0.5626234859548148, "naucs_at_1_std": 0.3716175586289838, "naucs_at_1_diff1": 0.834850957821493, "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}, "arxivqa_test_subsampled": {"ndcg_at_1": 0.702, "ndcg_at_3": 0.76743, "ndcg_at_5": 0.77991, "ndcg_at_10": 0.79468, "ndcg_at_20": 0.80462, "ndcg_at_100": 0.8145, "ndcg_at_1000": 0.81657, "map_at_1": 0.702, "map_at_3": 0.75133, "map_at_5": 0.75833, "map_at_10": 0.76436, "map_at_20": 0.767, "map_at_100": 0.76831, "map_at_1000": 0.76839, "recall_at_1": 0.702, "recall_at_3": 0.814, "recall_at_5": 0.844, "recall_at_10": 0.89, "recall_at_20": 0.93, "recall_at_100": 0.984, "recall_at_1000": 1.0, "precision_at_1": 0.702, "precision_at_3": 0.27133, "precision_at_5": 0.1688, "precision_at_10": 0.089, "precision_at_20": 0.0465, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.7, "mrr_at_3": 0.7506666666666666, "mrr_at_5": 0.7575666666666667, "mrr_at_10": 0.76395, "mrr_at_20": 0.7664683712486344, "mrr_at_100": 0.7677856040474413, "mrr_at_1000": 0.767866298103699, "naucs_at_1_max": 0.6661847878465089, "naucs_at_1_std": -0.217519374789405, "naucs_at_1_diff1": 0.9071749220117173, "naucs_at_3_max": 0.697658762809486, "naucs_at_3_std": -0.18659371894467894, "naucs_at_3_diff1": 0.839073335969141, "naucs_at_5_max": 0.7447876108417706, "naucs_at_5_std": -0.17636087316938498, "naucs_at_5_diff1": 0.8526087065738912, "naucs_at_10_max": 0.7873636285542479, "naucs_at_10_std": -0.15812215445408626, "naucs_at_10_diff1": 0.8351945709131511, "naucs_at_20_max": 0.7746565292783784, "naucs_at_20_std": -0.23473389355742383, "naucs_at_20_diff1": 0.8061224489795931, "naucs_at_100_max": 0.8027544351073763, "naucs_at_100_std": 0.2001050420168152, "naucs_at_100_diff1": 0.7639472455648932, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_test_subsampled": {"ndcg_at_1": 0.49446, "ndcg_at_3": 0.54968, "ndcg_at_5": 0.57172, "ndcg_at_10": 0.59184, "ndcg_at_20": 0.60528, "ndcg_at_100": 0.62838, "ndcg_at_1000": 0.64353, "map_at_1": 0.49446, "map_at_3": 0.53585, "map_at_5": 0.54815, "map_at_10": 0.55648, "map_at_20": 0.56018, "map_at_100": 0.56326, "map_at_1000": 0.56389, "recall_at_1": 0.49446, "recall_at_3": 0.5898, "recall_at_5": 0.64302, "recall_at_10": 0.7051, "recall_at_20": 0.75831, "recall_at_100": 0.8847, "recall_at_1000": 1.0, "precision_at_1": 0.49446, "precision_at_3": 0.1966, "precision_at_5": 0.1286, "precision_at_10": 0.07051, "precision_at_20": 0.03792, "precision_at_100": 0.00885, "precision_at_1000": 0.001, "mrr_at_1": 0.49223946784922396, "mrr_at_3": 0.5339985218033999, "mrr_at_5": 0.5473022912047303, "mrr_at_10": 0.5553206278816035, "mrr_at_20": 0.5589821565391849, "mrr_at_100": 0.5619819074681309, "mrr_at_1000": 0.5626456935597429, "naucs_at_1_max": 0.32878731695222985, "naucs_at_1_std": 0.15591990126747984, "naucs_at_1_diff1": 0.8493613636054403, "naucs_at_3_max": 0.23098165064202703, "naucs_at_3_std": 0.1729343384390047, "naucs_at_3_diff1": 0.79653911998206, "naucs_at_5_max": 0.20443193032581358, "naucs_at_5_std": 0.22886452804275878, "naucs_at_5_diff1": 0.7709831107458899, "naucs_at_10_max": 0.11430383031823631, "naucs_at_10_std": 0.3505331687518112, "naucs_at_10_diff1": 0.7655459781075918, "naucs_at_20_max": 0.06375294772557255, "naucs_at_20_std": 0.47875225635393476, "naucs_at_20_diff1": 0.7402047132383933, "naucs_at_100_max": -0.17203513994521832, "naucs_at_100_std": 0.719961371895444, "naucs_at_100_diff1": 0.7516431118242167, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.94, "ndcg_at_3": 0.96262, "ndcg_at_5": 0.96693, "ndcg_at_10": 0.96693, "ndcg_at_20": 0.96948, "ndcg_at_100": 0.96948, "ndcg_at_1000": 0.96948, "map_at_1": 0.94, "map_at_3": 0.95667, "map_at_5": 0.95917, "map_at_10": 0.95917, "map_at_20": 0.95988, "map_at_100": 0.95988, "map_at_1000": 0.95988, "recall_at_1": 0.94, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "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": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.96, "mrr_at_3": 0.9683333333333333, "mrr_at_5": 0.9708333333333333, "mrr_at_10": 0.9708333333333333, "mrr_at_20": 0.971547619047619, "mrr_at_100": 0.971547619047619, "mrr_at_1000": 0.971547619047619, "naucs_at_1_max": 0.4701991907874248, "naucs_at_1_std": -0.2544351073762836, "naucs_at_1_diff1": 0.9319172113289763, "naucs_at_3_max": -0.004668534080301393, "naucs_at_3_std": -0.5088702147525775, "naucs_at_3_diff1": 0.7957516339869218, "naucs_at_5_max": -0.5634920634920767, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.7222222222222276, "naucs_at_10_max": -0.5634920634920767, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.7222222222222276, "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}, "infovqa_test_subsampled": {"ndcg_at_1": 0.76518, "ndcg_at_3": 0.81846, "ndcg_at_5": 0.82779, "ndcg_at_10": 0.84084, "ndcg_at_20": 0.8454, "ndcg_at_100": 0.85306, "ndcg_at_1000": 0.85616, "map_at_1": 0.76518, "map_at_3": 0.80601, "map_at_5": 0.81127, "map_at_10": 0.81663, "map_at_20": 0.81786, "map_at_100": 0.81898, "map_at_1000": 0.81909, "recall_at_1": 0.76518, "recall_at_3": 0.85425, "recall_at_5": 0.87652, "recall_at_10": 0.917, "recall_at_20": 0.93522, "recall_at_100": 0.97571, "recall_at_1000": 1.0, "precision_at_1": 0.76518, "precision_at_3": 0.28475, "precision_at_5": 0.1753, "precision_at_10": 0.0917, "precision_at_20": 0.04676, "precision_at_100": 0.00976, "precision_at_1000": 0.001, "mrr_at_1": 0.7672064777327935, "mrr_at_3": 0.8076923076923077, "mrr_at_5": 0.8130566801619433, "mrr_at_10": 0.8183712486344065, "mrr_at_20": 0.8196021674007504, "mrr_at_100": 0.8207219702130965, "mrr_at_1000": 0.8208340179158132, "naucs_at_1_max": 0.526736932815251, "naucs_at_1_std": -0.08005662601905021, "naucs_at_1_diff1": 0.8906383040101385, "naucs_at_3_max": 0.5628217589502187, "naucs_at_3_std": 0.07419124093710198, "naucs_at_3_diff1": 0.819273316147957, "naucs_at_5_max": 0.6142211700114351, "naucs_at_5_std": 0.13484006376865668, "naucs_at_5_diff1": 0.7974348993177082, "naucs_at_10_max": 0.5107732925204674, "naucs_at_10_std": 0.08282924765220158, "naucs_at_10_diff1": 0.7501472816409511, "naucs_at_20_max": 0.6069714717598735, "naucs_at_20_std": 0.24818260935350467, "naucs_at_20_diff1": 0.7972653744711068, "naucs_at_100_max": 0.7715054503371943, "naucs_at_100_std": 0.6498035527508992, "naucs_at_100_diff1": 0.7627810617053321, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.95155, "ndcg_at_5": 0.95155, "ndcg_at_10": 0.95155, "ndcg_at_20": 0.95425, "ndcg_at_100": 0.95618, "ndcg_at_1000": 0.95745, "map_at_1": 0.92, "map_at_3": 0.945, "map_at_5": 0.945, "map_at_10": 0.945, "map_at_20": 0.94583, "map_at_100": 0.94612, "map_at_1000": 0.94616, "recall_at_1": 0.92, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.945, "mrr_at_5": 0.945, "mrr_at_10": 0.945, "mrr_at_20": 0.9458333333333333, "mrr_at_100": 0.9461190476190476, "mrr_at_1000": 0.9461614205004035, "naucs_at_1_max": 0.5274859943977597, "naucs_at_1_std": -0.6526027077497683, "naucs_at_1_diff1": 0.9673202614379083, "naucs_at_3_max": 0.807812013694371, "naucs_at_3_std": -1.1517273576097098, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.807812013694364, "naucs_at_5_std": -1.1517273576097071, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.807812013694364, "naucs_at_10_std": -1.1517273576097071, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.9346405228758136, "naucs_at_20_std": -0.8576097105508901, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": -0.5634920634920583, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tabfquad_test_subsampled": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.88465, "ndcg_at_5": 0.89664, "ndcg_at_10": 0.90491, "ndcg_at_20": 0.91464, "ndcg_at_100": 0.91464, "ndcg_at_1000": 0.91464, "map_at_1": 0.85, "map_at_3": 0.87679, "map_at_5": 0.88357, "map_at_10": 0.8871, "map_at_20": 0.88966, "map_at_100": 0.88966, "map_at_1000": 0.88966, "recall_at_1": 0.85, "recall_at_3": 0.90714, "recall_at_5": 0.93571, "recall_at_10": 0.96071, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.30238, "precision_at_5": 0.18714, "precision_at_10": 0.09607, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.85, "mrr_at_3": 0.8779761904761905, "mrr_at_5": 0.8838690476190476, "mrr_at_10": 0.8874900793650794, "mrr_at_20": 0.8898663632119514, "mrr_at_100": 0.8900364312391623, "mrr_at_1000": 0.8900364312391623, "naucs_at_1_max": 0.6249012133327131, "naucs_at_1_std": 0.27568453349449135, "naucs_at_1_diff1": 0.851971084561387, "naucs_at_3_max": 0.7154528478057898, "naucs_at_3_std": 0.3263664440135032, "naucs_at_3_diff1": 0.8540364863894296, "naucs_at_5_max": 0.7756769374416456, "naucs_at_5_std": 0.5388525780682669, "naucs_at_5_diff1": 0.8674914410208527, "naucs_at_10_max": 0.7903403785756714, "naucs_at_10_std": 0.6866564807741266, "naucs_at_10_diff1": 0.832187420422716, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "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}}
|