QuentinJG commited on
Commit
1aa9325
·
verified ·
1 Parent(s): 8fc03a3

Update results.json

Browse files
Files changed (1) hide show
  1. results.json +465 -1
results.json CHANGED
@@ -1 +1,465 @@
1
- {"./data_dir/eval_vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.67, "ndcg_at_3": 0.73664, "ndcg_at_5": 0.74886, "ndcg_at_10": 0.76608, "ndcg_at_20": 0.77508, "ndcg_at_50": 0.78465, "ndcg_at_100": 0.78928, "map_at_1": 0.67, "map_at_3": 0.71967, "map_at_5": 0.72637, "map_at_10": 0.73332, "map_at_20": 0.73575, "map_at_50": 0.7373, "map_at_100": 0.73774, "recall_at_1": 0.67, "recall_at_3": 0.786, "recall_at_5": 0.816, "recall_at_10": 0.87, "recall_at_20": 0.906, "recall_at_50": 0.954, "recall_at_100": 0.982, "precision_at_1": 0.67, "precision_at_3": 0.262, "precision_at_5": 0.1632, "precision_at_10": 0.087, "precision_at_20": 0.0453, "precision_at_50": 0.01908, "precision_at_100": 0.00982, "mrr_at_1": 0.674, "mrr_at_3": 0.723, "mrr_at_5": 0.7291, "mrr_at_10": 0.7366095238095238, "mrr_at_20": 0.7391611043325439, "mrr_at_50": 0.7409444251953623, "mrr_at_100": 0.7413271325461593, "naucs_at_1_max": 0.5444803710788707, "naucs_at_1_std": -0.09109715427197845, "naucs_at_1_diff1": 0.9253203771732317, "naucs_at_3_max": 0.5919376009932287, "naucs_at_3_std": -0.04496538390458086, "naucs_at_3_diff1": 0.8649522103597137, "naucs_at_5_max": 0.6306070025471655, "naucs_at_5_std": 0.001678323187842219, "naucs_at_5_diff1": 0.8645469067046583, "naucs_at_10_max": 0.6801229356439317, "naucs_at_10_std": 0.03928756572613559, "naucs_at_10_diff1": 0.8395171443382958, "naucs_at_20_max": 0.7005979696843283, "naucs_at_20_std": 0.04557283906470355, "naucs_at_20_diff1": 0.8023322804299033, "naucs_at_50_max": 0.7126212803962136, "naucs_at_50_std": -0.09452766613891975, "naucs_at_50_diff1": 0.8312223440100683, "naucs_at_100_max": 0.85968461458657, "naucs_at_100_std": -0.10281149496835222, "naucs_at_100_diff1": 0.896514161220045}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.50554, "ndcg_at_3": 0.55831, "ndcg_at_5": 0.58055, "ndcg_at_10": 0.60677, "ndcg_at_20": 0.62553, "ndcg_at_50": 0.63388, "ndcg_at_100": 0.64093, "map_at_1": 0.50554, "map_at_3": 0.54582, "map_at_5": 0.55835, "map_at_10": 0.569, "map_at_20": 0.5743, "map_at_50": 0.57564, "map_at_100": 0.57622, "recall_at_1": 0.50554, "recall_at_3": 0.59424, "recall_at_5": 0.64745, "recall_at_10": 0.72949, "recall_at_20": 0.80266, "recall_at_50": 0.84479, "recall_at_100": 0.88914, "precision_at_1": 0.50554, "precision_at_3": 0.19808, "precision_at_5": 0.12949, "precision_at_10": 0.07295, "precision_at_20": 0.04013, "precision_at_50": 0.0169, "precision_at_100": 0.00889, "mrr_at_1": 0.5033259423503326, "mrr_at_3": 0.5476718403547672, "mrr_at_5": 0.5574279379157429, "mrr_at_10": 0.5684528208918452, "mrr_at_20": 0.573404311645784, "mrr_at_50": 0.5749334030411379, "mrr_at_100": 0.575603354450426, "naucs_at_1_max": 0.2625490776539377, "naucs_at_1_std": 0.3310850636640096, "naucs_at_1_diff1": 0.8285865433933254, "naucs_at_3_max": 0.18953190824386826, "naucs_at_3_std": 0.38629715857674524, "naucs_at_3_diff1": 0.769918430991528, "naucs_at_5_max": 0.14915660669648698, "naucs_at_5_std": 0.39060413735358934, "naucs_at_5_diff1": 0.7373299633405666, "naucs_at_10_max": 0.008734548704545675, "naucs_at_10_std": 0.5053066426323437, "naucs_at_10_diff1": 0.7260812769949216, "naucs_at_20_max": -0.1110192872274276, "naucs_at_20_std": 0.6213072109985829, "naucs_at_20_diff1": 0.6964830158995551, "naucs_at_50_max": -0.16049662657697744, "naucs_at_50_std": 0.7364897688356142, "naucs_at_50_diff1": 0.7182771454403309, "naucs_at_100_max": -0.19221684927376187, "naucs_at_100_std": 0.8505984612548488, "naucs_at_100_diff1": 0.7419613287710981}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.93417, "ndcg_at_5": 0.93847, "ndcg_at_10": 0.93847, "ndcg_at_20": 0.93847, "ndcg_at_50": 0.94063, "ndcg_at_100": 0.9422, "map_at_1": 0.88, "map_at_3": 0.92167, "map_at_5": 0.92417, "map_at_10": 0.92417, "map_at_20": 0.92417, "map_at_50": 0.92458, "map_at_100": 0.92471, "recall_at_1": 0.88, "recall_at_3": 0.97, "recall_at_5": 0.98, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.32333, "precision_at_5": 0.196, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.89, "mrr_at_3": 0.93, "mrr_at_5": 0.9325, "mrr_at_10": 0.9325, "mrr_at_20": 0.9325, "mrr_at_50": 0.9329166666666667, "mrr_at_100": 0.9330448717948718, "naucs_at_1_max": 0.36497772828507796, "naucs_at_1_std": -0.272231944002546, "naucs_at_1_diff1": 0.9777282850779508, "naucs_at_3_max": 0.693432928727046, "naucs_at_3_std": -0.15452847805789072, "naucs_at_3_diff1": 0.9564270152505466, "naucs_at_5_max": 0.6790382819794609, "naucs_at_5_std": -0.5929038281979465, "naucs_at_5_diff1": 0.9346405228758136, "naucs_at_10_max": 0.6790382819794609, "naucs_at_10_std": -0.5929038281979465, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.6790382819794609, "naucs_at_20_std": -0.5929038281979465, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.554154995331464, "naucs_at_50_diff1": 0.8692810457516374, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tatdqa_test": {"ndcg_at_1": 0.64581, "ndcg_at_3": 0.73981, "ndcg_at_5": 0.7668, "ndcg_at_10": 0.787, "ndcg_at_20": 0.79364, "ndcg_at_50": 0.79698, "ndcg_at_100": 0.79864, "map_at_1": 0.64581, "map_at_3": 0.71648, "map_at_5": 0.73158, "map_at_10": 0.74001, "map_at_20": 0.74185, "map_at_50": 0.74242, "map_at_100": 0.74256, "recall_at_1": 0.64581, "recall_at_3": 0.80741, "recall_at_5": 0.87242, "recall_at_10": 0.93439, "recall_at_20": 0.96051, "recall_at_50": 0.97691, "recall_at_100": 0.98724, "precision_at_1": 0.64581, "precision_at_3": 0.26914, "precision_at_5": 0.17448, "precision_at_10": 0.09344, "precision_at_20": 0.04803, "precision_at_50": 0.01954, "precision_at_100": 0.00987, "mrr_at_1": 0.6433778857837181, "mrr_at_3": 0.7150668286755771, "mrr_at_5": 0.7304981773997571, "mrr_at_10": 0.7387049412717699, "mrr_at_20": 0.7404579555191415, "mrr_at_50": 0.7410660643728302, "mrr_at_100": 0.7412038533898355, "naucs_at_1_max": 0.13431737923823708, "naucs_at_1_std": -0.3067075571650227, "naucs_at_1_diff1": 0.8067592167032371, "naucs_at_3_max": 0.18727434840097998, "naucs_at_3_std": -0.27607320609227726, "naucs_at_3_diff1": 0.6950163190033429, "naucs_at_5_max": 0.2109382115959134, "naucs_at_5_std": -0.22542299636024854, "naucs_at_5_diff1": 0.6560772753501689, "naucs_at_10_max": 0.3049581820340452, "naucs_at_10_std": 0.10695854160572203, "naucs_at_10_diff1": 0.5979569201987198, "naucs_at_20_max": 0.3524427577390326, "naucs_at_20_std": 0.2838037847480218, "naucs_at_20_diff1": 0.5748977828288308, "naucs_at_50_max": 0.39877531195470334, "naucs_at_50_std": 0.47760692333540594, "naucs_at_50_diff1": 0.48464495157589027, "naucs_at_100_max": 0.3531041790707774, "naucs_at_100_std": 0.4303621036969795, "naucs_at_100_diff1": 0.42655633089874984}, "./data_dir/eval_vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.80769, "ndcg_at_3": 0.86119, "ndcg_at_5": 0.86799, "ndcg_at_10": 0.87508, "ndcg_at_20": 0.8788, "ndcg_at_50": 0.88321, "ndcg_at_100": 0.88418, "map_at_1": 0.80769, "map_at_3": 0.84818, "map_at_5": 0.85202, "map_at_10": 0.85488, "map_at_20": 0.85598, "map_at_50": 0.85668, "map_at_100": 0.85677, "recall_at_1": 0.80769, "recall_at_3": 0.89879, "recall_at_5": 0.91498, "recall_at_10": 0.93725, "recall_at_20": 0.95142, "recall_at_50": 0.97368, "recall_at_100": 0.97976, "precision_at_1": 0.80769, "precision_at_3": 0.2996, "precision_at_5": 0.183, "precision_at_10": 0.09372, "precision_at_20": 0.04757, "precision_at_50": 0.01947, "precision_at_100": 0.0098, "mrr_at_1": 0.8117408906882592, "mrr_at_3": 0.8488529014844804, "mrr_at_5": 0.8532051282051283, "mrr_at_10": 0.8560359231411864, "mrr_at_20": 0.8570996255206782, "mrr_at_50": 0.8577900744824616, "mrr_at_100": 0.8578711146551276, "naucs_at_1_max": 0.5181292739994149, "naucs_at_1_std": -0.12587128411667012, "naucs_at_1_diff1": 0.9118360487145103, "naucs_at_3_max": 0.5428075702339784, "naucs_at_3_std": -0.133844833983956, "naucs_at_3_diff1": 0.8487810208609975, "naucs_at_5_max": 0.570342039887235, "naucs_at_5_std": -0.1629741497251075, "naucs_at_5_diff1": 0.8403883247563, "naucs_at_10_max": 0.7076634965650749, "naucs_at_10_std": 0.14379204929117678, "naucs_at_10_diff1": 0.8238016143503649, "naucs_at_20_max": 0.8079586920995654, "naucs_at_20_std": 0.21002182843283598, "naucs_at_20_diff1": 0.825877668290874, "naucs_at_50_max": 0.8233669400006994, "naucs_at_50_std": 0.18166589601039382, "naucs_at_50_diff1": 0.8057881231371927, "naucs_at_100_max": 0.8922124708224929, "naucs_at_100_std": 0.6406492513828425, "naucs_at_100_diff1": 0.7867049962977823}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.97893, "ndcg_at_5": 0.97893, "ndcg_at_10": 0.97893, "ndcg_at_20": 0.97893, "ndcg_at_50": 0.97893, "ndcg_at_100": 0.97893, "map_at_1": 0.95, "map_at_3": 0.97167, "map_at_5": 0.97167, "map_at_10": 0.97167, "map_at_20": 0.97167, "map_at_50": 0.97167, "map_at_100": 0.97167, "recall_at_1": 0.95, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.95, "mrr_at_3": 0.9716666666666667, "mrr_at_5": 0.9716666666666667, "mrr_at_10": 0.9716666666666667, "mrr_at_20": 0.9716666666666667, "mrr_at_50": 0.9716666666666667, "mrr_at_100": 0.9716666666666667, "naucs_at_1_max": 0.5808590102707767, "naucs_at_1_std": -0.1164332399626522, "naucs_at_1_diff1": 0.9477124183006508, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tabfquad_test_subsampled": {"ndcg_at_1": 0.68929, "ndcg_at_3": 0.74413, "ndcg_at_5": 0.75167, "ndcg_at_10": 0.77118, "ndcg_at_20": 0.78112, "ndcg_at_50": 0.79873, "ndcg_at_100": 0.80054, "map_at_1": 0.68929, "map_at_3": 0.73095, "map_at_5": 0.73524, "map_at_10": 0.74323, "map_at_20": 0.74596, "map_at_50": 0.74876, "map_at_100": 0.74894, "recall_at_1": 0.68929, "recall_at_3": 0.78214, "recall_at_5": 0.8, "recall_at_10": 0.86071, "recall_at_20": 0.9, "recall_at_50": 0.98929, "recall_at_100": 1.0, "precision_at_1": 0.68929, "precision_at_3": 0.26071, "precision_at_5": 0.16, "precision_at_10": 0.08607, "precision_at_20": 0.045, "precision_at_50": 0.01979, "precision_at_100": 0.01, "mrr_at_1": 0.6857142857142857, "mrr_at_3": 0.7273809523809524, "mrr_at_5": 0.7332738095238095, "mrr_at_10": 0.7413988095238095, "mrr_at_20": 0.7440813863424158, "mrr_at_50": 0.7468722884841633, "mrr_at_100": 0.7470525854039923, "naucs_at_1_max": 0.2870009874897007, "naucs_at_1_std": 0.04204064432130546, "naucs_at_1_diff1": 0.7891552245752849, "naucs_at_3_max": 0.29717890310145373, "naucs_at_3_std": 0.10697806369788107, "naucs_at_3_diff1": 0.6949610753710974, "naucs_at_5_max": 0.2523369487655202, "naucs_at_5_std": 0.06743256743256658, "naucs_at_5_diff1": 0.6558976737548161, "naucs_at_10_max": 0.24856446841830593, "naucs_at_10_std": 0.02682144721469618, "naucs_at_10_diff1": 0.6389296278803848, "naucs_at_20_max": 0.16003067893824288, "naucs_at_20_std": -0.11236161131119002, "naucs_at_20_diff1": 0.601724022942509, "naucs_at_50_max": 0.8202614379084879, "naucs_at_50_std": 0.7424525365701868, "naucs_at_50_diff1": 0.7587924058512231, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.94178, "ndcg_at_5": 0.94609, "ndcg_at_10": 0.94609, "ndcg_at_20": 0.94609, "ndcg_at_50": 0.94609, "ndcg_at_100": 0.94609, "map_at_1": 0.87, "map_at_3": 0.925, "map_at_5": 0.9275, "map_at_10": 0.9275, "map_at_20": 0.9275, "map_at_50": 0.9275, "map_at_100": 0.9275, "recall_at_1": 0.87, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.89, "mrr_at_3": 0.935, "mrr_at_5": 0.9375, "mrr_at_10": 0.9375, "mrr_at_20": 0.9375, "mrr_at_50": 0.9375, "mrr_at_100": 0.9375, "naucs_at_1_max": 0.5187736058653628, "naucs_at_1_std": 0.22202473524402008, "naucs_at_1_diff1": 0.7872694956676297, "naucs_at_3_max": 0.5541549953314585, "naucs_at_3_std": 0.35807656395889226, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/shiftproject_test": {"ndcg_at_1": 0.48, "ndcg_at_3": 0.62226, "ndcg_at_5": 0.66313, "ndcg_at_10": 0.70227, "ndcg_at_20": 0.70762, "ndcg_at_50": 0.71377, "ndcg_at_100": 0.71377, "map_at_1": 0.48, "map_at_3": 0.58833, "map_at_5": 0.61083, "map_at_10": 0.62718, "map_at_20": 0.6288, "map_at_50": 0.62987, "map_at_100": 0.62987, "recall_at_1": 0.48, "recall_at_3": 0.72, "recall_at_5": 0.82, "recall_at_10": 0.94, "recall_at_20": 0.96, "recall_at_50": 0.99, "recall_at_100": 0.99, "precision_at_1": 0.48, "precision_at_3": 0.24, "precision_at_5": 0.164, "precision_at_10": 0.094, "precision_at_20": 0.048, "precision_at_50": 0.0198, "precision_at_100": 0.0099, "mrr_at_1": 0.51, "mrr_at_3": 0.6133333333333334, "mrr_at_5": 0.6333333333333333, "mrr_at_10": 0.6481230158730159, "mrr_at_20": 0.6503713924963925, "mrr_at_50": 0.6509864903528697, "mrr_at_100": 0.6509864903528697, "naucs_at_1_max": 0.01784958187784493, "naucs_at_1_std": -0.21715888641896902, "naucs_at_1_diff1": 0.7087302847464805, "naucs_at_3_max": 0.08859890109890145, "naucs_at_3_std": -0.28323412698412614, "naucs_at_3_diff1": 0.4830586080586077, "naucs_at_5_max": 0.10656459962550972, "naucs_at_5_std": -0.10389360061680472, "naucs_at_5_diff1": 0.40610199361163074, "naucs_at_10_max": -0.18744164332399568, "naucs_at_10_std": -0.024042950513536908, "naucs_at_10_diff1": 0.6868969810146294, "naucs_at_20_max": -0.22980859010270466, "naucs_at_20_std": -0.1562791783379993, "naucs_at_20_diff1": 0.7112511671335194, "naucs_at_50_max": -0.17133520074697067, "naucs_at_50_std": 0.12278244631185525, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": -0.17133520074697067, "naucs_at_100_std": 0.12278244631185525, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98762, "ndcg_at_5": 0.98762, "ndcg_at_10": 0.98762, "ndcg_at_20": 0.98762, "ndcg_at_50": 0.98762, "ndcg_at_100": 0.98762, "map_at_1": 0.97, "map_at_3": 0.98333, "map_at_5": 0.98333, "map_at_10": 0.98333, "map_at_20": 0.98333, "map_at_50": 0.98333, "map_at_100": 0.98333, "recall_at_1": 0.97, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.97, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.97, "mrr_at_3": 0.9833333333333333, "mrr_at_5": 0.9833333333333333, "mrr_at_10": 0.9833333333333333, "mrr_at_20": 0.9833333333333333, "mrr_at_50": 0.9833333333333333, "mrr_at_100": 0.9833333333333333, "naucs_at_1_max": 0.912854030501093, "naucs_at_1_std": 0.6934329287270453, "naucs_at_1_diff1": 0.912854030501093, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.44872, "ndcg_at_3": 0.51996, "ndcg_at_5": 0.52232, "ndcg_at_10": 0.57763, "ndcg_at_20": 0.62215, "ndcg_at_50": 0.64665, "ndcg_at_100": 0.65281, "map_at_1": 0.30481, "map_at_3": 0.44263, "map_at_5": 0.46343, "map_at_10": 0.49741, "map_at_20": 0.51592, "map_at_50": 0.52237, "map_at_100": 0.52398, "recall_at_1": 0.30481, "recall_at_3": 0.54615, "recall_at_5": 0.57807, "recall_at_10": 0.71877, "recall_at_20": 0.86108, "recall_at_50": 0.95162, "recall_at_100": 0.97216, "precision_at_1": 0.46154, "precision_at_3": 0.30769, "precision_at_5": 0.21538, "precision_at_10": 0.14038, "precision_at_20": 0.08654, "precision_at_50": 0.04154, "precision_at_100": 0.0225, "mrr_at_1": 0.4423076923076923, "mrr_at_3": 0.5448717948717949, "mrr_at_5": 0.5583333333333333, "mrr_at_10": 0.5792353479853479, "mrr_at_20": 0.5826894961763383, "mrr_at_50": 0.5850171075017945, "mrr_at_100": 0.5850171075017945, "naucs_at_1_max": 0.24419022886817585, "naucs_at_1_std": 0.20913530757518103, "naucs_at_1_diff1": 0.18956477760151022, "naucs_at_3_max": 0.021538678019016246, "naucs_at_3_std": 0.10725557234497837, "naucs_at_3_diff1": -0.04875457481754448, "naucs_at_5_max": 0.014645022986549194, "naucs_at_5_std": 0.044129824597325146, "naucs_at_5_diff1": -0.11174495404454246, "naucs_at_10_max": -0.11448340055341263, "naucs_at_10_std": -0.10902704168644266, "naucs_at_10_diff1": -0.30406392580200137, "naucs_at_20_max": -0.2404702117925663, "naucs_at_20_std": -0.22313364654433895, "naucs_at_20_diff1": -0.31695759183309535, "naucs_at_50_max": -0.31937538050402253, "naucs_at_50_std": -0.2759760110803978, "naucs_at_50_diff1": -0.24888406251943948, "naucs_at_100_max": -0.259723966830786, "naucs_at_100_std": -0.21333793632671658, "naucs_at_100_diff1": -0.23851384327512057},
2
+ "vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
3
+ "ndcg_at_1": 0.39224,
4
+ "ndcg_at_3": 0.37476,
5
+ "ndcg_at_5": 0.36148,
6
+ "ndcg_at_10": 0.36794,
7
+ "ndcg_at_20": 0.40776,
8
+ "ndcg_at_50": 0.48463,
9
+ "ndcg_at_100": 0.53033,
10
+ "map_at_1": 0.04401,
11
+ "map_at_3": 0.0993,
12
+ "map_at_5": 0.13005,
13
+ "map_at_10": 0.17704,
14
+ "map_at_20": 0.21969,
15
+ "map_at_50": 0.26748,
16
+ "map_at_100": 0.29042,
17
+ "recall_at_1": 0.04401,
18
+ "recall_at_3": 0.13187,
19
+ "recall_at_5": 0.192,
20
+ "recall_at_10": 0.3039,
21
+ "recall_at_20": 0.45606,
22
+ "recall_at_50": 0.67169,
23
+ "recall_at_100": 0.80877,
24
+ "precision_at_1": 0.39224,
25
+ "precision_at_3": 0.35632,
26
+ "precision_at_5": 0.325,
27
+ "precision_at_10": 0.28319,
28
+ "precision_at_20": 0.2306,
29
+ "precision_at_50": 0.15836,
30
+ "precision_at_100": 0.10789,
31
+ "mrr_at_1": 0.3922413793103448,
32
+ "mrr_at_3": 0.49856321839080464,
33
+ "mrr_at_5": 0.5224856321839081,
34
+ "mrr_at_10": 0.5373648741105638,
35
+ "mrr_at_20": 0.5419287783917268,
36
+ "mrr_at_50": 0.5442446092894189,
37
+ "mrr_at_100": 0.5445144362126614,
38
+ "naucs_at_1_max": -0.09046956137538088,
39
+ "naucs_at_1_std": -0.029272928593796467,
40
+ "naucs_at_1_diff1": -0.01949330501218432,
41
+ "naucs_at_3_max": 0.019777226299839537,
42
+ "naucs_at_3_std": 0.05400545367360109,
43
+ "naucs_at_3_diff1": -0.07318677988609872,
44
+ "naucs_at_5_max": 0.0035718336913224936,
45
+ "naucs_at_5_std": 0.027188298117242122,
46
+ "naucs_at_5_diff1": -0.07827063058686147,
47
+ "naucs_at_10_max": 0.008049347237839717,
48
+ "naucs_at_10_std": 0.03145707085203085,
49
+ "naucs_at_10_diff1": -0.07144093527570813,
50
+ "naucs_at_20_max": -0.003043019306168713,
51
+ "naucs_at_20_std": 0.04245224333344333,
52
+ "naucs_at_20_diff1": -0.0974791685465552,
53
+ "naucs_at_50_max": -0.008203803722240203,
54
+ "naucs_at_50_std": 0.004296600594517341,
55
+ "naucs_at_50_diff1": -0.08202642486940749,
56
+ "naucs_at_100_max": -0.05980969604715223,
57
+ "naucs_at_100_std": -0.07215268813689295,
58
+ "naucs_at_100_diff1": -0.05108060621594025
59
+ },
60
+ "vidore/synthetic_axa_filtered_v1.0_multilingual": {
61
+ "ndcg_at_1": 0.31944,
62
+ "ndcg_at_3": 0.36735,
63
+ "ndcg_at_5": 0.37705,
64
+ "ndcg_at_10": 0.40069,
65
+ "ndcg_at_20": 0.43513,
66
+ "ndcg_at_50": 0.49148,
67
+ "ndcg_at_100": 0.52626,
68
+ "map_at_1": 0.1883,
69
+ "map_at_3": 0.24848,
70
+ "map_at_5": 0.27905,
71
+ "map_at_10": 0.30821,
72
+ "map_at_20": 0.32807,
73
+ "map_at_50": 0.34999,
74
+ "map_at_100": 0.35742,
75
+ "recall_at_1": 0.1883,
76
+ "recall_at_3": 0.30968,
77
+ "recall_at_5": 0.38218,
78
+ "recall_at_10": 0.47556,
79
+ "recall_at_20": 0.56898,
80
+ "recall_at_50": 0.72054,
81
+ "recall_at_100": 0.86053,
82
+ "precision_at_1": 0.31944,
83
+ "precision_at_3": 0.25,
84
+ "precision_at_5": 0.20278,
85
+ "precision_at_10": 0.15,
86
+ "precision_at_20": 0.10694,
87
+ "precision_at_50": 0.06556,
88
+ "precision_at_100": 0.03972,
89
+ "mrr_at_1": 0.3194444444444444,
90
+ "mrr_at_3": 0.41435185185185186,
91
+ "mrr_at_5": 0.44143518518518515,
92
+ "mrr_at_10": 0.45383597883597887,
93
+ "mrr_at_20": 0.4603018758656014,
94
+ "mrr_at_50": 0.46184289024143715,
95
+ "mrr_at_100": 0.46279641774158087,
96
+ "naucs_at_1_max": 0.25256807521642977,
97
+ "naucs_at_1_std": 0.5222755178306032,
98
+ "naucs_at_1_diff1": 0.22322127062494312,
99
+ "naucs_at_3_max": 0.01027997935801778,
100
+ "naucs_at_3_std": 0.26082012822073436,
101
+ "naucs_at_3_diff1": 0.18412709220174425,
102
+ "naucs_at_5_max": -0.023540307718607937,
103
+ "naucs_at_5_std": 0.20590277989329697,
104
+ "naucs_at_5_diff1": 0.1394140867278813,
105
+ "naucs_at_10_max": -0.1530545347893013,
106
+ "naucs_at_10_std": 0.07281002973646711,
107
+ "naucs_at_10_diff1": 0.1087825983057161,
108
+ "naucs_at_20_max": -0.24948473963259538,
109
+ "naucs_at_20_std": -0.052063417282516324,
110
+ "naucs_at_20_diff1": 0.04499575326148708,
111
+ "naucs_at_50_max": -0.3456643349075049,
112
+ "naucs_at_50_std": -0.14962525206807992,
113
+ "naucs_at_50_diff1": -0.1032344032141534,
114
+ "naucs_at_100_max": -0.41065527201035196,
115
+ "naucs_at_100_std": -0.24631195551976134,
116
+ "naucs_at_100_diff1": -0.1270004114792933
117
+ },
118
+ "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
119
+ "ndcg_at_1": 0.475,
120
+ "ndcg_at_3": 0.50399,
121
+ "ndcg_at_5": 0.5426,
122
+ "ndcg_at_10": 0.56572,
123
+ "ndcg_at_20": 0.59334,
124
+ "ndcg_at_50": 0.62054,
125
+ "ndcg_at_100": 0.63584,
126
+ "map_at_1": 0.29844,
127
+ "map_at_3": 0.40685,
128
+ "map_at_5": 0.44582,
129
+ "map_at_10": 0.46931,
130
+ "map_at_20": 0.48245,
131
+ "map_at_50": 0.49251,
132
+ "map_at_100": 0.49533,
133
+ "recall_at_1": 0.29844,
134
+ "recall_at_3": 0.48891,
135
+ "recall_at_5": 0.59575,
136
+ "recall_at_10": 0.67602,
137
+ "recall_at_20": 0.75242,
138
+ "recall_at_50": 0.83386,
139
+ "recall_at_100": 0.89769,
140
+ "precision_at_1": 0.475,
141
+ "precision_at_3": 0.30833,
142
+ "precision_at_5": 0.24875,
143
+ "precision_at_10": 0.15125,
144
+ "precision_at_20": 0.09344,
145
+ "precision_at_50": 0.0465,
146
+ "precision_at_100": 0.026,
147
+ "mrr_at_1": 0.49375,
148
+ "mrr_at_3": 0.5958333333333333,
149
+ "mrr_at_5": 0.6202083333333334,
150
+ "mrr_at_10": 0.6287375992063492,
151
+ "mrr_at_20": 0.6311754670660437,
152
+ "mrr_at_50": 0.6321625072817313,
153
+ "mrr_at_100": 0.6324052960661868,
154
+ "naucs_at_1_max": 0.288181487963544,
155
+ "naucs_at_1_std": -0.05426311792094572,
156
+ "naucs_at_1_diff1": 0.4584585410956644,
157
+ "naucs_at_3_max": 0.17191913339472156,
158
+ "naucs_at_3_std": -0.020066630109774056,
159
+ "naucs_at_3_diff1": 0.09632913618821975,
160
+ "naucs_at_5_max": 0.09215639006811155,
161
+ "naucs_at_5_std": 0.0012666140953723163,
162
+ "naucs_at_5_diff1": -0.06192925755984746,
163
+ "naucs_at_10_max": 0.035222797177968716,
164
+ "naucs_at_10_std": 0.007929567555839194,
165
+ "naucs_at_10_diff1": -0.15828889663289214,
166
+ "naucs_at_20_max": -0.013133460063983105,
167
+ "naucs_at_20_std": 0.045498580990890984,
168
+ "naucs_at_20_diff1": -0.18372934627970697,
169
+ "naucs_at_50_max": -0.05231228123361153,
170
+ "naucs_at_50_std": 0.08122908162109731,
171
+ "naucs_at_50_diff1": -0.18562366170287978,
172
+ "naucs_at_100_max": -0.09050436131033135,
173
+ "naucs_at_100_std": 0.07301259934095748,
174
+ "naucs_at_100_diff1": -0.18245241325838332
175
+ },
176
+ "vidore/synthetic_rse_restaurant_filtered_v1.0": {
177
+ "ndcg_at_1": 0.26316,
178
+ "ndcg_at_3": 0.36311,
179
+ "ndcg_at_5": 0.39176,
180
+ "ndcg_at_10": 0.4454,
181
+ "ndcg_at_20": 0.50519,
182
+ "ndcg_at_50": 0.55061,
183
+ "ndcg_at_100": 0.56466,
184
+ "map_at_1": 0.15482,
185
+ "map_at_3": 0.27015,
186
+ "map_at_5": 0.29589,
187
+ "map_at_10": 0.33078,
188
+ "map_at_20": 0.36126,
189
+ "map_at_50": 0.3824,
190
+ "map_at_100": 0.38909,
191
+ "recall_at_1": 0.15482,
192
+ "recall_at_3": 0.37362,
193
+ "recall_at_5": 0.44749,
194
+ "recall_at_10": 0.60324,
195
+ "recall_at_20": 0.78193,
196
+ "recall_at_50": 0.91531,
197
+ "recall_at_100": 0.95395,
198
+ "precision_at_1": 0.26316,
199
+ "precision_at_3": 0.25146,
200
+ "precision_at_5": 0.20702,
201
+ "precision_at_10": 0.15088,
202
+ "precision_at_20": 0.11228,
203
+ "precision_at_50": 0.06667,
204
+ "precision_at_100": 0.03789,
205
+ "mrr_at_1": 0.3157894736842105,
206
+ "mrr_at_3": 0.4473684210526316,
207
+ "mrr_at_5": 0.46754385964912276,
208
+ "mrr_at_10": 0.48647312726260095,
209
+ "mrr_at_20": 0.49202021175705385,
210
+ "mrr_at_50": 0.49322536427799585,
211
+ "mrr_at_100": 0.49322536427799585,
212
+ "naucs_at_1_max": -0.05405282049792571,
213
+ "naucs_at_1_std": 0.023445855968560407,
214
+ "naucs_at_1_diff1": 0.21928586224649782,
215
+ "naucs_at_3_max": -0.011620395920182198,
216
+ "naucs_at_3_std": 0.08615056848034938,
217
+ "naucs_at_3_diff1": -0.15099634717817523,
218
+ "naucs_at_5_max": -0.1652385842485644,
219
+ "naucs_at_5_std": -0.1076298647113443,
220
+ "naucs_at_5_diff1": -0.26773917349447285,
221
+ "naucs_at_10_max": -0.20948212317741371,
222
+ "naucs_at_10_std": -0.04217452519607505,
223
+ "naucs_at_10_diff1": -0.17241123984858953,
224
+ "naucs_at_20_max": -0.3585661146008277,
225
+ "naucs_at_20_std": -0.11294869002059522,
226
+ "naucs_at_20_diff1": -0.27144993416761004,
227
+ "naucs_at_50_max": -0.33543648981957763,
228
+ "naucs_at_50_std": -0.014416596192293988,
229
+ "naucs_at_50_diff1": -0.2783603795291369,
230
+ "naucs_at_100_max": -0.3125483341345789,
231
+ "naucs_at_100_std": 0.04759656217556336,
232
+ "naucs_at_100_diff1": -0.27748680314970026
233
+ },
234
+ "vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
235
+ "ndcg_at_1": 0.3114,
236
+ "ndcg_at_3": 0.35716,
237
+ "ndcg_at_5": 0.39093,
238
+ "ndcg_at_10": 0.45776,
239
+ "ndcg_at_20": 0.51442,
240
+ "ndcg_at_50": 0.55435,
241
+ "ndcg_at_100": 0.57057,
242
+ "map_at_1": 0.1635,
243
+ "map_at_3": 0.26015,
244
+ "map_at_5": 0.29428,
245
+ "map_at_10": 0.33703,
246
+ "map_at_20": 0.36703,
247
+ "map_at_50": 0.38532,
248
+ "map_at_100": 0.39218,
249
+ "recall_at_1": 0.1635,
250
+ "recall_at_3": 0.34212,
251
+ "recall_at_5": 0.43294,
252
+ "recall_at_10": 0.62713,
253
+ "recall_at_20": 0.80024,
254
+ "recall_at_50": 0.9216,
255
+ "recall_at_100": 0.97058,
256
+ "precision_at_1": 0.3114,
257
+ "precision_at_3": 0.25,
258
+ "precision_at_5": 0.21228,
259
+ "precision_at_10": 0.16272,
260
+ "precision_at_20": 0.11732,
261
+ "precision_at_50": 0.06509,
262
+ "precision_at_100": 0.03768,
263
+ "mrr_at_1": 0.3201754385964912,
264
+ "mrr_at_3": 0.4276315789473684,
265
+ "mrr_at_5": 0.45570175438596494,
266
+ "mrr_at_10": 0.4726991088833194,
267
+ "mrr_at_20": 0.47990133359766324,
268
+ "mrr_at_50": 0.4817393870105699,
269
+ "mrr_at_100": 0.48179098659777314,
270
+ "naucs_at_1_max": -0.043051520891704526,
271
+ "naucs_at_1_std": 0.04332255792861466,
272
+ "naucs_at_1_diff1": 0.25290228804176196,
273
+ "naucs_at_3_max": -0.015276644061893118,
274
+ "naucs_at_3_std": 0.05163750744485839,
275
+ "naucs_at_3_diff1": 0.040189218663360116,
276
+ "naucs_at_5_max": -0.05235721102136031,
277
+ "naucs_at_5_std": 0.005811214103192345,
278
+ "naucs_at_5_diff1": 0.019471817185607386,
279
+ "naucs_at_10_max": -0.15526718391563657,
280
+ "naucs_at_10_std": -0.030920730403369213,
281
+ "naucs_at_10_diff1": -0.009103205213602163,
282
+ "naucs_at_20_max": -0.16361665459184682,
283
+ "naucs_at_20_std": -0.006377615107252758,
284
+ "naucs_at_20_diff1": -0.11234618830619728,
285
+ "naucs_at_50_max": -0.15363708207480695,
286
+ "naucs_at_50_std": 0.07280318534401509,
287
+ "naucs_at_50_diff1": -0.15710162022601212,
288
+ "naucs_at_100_max": -0.1483886076804903,
289
+ "naucs_at_100_std": 0.10513102578338192,
290
+ "naucs_at_100_diff1": -0.15391945667071522
291
+ },
292
+ "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
293
+ "ndcg_at_1": 0.38125,
294
+ "ndcg_at_3": 0.39476,
295
+ "ndcg_at_5": 0.4206,
296
+ "ndcg_at_10": 0.45509,
297
+ "ndcg_at_20": 0.48714,
298
+ "ndcg_at_50": 0.51836,
299
+ "ndcg_at_100": 0.53432,
300
+ "map_at_1": 0.24209,
301
+ "map_at_3": 0.31985,
302
+ "map_at_5": 0.34726,
303
+ "map_at_10": 0.3711,
304
+ "map_at_20": 0.38475,
305
+ "map_at_50": 0.39391,
306
+ "map_at_100": 0.39676,
307
+ "recall_at_1": 0.24209,
308
+ "recall_at_3": 0.38347,
309
+ "recall_at_5": 0.45975,
310
+ "recall_at_10": 0.56148,
311
+ "recall_at_20": 0.65407,
312
+ "recall_at_50": 0.75821,
313
+ "recall_at_100": 0.82192,
314
+ "precision_at_1": 0.38125,
315
+ "precision_at_3": 0.23333,
316
+ "precision_at_5": 0.18344,
317
+ "precision_at_10": 0.12031,
318
+ "precision_at_20": 0.07758,
319
+ "precision_at_50": 0.04006,
320
+ "precision_at_100": 0.02297,
321
+ "mrr_at_1": 0.3984375,
322
+ "mrr_at_3": 0.47890625,
323
+ "mrr_at_5": 0.497734375,
324
+ "mrr_at_10": 0.5095529513888889,
325
+ "mrr_at_20": 0.5151586381105779,
326
+ "mrr_at_50": 0.5174101160297588,
327
+ "mrr_at_100": 0.5178826588862087,
328
+ "naucs_at_1_max": 0.13899599795432951,
329
+ "naucs_at_1_std": 0.0368281555683635,
330
+ "naucs_at_1_diff1": 0.5053982968982114,
331
+ "naucs_at_3_max": 0.07054641540082532,
332
+ "naucs_at_3_std": 0.05000850601457527,
333
+ "naucs_at_3_diff1": 0.21532701510229157,
334
+ "naucs_at_5_max": 0.01417845342936614,
335
+ "naucs_at_5_std": 0.020526726379349457,
336
+ "naucs_at_5_diff1": 0.10818783419375576,
337
+ "naucs_at_10_max": -0.020678341996715813,
338
+ "naucs_at_10_std": 0.02320094009445125,
339
+ "naucs_at_10_diff1": 0.006460602129137368,
340
+ "naucs_at_20_max": -0.056359581334902174,
341
+ "naucs_at_20_std": 0.022492779057438163,
342
+ "naucs_at_20_diff1": -0.04495830300371242,
343
+ "naucs_at_50_max": -0.08195205931936514,
344
+ "naucs_at_50_std": 0.036322084125175555,
345
+ "naucs_at_50_diff1": -0.07768679112951372,
346
+ "naucs_at_100_max": -0.10382076960662541,
347
+ "naucs_at_100_std": 0.017015419651631922,
348
+ "naucs_at_100_diff1": -0.08434098316520129
349
+ },
350
+ "vidore/synthetic_axa_filtered_v1.0": {
351
+ "ndcg_at_1": 0.5,
352
+ "ndcg_at_3": 0.56184,
353
+ "ndcg_at_5": 0.587,
354
+ "ndcg_at_10": 0.60148,
355
+ "ndcg_at_20": 0.62635,
356
+ "ndcg_at_50": 0.67819,
357
+ "ndcg_at_100": 0.69787,
358
+ "map_at_1": 0.28611,
359
+ "map_at_3": 0.36587,
360
+ "map_at_5": 0.43319,
361
+ "map_at_10": 0.47842,
362
+ "map_at_20": 0.50424,
363
+ "map_at_50": 0.53292,
364
+ "map_at_100": 0.53674,
365
+ "recall_at_1": 0.28611,
366
+ "recall_at_3": 0.42945,
367
+ "recall_at_5": 0.58465,
368
+ "recall_at_10": 0.68747,
369
+ "recall_at_20": 0.75855,
370
+ "recall_at_50": 0.88111,
371
+ "recall_at_100": 0.97026,
372
+ "precision_at_1": 0.5,
373
+ "precision_at_3": 0.40741,
374
+ "precision_at_5": 0.33333,
375
+ "precision_at_10": 0.23333,
376
+ "precision_at_20": 0.15278,
377
+ "precision_at_50": 0.08444,
378
+ "precision_at_100": 0.045,
379
+ "mrr_at_1": 0.5,
380
+ "mrr_at_3": 0.6203703703703703,
381
+ "mrr_at_5": 0.6481481481481481,
382
+ "mrr_at_10": 0.6574074074074074,
383
+ "mrr_at_20": 0.6574074074074074,
384
+ "mrr_at_50": 0.65854119425548,
385
+ "mrr_at_100": 0.65854119425548,
386
+ "naucs_at_1_max": 0.42651593299790197,
387
+ "naucs_at_1_std": 0.5071500249117564,
388
+ "naucs_at_1_diff1": 0.30239223033901025,
389
+ "naucs_at_3_max": -0.2757769266874663,
390
+ "naucs_at_3_std": -0.205926822886879,
391
+ "naucs_at_3_diff1": 0.06908403486928417,
392
+ "naucs_at_5_max": -0.3693499917580161,
393
+ "naucs_at_5_std": -0.2923131576624302,
394
+ "naucs_at_5_diff1": -0.050910460634029486,
395
+ "naucs_at_10_max": -0.572254001138292,
396
+ "naucs_at_10_std": -0.46716738275931796,
397
+ "naucs_at_10_diff1": -0.0735594830753536,
398
+ "naucs_at_20_max": -0.6311605275619012,
399
+ "naucs_at_20_std": -0.493877197928487,
400
+ "naucs_at_20_diff1": -0.08810700944293344,
401
+ "naucs_at_50_max": -0.5994854185823998,
402
+ "naucs_at_50_std": -0.3880377145984835,
403
+ "naucs_at_50_diff1": -0.2337980752344902,
404
+ "naucs_at_100_max": -0.5975814841373683,
405
+ "naucs_at_100_std": -0.3931594317744619,
406
+ "naucs_at_100_diff1": -0.20608009190940405
407
+ },
408
+ "vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
409
+ "ndcg_at_1": 0.56897,
410
+ "ndcg_at_3": 0.5211,
411
+ "ndcg_at_5": 0.50298,
412
+ "ndcg_at_10": 0.52258,
413
+ "ndcg_at_20": 0.55507,
414
+ "ndcg_at_50": 0.62454,
415
+ "ndcg_at_100": 0.65668,
416
+ "map_at_1": 0.06658,
417
+ "map_at_3": 0.14611,
418
+ "map_at_5": 0.19305,
419
+ "map_at_10": 0.27576,
420
+ "map_at_20": 0.33378,
421
+ "map_at_50": 0.39269,
422
+ "map_at_100": 0.41666,
423
+ "recall_at_1": 0.06658,
424
+ "recall_at_3": 0.18538,
425
+ "recall_at_5": 0.26874,
426
+ "recall_at_10": 0.44378,
427
+ "recall_at_20": 0.5979,
428
+ "recall_at_50": 0.79293,
429
+ "recall_at_100": 0.89795,
430
+ "precision_at_1": 0.56897,
431
+ "precision_at_3": 0.48851,
432
+ "precision_at_5": 0.44483,
433
+ "precision_at_10": 0.3931,
434
+ "precision_at_20": 0.30431,
435
+ "precision_at_50": 0.19517,
436
+ "precision_at_100": 0.12379,
437
+ "mrr_at_1": 0.5862068965517241,
438
+ "mrr_at_3": 0.675287356321839,
439
+ "mrr_at_5": 0.6985632183908046,
440
+ "mrr_at_10": 0.7113711001642037,
441
+ "mrr_at_20": 0.71252052545156,
442
+ "mrr_at_50": 0.7133415435139574,
443
+ "mrr_at_100": 0.7133415435139574,
444
+ "naucs_at_1_max": -0.40040744598442884,
445
+ "naucs_at_1_std": -0.2985416538266988,
446
+ "naucs_at_1_diff1": 0.12036209692812928,
447
+ "naucs_at_3_max": -0.3377813006714379,
448
+ "naucs_at_3_std": -0.2501659993033734,
449
+ "naucs_at_3_diff1": -0.03738351632070548,
450
+ "naucs_at_5_max": -0.1125861127198914,
451
+ "naucs_at_5_std": -0.06443718988916795,
452
+ "naucs_at_5_diff1": -0.03965316546372891,
453
+ "naucs_at_10_max": -0.009590286755270482,
454
+ "naucs_at_10_std": 0.006695305574988969,
455
+ "naucs_at_10_diff1": -0.09088428457053505,
456
+ "naucs_at_20_max": 0.05383858850417515,
457
+ "naucs_at_20_std": 0.05335828984185507,
458
+ "naucs_at_20_diff1": -0.12843644755345873,
459
+ "naucs_at_50_max": 0.016749758399340033,
460
+ "naucs_at_50_std": 0.006620482393505167,
461
+ "naucs_at_50_diff1": -0.09393030796852221,
462
+ "naucs_at_100_max": -0.069387597095011,
463
+ "naucs_at_100_std": -0.09518999664037518,
464
+ "naucs_at_100_diff1": -0.05750748161503184
465
+ }, "./data_dir/eval_vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.67, "ndcg_at_3": 0.73664, "ndcg_at_5": 0.74886, "ndcg_at_10": 0.76608, "ndcg_at_20": 0.77508, "ndcg_at_50": 0.78465, "ndcg_at_100": 0.78928, "map_at_1": 0.67, "map_at_3": 0.71967, "map_at_5": 0.72637, "map_at_10": 0.73332, "map_at_20": 0.73575, "map_at_50": 0.7373, "map_at_100": 0.73774, "recall_at_1": 0.67, "recall_at_3": 0.786, "recall_at_5": 0.816, "recall_at_10": 0.87, "recall_at_20": 0.906, "recall_at_50": 0.954, "recall_at_100": 0.982, "precision_at_1": 0.67, "precision_at_3": 0.262, "precision_at_5": 0.1632, "precision_at_10": 0.087, "precision_at_20": 0.0453, "precision_at_50": 0.01908, "precision_at_100": 0.00982, "mrr_at_1": 0.674, "mrr_at_3": 0.723, "mrr_at_5": 0.7291, "mrr_at_10": 0.7366095238095238, "mrr_at_20": 0.7391611043325439, "mrr_at_50": 0.7409444251953623, "mrr_at_100": 0.7413271325461593, "naucs_at_1_max": 0.5444803710788707, "naucs_at_1_std": -0.09109715427197845, "naucs_at_1_diff1": 0.9253203771732317, "naucs_at_3_max": 0.5919376009932287, "naucs_at_3_std": -0.04496538390458086, "naucs_at_3_diff1": 0.8649522103597137, "naucs_at_5_max": 0.6306070025471655, "naucs_at_5_std": 0.001678323187842219, "naucs_at_5_diff1": 0.8645469067046583, "naucs_at_10_max": 0.6801229356439317, "naucs_at_10_std": 0.03928756572613559, "naucs_at_10_diff1": 0.8395171443382958, "naucs_at_20_max": 0.7005979696843283, "naucs_at_20_std": 0.04557283906470355, "naucs_at_20_diff1": 0.8023322804299033, "naucs_at_50_max": 0.7126212803962136, "naucs_at_50_std": -0.09452766613891975, "naucs_at_50_diff1": 0.8312223440100683, "naucs_at_100_max": 0.85968461458657, "naucs_at_100_std": -0.10281149496835222, "naucs_at_100_diff1": 0.896514161220045}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.50554, "ndcg_at_3": 0.55831, "ndcg_at_5": 0.58055, "ndcg_at_10": 0.60677, "ndcg_at_20": 0.62553, "ndcg_at_50": 0.63388, "ndcg_at_100": 0.64093, "map_at_1": 0.50554, "map_at_3": 0.54582, "map_at_5": 0.55835, "map_at_10": 0.569, "map_at_20": 0.5743, "map_at_50": 0.57564, "map_at_100": 0.57622, "recall_at_1": 0.50554, "recall_at_3": 0.59424, "recall_at_5": 0.64745, "recall_at_10": 0.72949, "recall_at_20": 0.80266, "recall_at_50": 0.84479, "recall_at_100": 0.88914, "precision_at_1": 0.50554, "precision_at_3": 0.19808, "precision_at_5": 0.12949, "precision_at_10": 0.07295, "precision_at_20": 0.04013, "precision_at_50": 0.0169, "precision_at_100": 0.00889, "mrr_at_1": 0.5033259423503326, "mrr_at_3": 0.5476718403547672, "mrr_at_5": 0.5574279379157429, "mrr_at_10": 0.5684528208918452, "mrr_at_20": 0.573404311645784, "mrr_at_50": 0.5749334030411379, "mrr_at_100": 0.575603354450426, "naucs_at_1_max": 0.2625490776539377, "naucs_at_1_std": 0.3310850636640096, "naucs_at_1_diff1": 0.8285865433933254, "naucs_at_3_max": 0.18953190824386826, "naucs_at_3_std": 0.38629715857674524, "naucs_at_3_diff1": 0.769918430991528, "naucs_at_5_max": 0.14915660669648698, "naucs_at_5_std": 0.39060413735358934, "naucs_at_5_diff1": 0.7373299633405666, "naucs_at_10_max": 0.008734548704545675, "naucs_at_10_std": 0.5053066426323437, "naucs_at_10_diff1": 0.7260812769949216, "naucs_at_20_max": -0.1110192872274276, "naucs_at_20_std": 0.6213072109985829, "naucs_at_20_diff1": 0.6964830158995551, "naucs_at_50_max": -0.16049662657697744, "naucs_at_50_std": 0.7364897688356142, "naucs_at_50_diff1": 0.7182771454403309, "naucs_at_100_max": -0.19221684927376187, "naucs_at_100_std": 0.8505984612548488, "naucs_at_100_diff1": 0.7419613287710981}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.93417, "ndcg_at_5": 0.93847, "ndcg_at_10": 0.93847, "ndcg_at_20": 0.93847, "ndcg_at_50": 0.94063, "ndcg_at_100": 0.9422, "map_at_1": 0.88, "map_at_3": 0.92167, "map_at_5": 0.92417, "map_at_10": 0.92417, "map_at_20": 0.92417, "map_at_50": 0.92458, "map_at_100": 0.92471, "recall_at_1": 0.88, "recall_at_3": 0.97, "recall_at_5": 0.98, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.32333, "precision_at_5": 0.196, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.89, "mrr_at_3": 0.93, "mrr_at_5": 0.9325, "mrr_at_10": 0.9325, "mrr_at_20": 0.9325, "mrr_at_50": 0.9329166666666667, "mrr_at_100": 0.9330448717948718, "naucs_at_1_max": 0.36497772828507796, "naucs_at_1_std": -0.272231944002546, "naucs_at_1_diff1": 0.9777282850779508, "naucs_at_3_max": 0.693432928727046, "naucs_at_3_std": -0.15452847805789072, "naucs_at_3_diff1": 0.9564270152505466, "naucs_at_5_max": 0.6790382819794609, "naucs_at_5_std": -0.5929038281979465, "naucs_at_5_diff1": 0.9346405228758136, "naucs_at_10_max": 0.6790382819794609, "naucs_at_10_std": -0.5929038281979465, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.6790382819794609, "naucs_at_20_std": -0.5929038281979465, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.554154995331464, "naucs_at_50_diff1": 0.8692810457516374, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tatdqa_test": {"ndcg_at_1": 0.64581, "ndcg_at_3": 0.73981, "ndcg_at_5": 0.7668, "ndcg_at_10": 0.787, "ndcg_at_20": 0.79364, "ndcg_at_50": 0.79698, "ndcg_at_100": 0.79864, "map_at_1": 0.64581, "map_at_3": 0.71648, "map_at_5": 0.73158, "map_at_10": 0.74001, "map_at_20": 0.74185, "map_at_50": 0.74242, "map_at_100": 0.74256, "recall_at_1": 0.64581, "recall_at_3": 0.80741, "recall_at_5": 0.87242, "recall_at_10": 0.93439, "recall_at_20": 0.96051, "recall_at_50": 0.97691, "recall_at_100": 0.98724, "precision_at_1": 0.64581, "precision_at_3": 0.26914, "precision_at_5": 0.17448, "precision_at_10": 0.09344, "precision_at_20": 0.04803, "precision_at_50": 0.01954, "precision_at_100": 0.00987, "mrr_at_1": 0.6433778857837181, "mrr_at_3": 0.7150668286755771, "mrr_at_5": 0.7304981773997571, "mrr_at_10": 0.7387049412717699, "mrr_at_20": 0.7404579555191415, "mrr_at_50": 0.7410660643728302, "mrr_at_100": 0.7412038533898355, "naucs_at_1_max": 0.13431737923823708, "naucs_at_1_std": -0.3067075571650227, "naucs_at_1_diff1": 0.8067592167032371, "naucs_at_3_max": 0.18727434840097998, "naucs_at_3_std": -0.27607320609227726, "naucs_at_3_diff1": 0.6950163190033429, "naucs_at_5_max": 0.2109382115959134, "naucs_at_5_std": -0.22542299636024854, "naucs_at_5_diff1": 0.6560772753501689, "naucs_at_10_max": 0.3049581820340452, "naucs_at_10_std": 0.10695854160572203, "naucs_at_10_diff1": 0.5979569201987198, "naucs_at_20_max": 0.3524427577390326, "naucs_at_20_std": 0.2838037847480218, "naucs_at_20_diff1": 0.5748977828288308, "naucs_at_50_max": 0.39877531195470334, "naucs_at_50_std": 0.47760692333540594, "naucs_at_50_diff1": 0.48464495157589027, "naucs_at_100_max": 0.3531041790707774, "naucs_at_100_std": 0.4303621036969795, "naucs_at_100_diff1": 0.42655633089874984}, "./data_dir/eval_vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.80769, "ndcg_at_3": 0.86119, "ndcg_at_5": 0.86799, "ndcg_at_10": 0.87508, "ndcg_at_20": 0.8788, "ndcg_at_50": 0.88321, "ndcg_at_100": 0.88418, "map_at_1": 0.80769, "map_at_3": 0.84818, "map_at_5": 0.85202, "map_at_10": 0.85488, "map_at_20": 0.85598, "map_at_50": 0.85668, "map_at_100": 0.85677, "recall_at_1": 0.80769, "recall_at_3": 0.89879, "recall_at_5": 0.91498, "recall_at_10": 0.93725, "recall_at_20": 0.95142, "recall_at_50": 0.97368, "recall_at_100": 0.97976, "precision_at_1": 0.80769, "precision_at_3": 0.2996, "precision_at_5": 0.183, "precision_at_10": 0.09372, "precision_at_20": 0.04757, "precision_at_50": 0.01947, "precision_at_100": 0.0098, "mrr_at_1": 0.8117408906882592, "mrr_at_3": 0.8488529014844804, "mrr_at_5": 0.8532051282051283, "mrr_at_10": 0.8560359231411864, "mrr_at_20": 0.8570996255206782, "mrr_at_50": 0.8577900744824616, "mrr_at_100": 0.8578711146551276, "naucs_at_1_max": 0.5181292739994149, "naucs_at_1_std": -0.12587128411667012, "naucs_at_1_diff1": 0.9118360487145103, "naucs_at_3_max": 0.5428075702339784, "naucs_at_3_std": -0.133844833983956, "naucs_at_3_diff1": 0.8487810208609975, "naucs_at_5_max": 0.570342039887235, "naucs_at_5_std": -0.1629741497251075, "naucs_at_5_diff1": 0.8403883247563, "naucs_at_10_max": 0.7076634965650749, "naucs_at_10_std": 0.14379204929117678, "naucs_at_10_diff1": 0.8238016143503649, "naucs_at_20_max": 0.8079586920995654, "naucs_at_20_std": 0.21002182843283598, "naucs_at_20_diff1": 0.825877668290874, "naucs_at_50_max": 0.8233669400006994, "naucs_at_50_std": 0.18166589601039382, "naucs_at_50_diff1": 0.8057881231371927, "naucs_at_100_max": 0.8922124708224929, "naucs_at_100_std": 0.6406492513828425, "naucs_at_100_diff1": 0.7867049962977823}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.97893, "ndcg_at_5": 0.97893, "ndcg_at_10": 0.97893, "ndcg_at_20": 0.97893, "ndcg_at_50": 0.97893, "ndcg_at_100": 0.97893, "map_at_1": 0.95, "map_at_3": 0.97167, "map_at_5": 0.97167, "map_at_10": 0.97167, "map_at_20": 0.97167, "map_at_50": 0.97167, "map_at_100": 0.97167, "recall_at_1": 0.95, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.95, "mrr_at_3": 0.9716666666666667, "mrr_at_5": 0.9716666666666667, "mrr_at_10": 0.9716666666666667, "mrr_at_20": 0.9716666666666667, "mrr_at_50": 0.9716666666666667, "mrr_at_100": 0.9716666666666667, "naucs_at_1_max": 0.5808590102707767, "naucs_at_1_std": -0.1164332399626522, "naucs_at_1_diff1": 0.9477124183006508, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tabfquad_test_subsampled": {"ndcg_at_1": 0.68929, "ndcg_at_3": 0.74413, "ndcg_at_5": 0.75167, "ndcg_at_10": 0.77118, "ndcg_at_20": 0.78112, "ndcg_at_50": 0.79873, "ndcg_at_100": 0.80054, "map_at_1": 0.68929, "map_at_3": 0.73095, "map_at_5": 0.73524, "map_at_10": 0.74323, "map_at_20": 0.74596, "map_at_50": 0.74876, "map_at_100": 0.74894, "recall_at_1": 0.68929, "recall_at_3": 0.78214, "recall_at_5": 0.8, "recall_at_10": 0.86071, "recall_at_20": 0.9, "recall_at_50": 0.98929, "recall_at_100": 1.0, "precision_at_1": 0.68929, "precision_at_3": 0.26071, "precision_at_5": 0.16, "precision_at_10": 0.08607, "precision_at_20": 0.045, "precision_at_50": 0.01979, "precision_at_100": 0.01, "mrr_at_1": 0.6857142857142857, "mrr_at_3": 0.7273809523809524, "mrr_at_5": 0.7332738095238095, "mrr_at_10": 0.7413988095238095, "mrr_at_20": 0.7440813863424158, "mrr_at_50": 0.7468722884841633, "mrr_at_100": 0.7470525854039923, "naucs_at_1_max": 0.2870009874897007, "naucs_at_1_std": 0.04204064432130546, "naucs_at_1_diff1": 0.7891552245752849, "naucs_at_3_max": 0.29717890310145373, "naucs_at_3_std": 0.10697806369788107, "naucs_at_3_diff1": 0.6949610753710974, "naucs_at_5_max": 0.2523369487655202, "naucs_at_5_std": 0.06743256743256658, "naucs_at_5_diff1": 0.6558976737548161, "naucs_at_10_max": 0.24856446841830593, "naucs_at_10_std": 0.02682144721469618, "naucs_at_10_diff1": 0.6389296278803848, "naucs_at_20_max": 0.16003067893824288, "naucs_at_20_std": -0.11236161131119002, "naucs_at_20_diff1": 0.601724022942509, "naucs_at_50_max": 0.8202614379084879, "naucs_at_50_std": 0.7424525365701868, "naucs_at_50_diff1": 0.7587924058512231, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.94178, "ndcg_at_5": 0.94609, "ndcg_at_10": 0.94609, "ndcg_at_20": 0.94609, "ndcg_at_50": 0.94609, "ndcg_at_100": 0.94609, "map_at_1": 0.87, "map_at_3": 0.925, "map_at_5": 0.9275, "map_at_10": 0.9275, "map_at_20": 0.9275, "map_at_50": 0.9275, "map_at_100": 0.9275, "recall_at_1": 0.87, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.89, "mrr_at_3": 0.935, "mrr_at_5": 0.9375, "mrr_at_10": 0.9375, "mrr_at_20": 0.9375, "mrr_at_50": 0.9375, "mrr_at_100": 0.9375, "naucs_at_1_max": 0.5187736058653628, "naucs_at_1_std": 0.22202473524402008, "naucs_at_1_diff1": 0.7872694956676297, "naucs_at_3_max": 0.5541549953314585, "naucs_at_3_std": 0.35807656395889226, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/shiftproject_test": {"ndcg_at_1": 0.48, "ndcg_at_3": 0.62226, "ndcg_at_5": 0.66313, "ndcg_at_10": 0.70227, "ndcg_at_20": 0.70762, "ndcg_at_50": 0.71377, "ndcg_at_100": 0.71377, "map_at_1": 0.48, "map_at_3": 0.58833, "map_at_5": 0.61083, "map_at_10": 0.62718, "map_at_20": 0.6288, "map_at_50": 0.62987, "map_at_100": 0.62987, "recall_at_1": 0.48, "recall_at_3": 0.72, "recall_at_5": 0.82, "recall_at_10": 0.94, "recall_at_20": 0.96, "recall_at_50": 0.99, "recall_at_100": 0.99, "precision_at_1": 0.48, "precision_at_3": 0.24, "precision_at_5": 0.164, "precision_at_10": 0.094, "precision_at_20": 0.048, "precision_at_50": 0.0198, "precision_at_100": 0.0099, "mrr_at_1": 0.51, "mrr_at_3": 0.6133333333333334, "mrr_at_5": 0.6333333333333333, "mrr_at_10": 0.6481230158730159, "mrr_at_20": 0.6503713924963925, "mrr_at_50": 0.6509864903528697, "mrr_at_100": 0.6509864903528697, "naucs_at_1_max": 0.01784958187784493, "naucs_at_1_std": -0.21715888641896902, "naucs_at_1_diff1": 0.7087302847464805, "naucs_at_3_max": 0.08859890109890145, "naucs_at_3_std": -0.28323412698412614, "naucs_at_3_diff1": 0.4830586080586077, "naucs_at_5_max": 0.10656459962550972, "naucs_at_5_std": -0.10389360061680472, "naucs_at_5_diff1": 0.40610199361163074, "naucs_at_10_max": -0.18744164332399568, "naucs_at_10_std": -0.024042950513536908, "naucs_at_10_diff1": 0.6868969810146294, "naucs_at_20_max": -0.22980859010270466, "naucs_at_20_std": -0.1562791783379993, "naucs_at_20_diff1": 0.7112511671335194, "naucs_at_50_max": -0.17133520074697067, "naucs_at_50_std": 0.12278244631185525, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": -0.17133520074697067, "naucs_at_100_std": 0.12278244631185525, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98762, "ndcg_at_5": 0.98762, "ndcg_at_10": 0.98762, "ndcg_at_20": 0.98762, "ndcg_at_50": 0.98762, "ndcg_at_100": 0.98762, "map_at_1": 0.97, "map_at_3": 0.98333, "map_at_5": 0.98333, "map_at_10": 0.98333, "map_at_20": 0.98333, "map_at_50": 0.98333, "map_at_100": 0.98333, "recall_at_1": 0.97, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.97, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.97, "mrr_at_3": 0.9833333333333333, "mrr_at_5": 0.9833333333333333, "mrr_at_10": 0.9833333333333333, "mrr_at_20": 0.9833333333333333, "mrr_at_50": 0.9833333333333333, "mrr_at_100": 0.9833333333333333, "naucs_at_1_max": 0.912854030501093, "naucs_at_1_std": 0.6934329287270453, "naucs_at_1_diff1": 0.912854030501093, "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_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}}