Update results.json
Browse files- results.json +465 -1
results.json
CHANGED
@@ -1 +1,465 @@
|
|
1 |
-
{"./data_dir/eval_vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.664, "ndcg_at_3": 0.71728, "ndcg_at_5": 0.73063, "ndcg_at_10": 0.75071, "ndcg_at_20": 0.76029, "ndcg_at_50": 0.77029, "ndcg_at_100": 0.77647, "map_at_1": 0.664, "map_at_3": 0.70333, "map_at_5": 0.71083, "map_at_10": 0.71913, "map_at_20": 0.72174, "map_at_50": 0.72338, "map_at_100": 0.72393, "recall_at_1": 0.664, "recall_at_3": 0.758, "recall_at_5": 0.79, "recall_at_10": 0.852, "recall_at_20": 0.89, "recall_at_50": 0.94, "recall_at_100": 0.978, "precision_at_1": 0.664, "precision_at_3": 0.25267, "precision_at_5": 0.158, "precision_at_10": 0.0852, "precision_at_20": 0.0445, "precision_at_50": 0.0188, "precision_at_100": 0.00978, "mrr_at_1": 0.666, "mrr_at_3": 0.7036666666666667, "mrr_at_5": 0.7110666666666667, "mrr_at_10": 0.719484126984127, "mrr_at_20": 0.722312611975228, "mrr_at_50": 0.7237972836422734, "mrr_at_100": 0.7243297450156544, "naucs_at_1_max": 0.5889213023056643, "naucs_at_1_std": -0.03738843019443627, "naucs_at_1_diff1": 0.9044815265827187, "naucs_at_3_max": 0.6597876116843661, "naucs_at_3_std": 0.041596651295516755, "naucs_at_3_diff1": 0.8645218684327024, "naucs_at_5_max": 0.6839060283261598, "naucs_at_5_std": 0.11626710270036247, "naucs_at_5_diff1": 0.8423112992040783, "naucs_at_10_max": 0.7812541175850534, "naucs_at_10_std": 0.21647297546578018, "naucs_at_10_diff1": 0.8277202413893048, "naucs_at_20_max": 0.7649600549780963, "naucs_at_20_std": 0.12761790224207298, "naucs_at_20_diff1": 0.7988574864702351, "naucs_at_50_max": 0.7467787114845937, "naucs_at_50_std": 0.2255835667600402, "naucs_at_50_diff1": 0.7687519452225302, "naucs_at_100_max": 0.8461505814447046, "naucs_at_100_std": 0.3166539343009966, "naucs_at_100_diff1": 0.8011628893981787}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.4745, "ndcg_at_3": 0.54173, "ndcg_at_5": 0.56769, "ndcg_at_10": 0.5861, "ndcg_at_20": 0.6048, "ndcg_at_50": 0.61661, "ndcg_at_100": 0.62385, "map_at_1": 0.4745, "map_at_3": 0.52513, "map_at_5": 0.53976, "map_at_10": 0.54722, "map_at_20": 0.55245, "map_at_50": 0.55432, "map_at_100": 0.55497, "recall_at_1": 0.4745, "recall_at_3": 0.5898, "recall_at_5": 0.65188, "recall_at_10": 0.70953, "recall_at_20": 0.78271, "recall_at_50": 0.84257, "recall_at_100": 0.88692, "precision_at_1": 0.4745, "precision_at_3": 0.1966, "precision_at_5": 0.13038, "precision_at_10": 0.07095, "precision_at_20": 0.03914, "precision_at_50": 0.01685, "precision_at_100": 0.00887, "mrr_at_1": 0.4722838137472284, "mrr_at_3": 0.5240206947524021, "mrr_at_5": 0.5384331116038433, "mrr_at_10": 0.545998310632457, "mrr_at_20": 0.5506564713842315, "mrr_at_50": 0.5529029054852187, "mrr_at_100": 0.5535124417758647, "naucs_at_1_max": 0.24308198716486704, "naucs_at_1_std": 0.4263216056628872, "naucs_at_1_diff1": 0.8579772747628749, "naucs_at_3_max": 0.16805600057176534, "naucs_at_3_std": 0.3924645370055808, "naucs_at_3_diff1": 0.7770233728520576, "naucs_at_5_max": 0.1218197178734784, "naucs_at_5_std": 0.4817802245485417, "naucs_at_5_diff1": 0.7532614461045579, "naucs_at_10_max": 0.03428092836449581, "naucs_at_10_std": 0.5151585952399194, "naucs_at_10_diff1": 0.7143986620927637, "naucs_at_20_max": -0.13960806153123748, "naucs_at_20_std": 0.6261345359875006, "naucs_at_20_diff1": 0.6826006385134176, "naucs_at_50_max": -0.2400541568650652, "naucs_at_50_std": 0.7530843562467058, "naucs_at_50_diff1": 0.6593166140032869, "naucs_at_100_max": -0.08884413440903777, "naucs_at_100_std": 0.7993547173030003, "naucs_at_100_diff1": 0.6944870252918233}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.93262, "ndcg_at_5": 0.93693, "ndcg_at_10": 0.93994, "ndcg_at_20": 0.94494, "ndcg_at_50": 0.94702, "ndcg_at_100": 0.94702, "map_at_1": 0.91, "map_at_3": 0.92667, "map_at_5": 0.92917, "map_at_10": 0.93028, "map_at_20": 0.93161, "map_at_50": 0.93198, "map_at_100": 0.93198, "recall_at_1": 0.91, "recall_at_3": 0.95, "recall_at_5": 0.96, "recall_at_10": 0.97, "recall_at_20": 0.99, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.31667, "precision_at_5": 0.192, "precision_at_10": 0.097, "precision_at_20": 0.0495, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.91, "mrr_at_3": 0.9283333333333332, "mrr_at_5": 0.9308333333333333, "mrr_at_10": 0.9319444444444445, "mrr_at_20": 0.9332777777777779, "mrr_at_50": 0.9336944444444444, "mrr_at_100": 0.9336944444444444, "naucs_at_1_max": 0.3011723207801644, "naucs_at_1_std": -0.4870837223778408, "naucs_at_1_diff1": 0.8742089428363928, "naucs_at_3_max": 0.730158730158726, "naucs_at_3_std": -0.21027077497665203, "naucs_at_3_diff1": 0.9183006535947692, "naucs_at_5_max": 0.6953781512605006, "naucs_at_5_std": -0.48015873015872135, "naucs_at_5_diff1": 0.8978758169934612, "naucs_at_10_max": 0.807812013694364, "naucs_at_10_std": -0.06022408963585601, "naucs_at_10_diff1": 0.8638344226579531, "naucs_at_20_max": 0.5541549953314738, "naucs_at_20_std": -0.1713352007469681, "naucs_at_20_diff1": 0.8692810457516413, "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/tatdqa_test": {"ndcg_at_1": 0.64095, "ndcg_at_3": 0.736, "ndcg_at_5": 0.7601, "ndcg_at_10": 0.7803, "ndcg_at_20": 0.78827, "ndcg_at_50": 0.79223, "ndcg_at_100": 0.7941, "map_at_1": 0.64095, "map_at_3": 0.71203, "map_at_5": 0.72546, "map_at_10": 0.734, "map_at_20": 0.73618, "map_at_50": 0.73687, "map_at_100": 0.73703, "recall_at_1": 0.64095, "recall_at_3": 0.80559, "recall_at_5": 0.86391, "recall_at_10": 0.92527, "recall_at_20": 0.95687, "recall_at_50": 0.97631, "recall_at_100": 0.98785, "precision_at_1": 0.64095, "precision_at_3": 0.26853, "precision_at_5": 0.17278, "precision_at_10": 0.09253, "precision_at_20": 0.04784, "precision_at_50": 0.01953, "precision_at_100": 0.00988, "mrr_at_1": 0.6354799513973268, "mrr_at_3": 0.7106115836371001, "mrr_at_5": 0.7234305386796274, "mrr_at_10": 0.731879833747999, "mrr_at_20": 0.7340755638044026, "mrr_at_50": 0.7348432926756366, "mrr_at_100": 0.7350248567706289, "naucs_at_1_max": 0.19811506816235372, "naucs_at_1_std": -0.2554693200419591, "naucs_at_1_diff1": 0.7675648256745395, "naucs_at_3_max": 0.2318301363088243, "naucs_at_3_std": -0.27759660815315446, "naucs_at_3_diff1": 0.6712729518538324, "naucs_at_5_max": 0.24793757976069947, "naucs_at_5_std": -0.2400954177562814, "naucs_at_5_diff1": 0.6522915581849575, "naucs_at_10_max": 0.33999905443604334, "naucs_at_10_std": -0.09243929665705147, "naucs_at_10_diff1": 0.6186302038158574, "naucs_at_20_max": 0.33414218317326, "naucs_at_20_std": 0.10107766265773643, "naucs_at_20_diff1": 0.5589735061846622, "naucs_at_50_max": 0.39336569274053196, "naucs_at_50_std": 0.3146553201604068, "naucs_at_50_diff1": 0.5632664235073339, "naucs_at_100_max": 0.6769613453644149, "naucs_at_100_std": 0.7790878478446186, "naucs_at_100_diff1": 0.6726227816477444}, "./data_dir/eval_vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.7834, "ndcg_at_3": 0.83083, "ndcg_at_5": 0.84232, "ndcg_at_10": 0.85157, "ndcg_at_20": 0.85985, "ndcg_at_50": 0.86443, "ndcg_at_100": 0.8657, "map_at_1": 0.7834, "map_at_3": 0.81984, "map_at_5": 0.82611, "map_at_10": 0.82998, "map_at_20": 0.8323, "map_at_50": 0.83311, "map_at_100": 0.83321, "recall_at_1": 0.7834, "recall_at_3": 0.86235, "recall_at_5": 0.89069, "recall_at_10": 0.91903, "recall_at_20": 0.95142, "recall_at_50": 0.97368, "recall_at_100": 0.98178, "precision_at_1": 0.7834, "precision_at_3": 0.28745, "precision_at_5": 0.17814, "precision_at_10": 0.0919, "precision_at_20": 0.04757, "precision_at_50": 0.01947, "precision_at_100": 0.00982, "mrr_at_1": 0.7813765182186235, "mrr_at_3": 0.8188259109311741, "mrr_at_5": 0.8248987854251012, "mrr_at_10": 0.829565098644046, "mrr_at_20": 0.8313956960718094, "mrr_at_50": 0.8322900405575263, "mrr_at_100": 0.832391579382424, "naucs_at_1_max": 0.518447362653061, "naucs_at_1_std": 0.025991835344041193, "naucs_at_1_diff1": 0.9010494190422811, "naucs_at_3_max": 0.5691970896074877, "naucs_at_3_std": 0.020323756354481724, "naucs_at_3_diff1": 0.8408073942635276, "naucs_at_5_max": 0.5665846312895253, "naucs_at_5_std": 0.08497408554034125, "naucs_at_5_diff1": 0.82223001004187, "naucs_at_10_max": 0.6452921091747841, "naucs_at_10_std": 0.19809424135208908, "naucs_at_10_diff1": 0.8431957937117052, "naucs_at_20_max": 0.7447325753492595, "naucs_at_20_std": 0.4528568090604771, "naucs_at_20_diff1": 0.8030103604465574, "naucs_at_50_max": 0.8343240898820317, "naucs_at_50_std": 0.6770625322907705, "naucs_at_50_diff1": 0.8472448651285527, "naucs_at_100_max": 0.8102131093810145, "naucs_at_100_std": 0.7381222519798937, "naucs_at_100_diff1": 0.8742471393840519}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.96786, "ndcg_at_5": 0.96786, "ndcg_at_10": 0.96786, "ndcg_at_20": 0.96786, "ndcg_at_50": 0.96786, "ndcg_at_100": 0.96786, "map_at_1": 0.92, "map_at_3": 0.95667, "map_at_5": 0.95667, "map_at_10": 0.95667, "map_at_20": 0.95667, "map_at_50": 0.95667, "map_at_100": 0.95667, "recall_at_1": 0.92, "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": 0.92, "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": 0.94, "mrr_at_3": 0.9666666666666667, "mrr_at_5": 0.9666666666666667, "mrr_at_10": 0.9666666666666667, "mrr_at_20": 0.9666666666666667, "mrr_at_50": 0.9666666666666667, "mrr_at_100": 0.9666666666666667, "naucs_at_1_max": 0.7619047619047616, "naucs_at_1_std": 0.24060457516339795, "naucs_at_1_diff1": 0.9162581699346404, "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": 0.56786, "ndcg_at_3": 0.62806, "ndcg_at_5": 0.65635, "ndcg_at_10": 0.67295, "ndcg_at_20": 0.68721, "ndcg_at_50": 0.70267, "ndcg_at_100": 0.71485, "map_at_1": 0.56786, "map_at_3": 0.6131, "map_at_5": 0.62899, "map_at_10": 0.63542, "map_at_20": 0.63924, "map_at_50": 0.64167, "map_at_100": 0.64292, "recall_at_1": 0.56786, "recall_at_3": 0.67143, "recall_at_5": 0.73929, "recall_at_10": 0.79286, "recall_at_20": 0.85, "recall_at_50": 0.92857, "recall_at_100": 1.0, "precision_at_1": 0.56786, "precision_at_3": 0.22381, "precision_at_5": 0.14786, "precision_at_10": 0.07929, "precision_at_20": 0.0425, "precision_at_50": 0.01857, "precision_at_100": 0.01, "mrr_at_1": 0.5678571428571428, "mrr_at_3": 0.6113095238095237, "mrr_at_5": 0.6277380952380953, "mrr_at_10": 0.6339356575963718, "mrr_at_20": 0.6379618770431741, "mrr_at_50": 0.6403947405923297, "mrr_at_100": 0.6416450055922677, "naucs_at_1_max": 0.15868730409527165, "naucs_at_1_std": 0.005476384052524141, "naucs_at_1_diff1": 0.6898556504931816, "naucs_at_3_max": 0.2265285828624092, "naucs_at_3_std": 0.07120249326962727, "naucs_at_3_diff1": 0.6460005820862944, "naucs_at_5_max": 0.18104774909508717, "naucs_at_5_std": 0.049974351749500545, "naucs_at_5_diff1": 0.599728345290476, "naucs_at_10_max": 0.08937034529451629, "naucs_at_10_std": 0.021830460219087747, "naucs_at_10_diff1": 0.5156241862403002, "naucs_at_20_max": -0.015480451861837658, "naucs_at_20_std": -0.04558133048207932, "naucs_at_20_diff1": 0.5020338431500163, "naucs_at_50_max": 0.02670401493930801, "naucs_at_50_std": -0.1887955182072852, "naucs_at_50_diff1": 0.31573295985060545, "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": 0.88, "ndcg_at_3": 0.92786, "ndcg_at_5": 0.94421, "ndcg_at_10": 0.94421, "ndcg_at_20": 0.94421, "ndcg_at_50": 0.94421, "ndcg_at_100": 0.94421, "map_at_1": 0.88, "map_at_3": 0.91667, "map_at_5": 0.92567, "map_at_10": 0.92567, "map_at_20": 0.92567, "map_at_50": 0.92567, "map_at_100": 0.92567, "recall_at_1": 0.88, "recall_at_3": 0.96, "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": 0.88, "precision_at_3": 0.32, "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": 0.91, "mrr_at_3": 0.9333333333333332, "mrr_at_5": 0.9423333333333334, "mrr_at_10": 0.9423333333333334, "mrr_at_20": 0.9423333333333334, "mrr_at_50": 0.9423333333333334, "mrr_at_100": 0.9423333333333334, "naucs_at_1_max": 0.45863824371619505, "naucs_at_1_std": 0.23079064587973264, "naucs_at_1_diff1": 0.8033725739739099, "naucs_at_3_max": 0.8068394024276336, "naucs_at_3_std": 0.5087535014005626, "naucs_at_3_diff1": 0.6038748832866443, "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": 0.45, "ndcg_at_3": 0.59464, "ndcg_at_5": 0.63982, "ndcg_at_10": 0.66889, "ndcg_at_20": 0.67709, "ndcg_at_50": 0.68517, "ndcg_at_100": 0.68853, "map_at_1": 0.45, "map_at_3": 0.55833, "map_at_5": 0.58333, "map_at_10": 0.59531, "map_at_20": 0.59789, "map_at_50": 0.59924, "map_at_100": 0.59957, "recall_at_1": 0.45, "recall_at_3": 0.7, "recall_at_5": 0.81, "recall_at_10": 0.9, "recall_at_20": 0.93, "recall_at_50": 0.97, "recall_at_100": 0.99, "precision_at_1": 0.45, "precision_at_3": 0.23333, "precision_at_5": 0.162, "precision_at_10": 0.09, "precision_at_20": 0.0465, "precision_at_50": 0.0194, "precision_at_100": 0.0099, "mrr_at_1": 0.47, "mrr_at_3": 0.5833333333333334, "mrr_at_5": 0.6018333333333333, "mrr_at_10": 0.615718253968254, "mrr_at_20": 0.6165515873015873, "mrr_at_50": 0.6179859646889059, "mrr_at_100": 0.6183226650256062, "naucs_at_1_max": 0.105925489425784, "naucs_at_1_std": -0.060066784521705045, "naucs_at_1_diff1": 0.49797682184246717, "naucs_at_3_max": 0.11120518825436876, "naucs_at_3_std": -0.10580075662042858, "naucs_at_3_diff1": 0.46674473067915695, "naucs_at_5_max": 0.03777044371103874, "naucs_at_5_std": -0.21048771543820866, "naucs_at_5_diff1": 0.38344072502488297, "naucs_at_10_max": 0.09103641456582774, "naucs_at_10_std": -0.14047619047618726, "naucs_at_10_diff1": 0.32413632119514585, "naucs_at_20_max": -0.0814992663732126, "naucs_at_20_std": -0.3702147525676927, "naucs_at_20_diff1": 0.34020274776577397, "naucs_at_50_max": -0.20401493930905526, "naucs_at_50_std": -0.5308123249299683, "naucs_at_50_diff1": 0.7860255213196357, "naucs_at_100_max": -0.5634920634920583, "naucs_at_100_std": -0.5634920634920583, "naucs_at_100_diff1": 0.35807656395892007}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.95786, "ndcg_at_5": 0.96172, "ndcg_at_10": 0.96172, "ndcg_at_20": 0.96172, "ndcg_at_50": 0.96172, "ndcg_at_100": 0.96332, "map_at_1": 0.92, "map_at_3": 0.95, "map_at_5": 0.952, "map_at_10": 0.952, "map_at_20": 0.952, "map_at_50": 0.952, "map_at_100": 0.95213, "recall_at_1": 0.92, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.92, "mrr_at_3": 0.95, "mrr_at_5": 0.9525, "mrr_at_10": 0.9525, "mrr_at_20": 0.9525, "mrr_at_50": 0.9525, "mrr_at_100": 0.9526315789473684, "naucs_at_1_max": 0.749649859943977, "naucs_at_1_std": 0.25116713352007414, "naucs_at_1_diff1": 0.9279295051353874, "naucs_at_3_max": 0.8611111111111119, "naucs_at_3_std": 0.6790382819794457, "naucs_at_3_diff1": 0.7117180205415458, "naucs_at_5_max": 0.7222222222222276, "naucs_at_5_std": 0.35807656395891135, "naucs_at_5_diff1": 0.8692810457516413, "naucs_at_10_max": 0.7222222222222276, "naucs_at_10_std": 0.35807656395891135, "naucs_at_10_diff1": 0.8692810457516413, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": 0.35807656395891135, "naucs_at_20_diff1": 0.8692810457516413, "naucs_at_50_max": 0.7222222222222041, "naucs_at_50_std": 0.35807656395892007, "naucs_at_50_diff1": 0.8692810457516374, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.42949, "ndcg_at_3": 0.42629, "ndcg_at_5": 0.45961, "ndcg_at_10": 0.51197, "ndcg_at_20": 0.56486, "ndcg_at_50": 0.60082, "ndcg_at_100": 0.60751, "map_at_1": 0.29359, "map_at_3": 0.35849, "map_at_5": 0.39691, "map_at_10": 0.42394, "map_at_20": 0.44497, "map_at_50": 0.45591, "map_at_100": 0.45812, "recall_at_1": 0.29359, "recall_at_3": 0.40192, "recall_at_5": 0.51186, "recall_at_10": 0.65353, "recall_at_20": 0.83719, "recall_at_50": 0.9546, "recall_at_100": 0.98071, "precision_at_1": 0.44231, "precision_at_3": 0.25, "precision_at_5": 0.19615, "precision_at_10": 0.125, "precision_at_20": 0.08173, "precision_at_50": 0.04231, "precision_at_100": 0.02288, "mrr_at_1": 0.4423076923076923, "mrr_at_3": 0.5192307692307692, "mrr_at_5": 0.5413461538461537, "mrr_at_10": 0.5577686202686202, "mrr_at_20": 0.5629998473748473, "mrr_at_50": 0.5671698871052319, "mrr_at_100": 0.5671698871052319, "naucs_at_1_max": 0.12399000241708227, "naucs_at_1_std": -0.1131468297994509, "naucs_at_1_diff1": 0.6622608079388528, "naucs_at_3_max": 0.018540827550754584, "naucs_at_3_std": -0.008541606353824588, "naucs_at_3_diff1": 0.22000823303615963, "naucs_at_5_max": -0.0919163184919483, "naucs_at_5_std": -0.05018222287046767, "naucs_at_5_diff1": 0.017309481258245964, "naucs_at_10_max": -0.1364161654384665, "naucs_at_10_std": -0.0486100321357069, "naucs_at_10_diff1": -0.06329750850536192, "naucs_at_20_max": -0.13951618884131453, "naucs_at_20_std": -0.06516885885416285, "naucs_at_20_diff1": -0.08056945398705187, "naucs_at_50_max": -0.1735505149817269, "naucs_at_50_std": -0.14539655663480958, "naucs_at_50_diff1": -0.22011163171544687, "naucs_at_100_max": -0.19644598055014903, "naucs_at_100_std": -0.17475618011030583, "naucs_at_100_diff1": -0.2681140556014967},
|
2 |
+
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
|
3 |
+
"ndcg_at_1": 0.27586,
|
4 |
+
"ndcg_at_3": 0.27713,
|
5 |
+
"ndcg_at_5": 0.27281,
|
6 |
+
"ndcg_at_10": 0.27095,
|
7 |
+
"ndcg_at_20": 0.30133,
|
8 |
+
"ndcg_at_50": 0.36971,
|
9 |
+
"ndcg_at_100": 0.42129,
|
10 |
+
"map_at_1": 0.02933,
|
11 |
+
"map_at_3": 0.07066,
|
12 |
+
"map_at_5": 0.09633,
|
13 |
+
"map_at_10": 0.12786,
|
14 |
+
"map_at_20": 0.15898,
|
15 |
+
"map_at_50": 0.19579,
|
16 |
+
"map_at_100": 0.21506,
|
17 |
+
"recall_at_1": 0.02933,
|
18 |
+
"recall_at_3": 0.09273,
|
19 |
+
"recall_at_5": 0.14324,
|
20 |
+
"recall_at_10": 0.22118,
|
21 |
+
"recall_at_20": 0.33292,
|
22 |
+
"recall_at_50": 0.5162,
|
23 |
+
"recall_at_100": 0.66532,
|
24 |
+
"precision_at_1": 0.27586,
|
25 |
+
"precision_at_3": 0.27443,
|
26 |
+
"precision_at_5": 0.25862,
|
27 |
+
"precision_at_10": 0.21164,
|
28 |
+
"precision_at_20": 0.17522,
|
29 |
+
"precision_at_50": 0.12422,
|
30 |
+
"precision_at_100": 0.08931,
|
31 |
+
"mrr_at_1": 0.25862068965517243,
|
32 |
+
"mrr_at_3": 0.3599137931034483,
|
33 |
+
"mrr_at_5": 0.38491379310344825,
|
34 |
+
"mrr_at_10": 0.3994766009852217,
|
35 |
+
"mrr_at_20": 0.40535174323707207,
|
36 |
+
"mrr_at_50": 0.4079076367313886,
|
37 |
+
"mrr_at_100": 0.40875255122380105,
|
38 |
+
"naucs_at_1_max": -0.07146268287237412,
|
39 |
+
"naucs_at_1_std": 0.05840538954077893,
|
40 |
+
"naucs_at_1_diff1": 0.09828667132274915,
|
41 |
+
"naucs_at_3_max": -0.03122538350364481,
|
42 |
+
"naucs_at_3_std": 0.17080547439921345,
|
43 |
+
"naucs_at_3_diff1": -0.03118040279119797,
|
44 |
+
"naucs_at_5_max": -0.0063938267739506345,
|
45 |
+
"naucs_at_5_std": 0.20804922213620664,
|
46 |
+
"naucs_at_5_diff1": -0.041295979888552124,
|
47 |
+
"naucs_at_10_max": 0.006023761582402221,
|
48 |
+
"naucs_at_10_std": 0.20080422219815167,
|
49 |
+
"naucs_at_10_diff1": -0.05274519430196443,
|
50 |
+
"naucs_at_20_max": 0.03517298183544102,
|
51 |
+
"naucs_at_20_std": 0.23730900896951754,
|
52 |
+
"naucs_at_20_diff1": -0.041363631387282725,
|
53 |
+
"naucs_at_50_max": 0.014840901846495337,
|
54 |
+
"naucs_at_50_std": 0.20514601668495377,
|
55 |
+
"naucs_at_50_diff1": -0.015531707338321939,
|
56 |
+
"naucs_at_100_max": -0.03634953861480098,
|
57 |
+
"naucs_at_100_std": 0.1191812990989981,
|
58 |
+
"naucs_at_100_diff1": 0.04285003520354746
|
59 |
+
},
|
60 |
+
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
61 |
+
"ndcg_at_1": 0.30556,
|
62 |
+
"ndcg_at_3": 0.33142,
|
63 |
+
"ndcg_at_5": 0.34103,
|
64 |
+
"ndcg_at_10": 0.36136,
|
65 |
+
"ndcg_at_20": 0.3897,
|
66 |
+
"ndcg_at_50": 0.42347,
|
67 |
+
"ndcg_at_100": 0.46291,
|
68 |
+
"map_at_1": 0.15859,
|
69 |
+
"map_at_3": 0.22357,
|
70 |
+
"map_at_5": 0.24838,
|
71 |
+
"map_at_10": 0.27445,
|
72 |
+
"map_at_20": 0.29251,
|
73 |
+
"map_at_50": 0.30304,
|
74 |
+
"map_at_100": 0.31031,
|
75 |
+
"recall_at_1": 0.15859,
|
76 |
+
"recall_at_3": 0.28677,
|
77 |
+
"recall_at_5": 0.34919,
|
78 |
+
"recall_at_10": 0.42618,
|
79 |
+
"recall_at_20": 0.5068,
|
80 |
+
"recall_at_50": 0.61249,
|
81 |
+
"recall_at_100": 0.76787,
|
82 |
+
"precision_at_1": 0.30556,
|
83 |
+
"precision_at_3": 0.21759,
|
84 |
+
"precision_at_5": 0.18611,
|
85 |
+
"precision_at_10": 0.1375,
|
86 |
+
"precision_at_20": 0.09375,
|
87 |
+
"precision_at_50": 0.04972,
|
88 |
+
"precision_at_100": 0.03292,
|
89 |
+
"mrr_at_1": 0.3055555555555556,
|
90 |
+
"mrr_at_3": 0.40046296296296297,
|
91 |
+
"mrr_at_5": 0.4212962962962963,
|
92 |
+
"mrr_at_10": 0.4328703703703704,
|
93 |
+
"mrr_at_20": 0.4353395061728395,
|
94 |
+
"mrr_at_50": 0.43782901538648666,
|
95 |
+
"mrr_at_100": 0.43938177243325466,
|
96 |
+
"naucs_at_1_max": -0.11972891665546266,
|
97 |
+
"naucs_at_1_std": 0.06803454075231265,
|
98 |
+
"naucs_at_1_diff1": 0.12277473841932252,
|
99 |
+
"naucs_at_3_max": -0.1280661381189997,
|
100 |
+
"naucs_at_3_std": 0.02955099347035927,
|
101 |
+
"naucs_at_3_diff1": -0.03229451352547933,
|
102 |
+
"naucs_at_5_max": -0.1473259550162733,
|
103 |
+
"naucs_at_5_std": -0.02817022199099353,
|
104 |
+
"naucs_at_5_diff1": 0.030713613360775806,
|
105 |
+
"naucs_at_10_max": -0.22965382145468607,
|
106 |
+
"naucs_at_10_std": -0.11078003228382262,
|
107 |
+
"naucs_at_10_diff1": 0.09039041461079847,
|
108 |
+
"naucs_at_20_max": -0.2807490883701333,
|
109 |
+
"naucs_at_20_std": -0.13575968442367178,
|
110 |
+
"naucs_at_20_diff1": 0.04284557748233534,
|
111 |
+
"naucs_at_50_max": -0.32202951157642307,
|
112 |
+
"naucs_at_50_std": -0.16461590657158515,
|
113 |
+
"naucs_at_50_diff1": 0.05400900095557806,
|
114 |
+
"naucs_at_100_max": -0.3858673402829035,
|
115 |
+
"naucs_at_100_std": -0.26052679356501335,
|
116 |
+
"naucs_at_100_diff1": 0.04019360896291041
|
117 |
+
},
|
118 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
|
119 |
+
"ndcg_at_1": 0.49375,
|
120 |
+
"ndcg_at_3": 0.50545,
|
121 |
+
"ndcg_at_5": 0.5323,
|
122 |
+
"ndcg_at_10": 0.56265,
|
123 |
+
"ndcg_at_20": 0.5911,
|
124 |
+
"ndcg_at_50": 0.61736,
|
125 |
+
"ndcg_at_100": 0.62829,
|
126 |
+
"map_at_1": 0.29789,
|
127 |
+
"map_at_3": 0.40402,
|
128 |
+
"map_at_5": 0.43762,
|
129 |
+
"map_at_10": 0.46432,
|
130 |
+
"map_at_20": 0.47787,
|
131 |
+
"map_at_50": 0.48644,
|
132 |
+
"map_at_100": 0.48877,
|
133 |
+
"recall_at_1": 0.29789,
|
134 |
+
"recall_at_3": 0.49153,
|
135 |
+
"recall_at_5": 0.57504,
|
136 |
+
"recall_at_10": 0.66868,
|
137 |
+
"recall_at_20": 0.752,
|
138 |
+
"recall_at_50": 0.83661,
|
139 |
+
"recall_at_100": 0.87411,
|
140 |
+
"precision_at_1": 0.49375,
|
141 |
+
"precision_at_3": 0.30625,
|
142 |
+
"precision_at_5": 0.23875,
|
143 |
+
"precision_at_10": 0.15437,
|
144 |
+
"precision_at_20": 0.09375,
|
145 |
+
"precision_at_50": 0.04525,
|
146 |
+
"precision_at_100": 0.02513,
|
147 |
+
"mrr_at_1": 0.4875,
|
148 |
+
"mrr_at_3": 0.584375,
|
149 |
+
"mrr_at_5": 0.6109375,
|
150 |
+
"mrr_at_10": 0.6181274801587302,
|
151 |
+
"mrr_at_20": 0.6211626073069088,
|
152 |
+
"mrr_at_50": 0.6224454491663636,
|
153 |
+
"mrr_at_100": 0.6225276860084688,
|
154 |
+
"naucs_at_1_max": 0.25971597849480205,
|
155 |
+
"naucs_at_1_std": -0.06591160266903759,
|
156 |
+
"naucs_at_1_diff1": 0.5137897509618341,
|
157 |
+
"naucs_at_3_max": 0.11511378826266674,
|
158 |
+
"naucs_at_3_std": -0.09491769996140816,
|
159 |
+
"naucs_at_3_diff1": 0.058686667002243,
|
160 |
+
"naucs_at_5_max": -0.01429372317252162,
|
161 |
+
"naucs_at_5_std": -0.08153841545091527,
|
162 |
+
"naucs_at_5_diff1": -0.11086194574376519,
|
163 |
+
"naucs_at_10_max": -0.04159388354898861,
|
164 |
+
"naucs_at_10_std": -0.08637885577524719,
|
165 |
+
"naucs_at_10_diff1": -0.1934197141662387,
|
166 |
+
"naucs_at_20_max": -0.06441956054177954,
|
167 |
+
"naucs_at_20_std": -0.022475783052031732,
|
168 |
+
"naucs_at_20_diff1": -0.2666709162895124,
|
169 |
+
"naucs_at_50_max": -0.0809057806099224,
|
170 |
+
"naucs_at_50_std": 0.04951610616563597,
|
171 |
+
"naucs_at_50_diff1": -0.2749968287605298,
|
172 |
+
"naucs_at_100_max": -0.13466182313615915,
|
173 |
+
"naucs_at_100_std": 0.04146134949414454,
|
174 |
+
"naucs_at_100_diff1": -0.30851157836220766
|
175 |
+
},
|
176 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
|
177 |
+
"ndcg_at_1": 0.15789,
|
178 |
+
"ndcg_at_3": 0.24589,
|
179 |
+
"ndcg_at_5": 0.27172,
|
180 |
+
"ndcg_at_10": 0.32485,
|
181 |
+
"ndcg_at_20": 0.36737,
|
182 |
+
"ndcg_at_50": 0.44367,
|
183 |
+
"ndcg_at_100": 0.46973,
|
184 |
+
"map_at_1": 0.10073,
|
185 |
+
"map_at_3": 0.18119,
|
186 |
+
"map_at_5": 0.20461,
|
187 |
+
"map_at_10": 0.2311,
|
188 |
+
"map_at_20": 0.25013,
|
189 |
+
"map_at_50": 0.27424,
|
190 |
+
"map_at_100": 0.28404,
|
191 |
+
"recall_at_1": 0.10073,
|
192 |
+
"recall_at_3": 0.26447,
|
193 |
+
"recall_at_5": 0.33158,
|
194 |
+
"recall_at_10": 0.4669,
|
195 |
+
"recall_at_20": 0.58975,
|
196 |
+
"recall_at_50": 0.84549,
|
197 |
+
"recall_at_100": 0.92588,
|
198 |
+
"precision_at_1": 0.15789,
|
199 |
+
"precision_at_3": 0.16959,
|
200 |
+
"precision_at_5": 0.14035,
|
201 |
+
"precision_at_10": 0.10877,
|
202 |
+
"precision_at_20": 0.08158,
|
203 |
+
"precision_at_50": 0.06,
|
204 |
+
"precision_at_100": 0.03737,
|
205 |
+
"mrr_at_1": 0.14035087719298245,
|
206 |
+
"mrr_at_3": 0.2807017543859649,
|
207 |
+
"mrr_at_5": 0.2982456140350877,
|
208 |
+
"mrr_at_10": 0.32170704539125594,
|
209 |
+
"mrr_at_20": 0.32845867401839374,
|
210 |
+
"mrr_at_50": 0.33345518300422383,
|
211 |
+
"mrr_at_100": 0.33345518300422383,
|
212 |
+
"naucs_at_1_max": 0.22400453476615198,
|
213 |
+
"naucs_at_1_std": 0.14968053041273224,
|
214 |
+
"naucs_at_1_diff1": 0.016172762313913572,
|
215 |
+
"naucs_at_3_max": 0.10813294914982394,
|
216 |
+
"naucs_at_3_std": 0.0650117553746402,
|
217 |
+
"naucs_at_3_diff1": -0.040697907716350505,
|
218 |
+
"naucs_at_5_max": -0.05712505615849394,
|
219 |
+
"naucs_at_5_std": -0.09866938564148231,
|
220 |
+
"naucs_at_5_diff1": 0.05016230281598974,
|
221 |
+
"naucs_at_10_max": -0.1020292479643766,
|
222 |
+
"naucs_at_10_std": -0.10874541622319586,
|
223 |
+
"naucs_at_10_diff1": -0.06638258303490649,
|
224 |
+
"naucs_at_20_max": -0.2958585292412995,
|
225 |
+
"naucs_at_20_std": -0.23597870154597572,
|
226 |
+
"naucs_at_20_diff1": -0.07170339252413134,
|
227 |
+
"naucs_at_50_max": -0.40829026815447106,
|
228 |
+
"naucs_at_50_std": -0.2811013441409715,
|
229 |
+
"naucs_at_50_diff1": -0.21951620832847335,
|
230 |
+
"naucs_at_100_max": -0.4146346375147778,
|
231 |
+
"naucs_at_100_std": -0.2795469565018257,
|
232 |
+
"naucs_at_100_diff1": -0.2553840696821133
|
233 |
+
},
|
234 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
|
235 |
+
"ndcg_at_1": 0.24123,
|
236 |
+
"ndcg_at_3": 0.28126,
|
237 |
+
"ndcg_at_5": 0.3133,
|
238 |
+
"ndcg_at_10": 0.36429,
|
239 |
+
"ndcg_at_20": 0.4161,
|
240 |
+
"ndcg_at_50": 0.47237,
|
241 |
+
"ndcg_at_100": 0.4958,
|
242 |
+
"map_at_1": 0.12746,
|
243 |
+
"map_at_3": 0.20411,
|
244 |
+
"map_at_5": 0.23304,
|
245 |
+
"map_at_10": 0.26447,
|
246 |
+
"map_at_20": 0.28692,
|
247 |
+
"map_at_50": 0.30711,
|
248 |
+
"map_at_100": 0.31548,
|
249 |
+
"recall_at_1": 0.12746,
|
250 |
+
"recall_at_3": 0.27589,
|
251 |
+
"recall_at_5": 0.36653,
|
252 |
+
"recall_at_10": 0.50529,
|
253 |
+
"recall_at_20": 0.66852,
|
254 |
+
"recall_at_50": 0.84526,
|
255 |
+
"recall_at_100": 0.92261,
|
256 |
+
"precision_at_1": 0.24123,
|
257 |
+
"precision_at_3": 0.19006,
|
258 |
+
"precision_at_5": 0.16316,
|
259 |
+
"precision_at_10": 0.12412,
|
260 |
+
"precision_at_20": 0.09232,
|
261 |
+
"precision_at_50": 0.05991,
|
262 |
+
"precision_at_100": 0.03645,
|
263 |
+
"mrr_at_1": 0.2324561403508772,
|
264 |
+
"mrr_at_3": 0.3362573099415205,
|
265 |
+
"mrr_at_5": 0.3564327485380117,
|
266 |
+
"mrr_at_10": 0.37909530771372874,
|
267 |
+
"mrr_at_20": 0.3880419270226994,
|
268 |
+
"mrr_at_50": 0.39104871811852004,
|
269 |
+
"mrr_at_100": 0.3913246488656195,
|
270 |
+
"naucs_at_1_max": 0.05126072306607597,
|
271 |
+
"naucs_at_1_std": 0.10524261906614556,
|
272 |
+
"naucs_at_1_diff1": 0.1662238649208727,
|
273 |
+
"naucs_at_3_max": -0.06882640588074418,
|
274 |
+
"naucs_at_3_std": -0.00687112776813947,
|
275 |
+
"naucs_at_3_diff1": 0.052359712799228894,
|
276 |
+
"naucs_at_5_max": -0.10672500814999647,
|
277 |
+
"naucs_at_5_std": -0.04616075188696077,
|
278 |
+
"naucs_at_5_diff1": 0.03808892702804544,
|
279 |
+
"naucs_at_10_max": -0.14402718163269573,
|
280 |
+
"naucs_at_10_std": -0.0800239875853204,
|
281 |
+
"naucs_at_10_diff1": 0.026621054060269014,
|
282 |
+
"naucs_at_20_max": -0.23536652634236535,
|
283 |
+
"naucs_at_20_std": -0.1791895245057551,
|
284 |
+
"naucs_at_20_diff1": -0.03550522345427236,
|
285 |
+
"naucs_at_50_max": -0.2895689158573214,
|
286 |
+
"naucs_at_50_std": -0.18484936511140687,
|
287 |
+
"naucs_at_50_diff1": -0.14671395313510677,
|
288 |
+
"naucs_at_100_max": -0.3013378788868252,
|
289 |
+
"naucs_at_100_std": -0.18494428073687805,
|
290 |
+
"naucs_at_100_diff1": -0.15560894907194894
|
291 |
+
},
|
292 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
|
293 |
+
"ndcg_at_1": 0.29688,
|
294 |
+
"ndcg_at_3": 0.31686,
|
295 |
+
"ndcg_at_5": 0.34035,
|
296 |
+
"ndcg_at_10": 0.37208,
|
297 |
+
"ndcg_at_20": 0.39946,
|
298 |
+
"ndcg_at_50": 0.43258,
|
299 |
+
"ndcg_at_100": 0.45037,
|
300 |
+
"map_at_1": 0.19114,
|
301 |
+
"map_at_3": 0.25227,
|
302 |
+
"map_at_5": 0.27618,
|
303 |
+
"map_at_10": 0.29729,
|
304 |
+
"map_at_20": 0.3094,
|
305 |
+
"map_at_50": 0.3174,
|
306 |
+
"map_at_100": 0.32008,
|
307 |
+
"recall_at_1": 0.19114,
|
308 |
+
"recall_at_3": 0.30932,
|
309 |
+
"recall_at_5": 0.37926,
|
310 |
+
"recall_at_10": 0.47025,
|
311 |
+
"recall_at_20": 0.5506,
|
312 |
+
"recall_at_50": 0.67285,
|
313 |
+
"recall_at_100": 0.74884,
|
314 |
+
"precision_at_1": 0.29688,
|
315 |
+
"precision_at_3": 0.1875,
|
316 |
+
"precision_at_5": 0.15063,
|
317 |
+
"precision_at_10": 0.10203,
|
318 |
+
"precision_at_20": 0.06555,
|
319 |
+
"precision_at_50": 0.03431,
|
320 |
+
"precision_at_100": 0.02019,
|
321 |
+
"mrr_at_1": 0.3046875,
|
322 |
+
"mrr_at_3": 0.3731770833333333,
|
323 |
+
"mrr_at_5": 0.3956770833333333,
|
324 |
+
"mrr_at_10": 0.4083984375,
|
325 |
+
"mrr_at_20": 0.41272608241055897,
|
326 |
+
"mrr_at_50": 0.41586130365740753,
|
327 |
+
"mrr_at_100": 0.4167288615149892,
|
328 |
+
"naucs_at_1_max": 0.09311618037135276,
|
329 |
+
"naucs_at_1_std": 0.018985676392572978,
|
330 |
+
"naucs_at_1_diff1": 0.48117347480106093,
|
331 |
+
"naucs_at_3_max": -0.0034360394668514023,
|
332 |
+
"naucs_at_3_std": 0.0026758409785930777,
|
333 |
+
"naucs_at_3_diff1": 0.17766574346546632,
|
334 |
+
"naucs_at_5_max": -0.013139840013063666,
|
335 |
+
"naucs_at_5_std": 0.02534411706670989,
|
336 |
+
"naucs_at_5_diff1": 0.09008620787415184,
|
337 |
+
"naucs_at_10_max": -0.05607839101439326,
|
338 |
+
"naucs_at_10_std": -0.014157807759662628,
|
339 |
+
"naucs_at_10_diff1": 0.007634295473431183,
|
340 |
+
"naucs_at_20_max": -0.051514513496406455,
|
341 |
+
"naucs_at_20_std": 0.013220188409135334,
|
342 |
+
"naucs_at_20_diff1": -0.05545218918531808,
|
343 |
+
"naucs_at_50_max": -0.05476112736426545,
|
344 |
+
"naucs_at_50_std": 0.027217039442371384,
|
345 |
+
"naucs_at_50_diff1": -0.08576521492878854,
|
346 |
+
"naucs_at_100_max": -0.0861361198809646,
|
347 |
+
"naucs_at_100_std": 0.0018778606927599745,
|
348 |
+
"naucs_at_100_diff1": -0.10821538089699209
|
349 |
+
},
|
350 |
+
"vidore/synthetic_axa_filtered_v1.0": {
|
351 |
+
"ndcg_at_1": 0.38889,
|
352 |
+
"ndcg_at_3": 0.48966,
|
353 |
+
"ndcg_at_5": 0.50412,
|
354 |
+
"ndcg_at_10": 0.52545,
|
355 |
+
"ndcg_at_20": 0.55696,
|
356 |
+
"ndcg_at_50": 0.59341,
|
357 |
+
"ndcg_at_100": 0.62141,
|
358 |
+
"map_at_1": 0.24444,
|
359 |
+
"map_at_3": 0.34782,
|
360 |
+
"map_at_5": 0.38206,
|
361 |
+
"map_at_10": 0.41966,
|
362 |
+
"map_at_20": 0.44673,
|
363 |
+
"map_at_50": 0.46066,
|
364 |
+
"map_at_100": 0.46871,
|
365 |
+
"recall_at_1": 0.24444,
|
366 |
+
"recall_at_3": 0.44533,
|
367 |
+
"recall_at_5": 0.50466,
|
368 |
+
"recall_at_10": 0.58675,
|
369 |
+
"recall_at_20": 0.67712,
|
370 |
+
"recall_at_50": 0.78932,
|
371 |
+
"recall_at_100": 0.87381,
|
372 |
+
"precision_at_1": 0.38889,
|
373 |
+
"precision_at_3": 0.31481,
|
374 |
+
"precision_at_5": 0.27778,
|
375 |
+
"precision_at_10": 0.21111,
|
376 |
+
"precision_at_20": 0.13889,
|
377 |
+
"precision_at_50": 0.07,
|
378 |
+
"precision_at_100": 0.04222,
|
379 |
+
"mrr_at_1": 0.3888888888888889,
|
380 |
+
"mrr_at_3": 0.5648148148148148,
|
381 |
+
"mrr_at_5": 0.5648148148148148,
|
382 |
+
"mrr_at_10": 0.5833333333333334,
|
383 |
+
"mrr_at_20": 0.5833333333333334,
|
384 |
+
"mrr_at_50": 0.5852490421455939,
|
385 |
+
"mrr_at_100": 0.5852490421455939,
|
386 |
+
"naucs_at_1_max": 0.06414390748033702,
|
387 |
+
"naucs_at_1_std": 0.09361633218553407,
|
388 |
+
"naucs_at_1_diff1": 0.3199354953342075,
|
389 |
+
"naucs_at_3_max": -0.29656915329520506,
|
390 |
+
"naucs_at_3_std": -0.2689215816405609,
|
391 |
+
"naucs_at_3_diff1": -0.048998778682797145,
|
392 |
+
"naucs_at_5_max": -0.4684237523665628,
|
393 |
+
"naucs_at_5_std": -0.4808166158380195,
|
394 |
+
"naucs_at_5_diff1": 0.03529551410696337,
|
395 |
+
"naucs_at_10_max": -0.6046861759557787,
|
396 |
+
"naucs_at_10_std": -0.5599671369036879,
|
397 |
+
"naucs_at_10_diff1": 0.09315401422887992,
|
398 |
+
"naucs_at_20_max": -0.6391674592430706,
|
399 |
+
"naucs_at_20_std": -0.5502288596488522,
|
400 |
+
"naucs_at_20_diff1": 0.08812208804345464,
|
401 |
+
"naucs_at_50_max": -0.6209697401456671,
|
402 |
+
"naucs_at_50_std": -0.46600812024697114,
|
403 |
+
"naucs_at_50_diff1": 0.06782711055635444,
|
404 |
+
"naucs_at_100_max": -0.6408164300214637,
|
405 |
+
"naucs_at_100_std": -0.49700512525148827,
|
406 |
+
"naucs_at_100_diff1": -0.010718202819271922
|
407 |
+
},
|
408 |
+
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
|
409 |
+
"ndcg_at_1": 0.55172,
|
410 |
+
"ndcg_at_3": 0.56242,
|
411 |
+
"ndcg_at_5": 0.53354,
|
412 |
+
"ndcg_at_10": 0.52325,
|
413 |
+
"ndcg_at_20": 0.54892,
|
414 |
+
"ndcg_at_50": 0.61967,
|
415 |
+
"ndcg_at_100": 0.65501,
|
416 |
+
"map_at_1": 0.05811,
|
417 |
+
"map_at_3": 0.1554,
|
418 |
+
"map_at_5": 0.20983,
|
419 |
+
"map_at_10": 0.27655,
|
420 |
+
"map_at_20": 0.32835,
|
421 |
+
"map_at_50": 0.38835,
|
422 |
+
"map_at_100": 0.41442,
|
423 |
+
"recall_at_1": 0.05811,
|
424 |
+
"recall_at_3": 0.19803,
|
425 |
+
"recall_at_5": 0.29414,
|
426 |
+
"recall_at_10": 0.43784,
|
427 |
+
"recall_at_20": 0.58599,
|
428 |
+
"recall_at_50": 0.78993,
|
429 |
+
"recall_at_100": 0.89218,
|
430 |
+
"precision_at_1": 0.55172,
|
431 |
+
"precision_at_3": 0.55747,
|
432 |
+
"precision_at_5": 0.48621,
|
433 |
+
"precision_at_10": 0.38966,
|
434 |
+
"precision_at_20": 0.29569,
|
435 |
+
"precision_at_50": 0.18897,
|
436 |
+
"precision_at_100": 0.12362,
|
437 |
+
"mrr_at_1": 0.5172413793103449,
|
438 |
+
"mrr_at_3": 0.6494252873563218,
|
439 |
+
"mrr_at_5": 0.6727011494252874,
|
440 |
+
"mrr_at_10": 0.6834770114942529,
|
441 |
+
"mrr_at_20": 0.6859279918864097,
|
442 |
+
"mrr_at_50": 0.6859279918864097,
|
443 |
+
"mrr_at_100": 0.6859279918864097,
|
444 |
+
"naucs_at_1_max": -0.2980988447497177,
|
445 |
+
"naucs_at_1_std": -0.21908510961071032,
|
446 |
+
"naucs_at_1_diff1": 0.12536739639550157,
|
447 |
+
"naucs_at_3_max": -0.04843642666725592,
|
448 |
+
"naucs_at_3_std": 0.0549203425432818,
|
449 |
+
"naucs_at_3_diff1": -0.050133695427531995,
|
450 |
+
"naucs_at_5_max": -0.0597678996153892,
|
451 |
+
"naucs_at_5_std": 0.07952714662316937,
|
452 |
+
"naucs_at_5_diff1": -0.03461754450178797,
|
453 |
+
"naucs_at_10_max": -0.1236409449095761,
|
454 |
+
"naucs_at_10_std": 0.019540468488830887,
|
455 |
+
"naucs_at_10_diff1": -0.07973899114901141,
|
456 |
+
"naucs_at_20_max": -0.05543962463891419,
|
457 |
+
"naucs_at_20_std": 0.08259432774295383,
|
458 |
+
"naucs_at_20_diff1": -0.0939866678506067,
|
459 |
+
"naucs_at_50_max": -0.026948237382347934,
|
460 |
+
"naucs_at_50_std": 0.09883880061905886,
|
461 |
+
"naucs_at_50_diff1": -0.03217943812138621,
|
462 |
+
"naucs_at_100_max": -0.08286980330809063,
|
463 |
+
"naucs_at_100_std": 0.016514989416905417,
|
464 |
+
"naucs_at_100_diff1": 0.027317685280586253
|
465 |
+
},"./data_dir/eval_vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.664, "ndcg_at_3": 0.71728, "ndcg_at_5": 0.73063, "ndcg_at_10": 0.75071, "ndcg_at_20": 0.76029, "ndcg_at_50": 0.77029, "ndcg_at_100": 0.77647, "map_at_1": 0.664, "map_at_3": 0.70333, "map_at_5": 0.71083, "map_at_10": 0.71913, "map_at_20": 0.72174, "map_at_50": 0.72338, "map_at_100": 0.72393, "recall_at_1": 0.664, "recall_at_3": 0.758, "recall_at_5": 0.79, "recall_at_10": 0.852, "recall_at_20": 0.89, "recall_at_50": 0.94, "recall_at_100": 0.978, "precision_at_1": 0.664, "precision_at_3": 0.25267, "precision_at_5": 0.158, "precision_at_10": 0.0852, "precision_at_20": 0.0445, "precision_at_50": 0.0188, "precision_at_100": 0.00978, "mrr_at_1": 0.666, "mrr_at_3": 0.7036666666666667, "mrr_at_5": 0.7110666666666667, "mrr_at_10": 0.719484126984127, "mrr_at_20": 0.722312611975228, "mrr_at_50": 0.7237972836422734, "mrr_at_100": 0.7243297450156544, "naucs_at_1_max": 0.5889213023056643, "naucs_at_1_std": -0.03738843019443627, "naucs_at_1_diff1": 0.9044815265827187, "naucs_at_3_max": 0.6597876116843661, "naucs_at_3_std": 0.041596651295516755, "naucs_at_3_diff1": 0.8645218684327024, "naucs_at_5_max": 0.6839060283261598, "naucs_at_5_std": 0.11626710270036247, "naucs_at_5_diff1": 0.8423112992040783, "naucs_at_10_max": 0.7812541175850534, "naucs_at_10_std": 0.21647297546578018, "naucs_at_10_diff1": 0.8277202413893048, "naucs_at_20_max": 0.7649600549780963, "naucs_at_20_std": 0.12761790224207298, "naucs_at_20_diff1": 0.7988574864702351, "naucs_at_50_max": 0.7467787114845937, "naucs_at_50_std": 0.2255835667600402, "naucs_at_50_diff1": 0.7687519452225302, "naucs_at_100_max": 0.8461505814447046, "naucs_at_100_std": 0.3166539343009966, "naucs_at_100_diff1": 0.8011628893981787}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.4745, "ndcg_at_3": 0.54173, "ndcg_at_5": 0.56769, "ndcg_at_10": 0.5861, "ndcg_at_20": 0.6048, "ndcg_at_50": 0.61661, "ndcg_at_100": 0.62385, "map_at_1": 0.4745, "map_at_3": 0.52513, "map_at_5": 0.53976, "map_at_10": 0.54722, "map_at_20": 0.55245, "map_at_50": 0.55432, "map_at_100": 0.55497, "recall_at_1": 0.4745, "recall_at_3": 0.5898, "recall_at_5": 0.65188, "recall_at_10": 0.70953, "recall_at_20": 0.78271, "recall_at_50": 0.84257, "recall_at_100": 0.88692, "precision_at_1": 0.4745, "precision_at_3": 0.1966, "precision_at_5": 0.13038, "precision_at_10": 0.07095, "precision_at_20": 0.03914, "precision_at_50": 0.01685, "precision_at_100": 0.00887, "mrr_at_1": 0.4722838137472284, "mrr_at_3": 0.5240206947524021, "mrr_at_5": 0.5384331116038433, "mrr_at_10": 0.545998310632457, "mrr_at_20": 0.5506564713842315, "mrr_at_50": 0.5529029054852187, "mrr_at_100": 0.5535124417758647, "naucs_at_1_max": 0.24308198716486704, "naucs_at_1_std": 0.4263216056628872, "naucs_at_1_diff1": 0.8579772747628749, "naucs_at_3_max": 0.16805600057176534, "naucs_at_3_std": 0.3924645370055808, "naucs_at_3_diff1": 0.7770233728520576, "naucs_at_5_max": 0.1218197178734784, "naucs_at_5_std": 0.4817802245485417, "naucs_at_5_diff1": 0.7532614461045579, "naucs_at_10_max": 0.03428092836449581, "naucs_at_10_std": 0.5151585952399194, "naucs_at_10_diff1": 0.7143986620927637, "naucs_at_20_max": -0.13960806153123748, "naucs_at_20_std": 0.6261345359875006, "naucs_at_20_diff1": 0.6826006385134176, "naucs_at_50_max": -0.2400541568650652, "naucs_at_50_std": 0.7530843562467058, "naucs_at_50_diff1": 0.6593166140032869, "naucs_at_100_max": -0.08884413440903777, "naucs_at_100_std": 0.7993547173030003, "naucs_at_100_diff1": 0.6944870252918233}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.93262, "ndcg_at_5": 0.93693, "ndcg_at_10": 0.93994, "ndcg_at_20": 0.94494, "ndcg_at_50": 0.94702, "ndcg_at_100": 0.94702, "map_at_1": 0.91, "map_at_3": 0.92667, "map_at_5": 0.92917, "map_at_10": 0.93028, "map_at_20": 0.93161, "map_at_50": 0.93198, "map_at_100": 0.93198, "recall_at_1": 0.91, "recall_at_3": 0.95, "recall_at_5": 0.96, "recall_at_10": 0.97, "recall_at_20": 0.99, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.31667, "precision_at_5": 0.192, "precision_at_10": 0.097, "precision_at_20": 0.0495, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.91, "mrr_at_3": 0.9283333333333332, "mrr_at_5": 0.9308333333333333, "mrr_at_10": 0.9319444444444445, "mrr_at_20": 0.9332777777777779, "mrr_at_50": 0.9336944444444444, "mrr_at_100": 0.9336944444444444, "naucs_at_1_max": 0.3011723207801644, "naucs_at_1_std": -0.4870837223778408, "naucs_at_1_diff1": 0.8742089428363928, "naucs_at_3_max": 0.730158730158726, "naucs_at_3_std": -0.21027077497665203, "naucs_at_3_diff1": 0.9183006535947692, "naucs_at_5_max": 0.6953781512605006, "naucs_at_5_std": -0.48015873015872135, "naucs_at_5_diff1": 0.8978758169934612, "naucs_at_10_max": 0.807812013694364, "naucs_at_10_std": -0.06022408963585601, "naucs_at_10_diff1": 0.8638344226579531, "naucs_at_20_max": 0.5541549953314738, "naucs_at_20_std": -0.1713352007469681, "naucs_at_20_diff1": 0.8692810457516413, "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/tatdqa_test": {"ndcg_at_1": 0.64095, "ndcg_at_3": 0.736, "ndcg_at_5": 0.7601, "ndcg_at_10": 0.7803, "ndcg_at_20": 0.78827, "ndcg_at_50": 0.79223, "ndcg_at_100": 0.7941, "map_at_1": 0.64095, "map_at_3": 0.71203, "map_at_5": 0.72546, "map_at_10": 0.734, "map_at_20": 0.73618, "map_at_50": 0.73687, "map_at_100": 0.73703, "recall_at_1": 0.64095, "recall_at_3": 0.80559, "recall_at_5": 0.86391, "recall_at_10": 0.92527, "recall_at_20": 0.95687, "recall_at_50": 0.97631, "recall_at_100": 0.98785, "precision_at_1": 0.64095, "precision_at_3": 0.26853, "precision_at_5": 0.17278, "precision_at_10": 0.09253, "precision_at_20": 0.04784, "precision_at_50": 0.01953, "precision_at_100": 0.00988, "mrr_at_1": 0.6354799513973268, "mrr_at_3": 0.7106115836371001, "mrr_at_5": 0.7234305386796274, "mrr_at_10": 0.731879833747999, "mrr_at_20": 0.7340755638044026, "mrr_at_50": 0.7348432926756366, "mrr_at_100": 0.7350248567706289, "naucs_at_1_max": 0.19811506816235372, "naucs_at_1_std": -0.2554693200419591, "naucs_at_1_diff1": 0.7675648256745395, "naucs_at_3_max": 0.2318301363088243, "naucs_at_3_std": -0.27759660815315446, "naucs_at_3_diff1": 0.6712729518538324, "naucs_at_5_max": 0.24793757976069947, "naucs_at_5_std": -0.2400954177562814, "naucs_at_5_diff1": 0.6522915581849575, "naucs_at_10_max": 0.33999905443604334, "naucs_at_10_std": -0.09243929665705147, "naucs_at_10_diff1": 0.6186302038158574, "naucs_at_20_max": 0.33414218317326, "naucs_at_20_std": 0.10107766265773643, "naucs_at_20_diff1": 0.5589735061846622, "naucs_at_50_max": 0.39336569274053196, "naucs_at_50_std": 0.3146553201604068, "naucs_at_50_diff1": 0.5632664235073339, "naucs_at_100_max": 0.6769613453644149, "naucs_at_100_std": 0.7790878478446186, "naucs_at_100_diff1": 0.6726227816477444}, "./data_dir/eval_vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.7834, "ndcg_at_3": 0.83083, "ndcg_at_5": 0.84232, "ndcg_at_10": 0.85157, "ndcg_at_20": 0.85985, "ndcg_at_50": 0.86443, "ndcg_at_100": 0.8657, "map_at_1": 0.7834, "map_at_3": 0.81984, "map_at_5": 0.82611, "map_at_10": 0.82998, "map_at_20": 0.8323, "map_at_50": 0.83311, "map_at_100": 0.83321, "recall_at_1": 0.7834, "recall_at_3": 0.86235, "recall_at_5": 0.89069, "recall_at_10": 0.91903, "recall_at_20": 0.95142, "recall_at_50": 0.97368, "recall_at_100": 0.98178, "precision_at_1": 0.7834, "precision_at_3": 0.28745, "precision_at_5": 0.17814, "precision_at_10": 0.0919, "precision_at_20": 0.04757, "precision_at_50": 0.01947, "precision_at_100": 0.00982, "mrr_at_1": 0.7813765182186235, "mrr_at_3": 0.8188259109311741, "mrr_at_5": 0.8248987854251012, "mrr_at_10": 0.829565098644046, "mrr_at_20": 0.8313956960718094, "mrr_at_50": 0.8322900405575263, "mrr_at_100": 0.832391579382424, "naucs_at_1_max": 0.518447362653061, "naucs_at_1_std": 0.025991835344041193, "naucs_at_1_diff1": 0.9010494190422811, "naucs_at_3_max": 0.5691970896074877, "naucs_at_3_std": 0.020323756354481724, "naucs_at_3_diff1": 0.8408073942635276, "naucs_at_5_max": 0.5665846312895253, "naucs_at_5_std": 0.08497408554034125, "naucs_at_5_diff1": 0.82223001004187, "naucs_at_10_max": 0.6452921091747841, "naucs_at_10_std": 0.19809424135208908, "naucs_at_10_diff1": 0.8431957937117052, "naucs_at_20_max": 0.7447325753492595, "naucs_at_20_std": 0.4528568090604771, "naucs_at_20_diff1": 0.8030103604465574, "naucs_at_50_max": 0.8343240898820317, "naucs_at_50_std": 0.6770625322907705, "naucs_at_50_diff1": 0.8472448651285527, "naucs_at_100_max": 0.8102131093810145, "naucs_at_100_std": 0.7381222519798937, "naucs_at_100_diff1": 0.8742471393840519}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.96786, "ndcg_at_5": 0.96786, "ndcg_at_10": 0.96786, "ndcg_at_20": 0.96786, "ndcg_at_50": 0.96786, "ndcg_at_100": 0.96786, "map_at_1": 0.92, "map_at_3": 0.95667, "map_at_5": 0.95667, "map_at_10": 0.95667, "map_at_20": 0.95667, "map_at_50": 0.95667, "map_at_100": 0.95667, "recall_at_1": 0.92, "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": 0.92, "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": 0.94, "mrr_at_3": 0.9666666666666667, "mrr_at_5": 0.9666666666666667, "mrr_at_10": 0.9666666666666667, "mrr_at_20": 0.9666666666666667, "mrr_at_50": 0.9666666666666667, "mrr_at_100": 0.9666666666666667, "naucs_at_1_max": 0.7619047619047616, "naucs_at_1_std": 0.24060457516339795, "naucs_at_1_diff1": 0.9162581699346404, "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": 0.56786, "ndcg_at_3": 0.62806, "ndcg_at_5": 0.65635, "ndcg_at_10": 0.67295, "ndcg_at_20": 0.68721, "ndcg_at_50": 0.70267, "ndcg_at_100": 0.71485, "map_at_1": 0.56786, "map_at_3": 0.6131, "map_at_5": 0.62899, "map_at_10": 0.63542, "map_at_20": 0.63924, "map_at_50": 0.64167, "map_at_100": 0.64292, "recall_at_1": 0.56786, "recall_at_3": 0.67143, "recall_at_5": 0.73929, "recall_at_10": 0.79286, "recall_at_20": 0.85, "recall_at_50": 0.92857, "recall_at_100": 1.0, "precision_at_1": 0.56786, "precision_at_3": 0.22381, "precision_at_5": 0.14786, "precision_at_10": 0.07929, "precision_at_20": 0.0425, "precision_at_50": 0.01857, "precision_at_100": 0.01, "mrr_at_1": 0.5678571428571428, "mrr_at_3": 0.6113095238095237, "mrr_at_5": 0.6277380952380953, "mrr_at_10": 0.6339356575963718, "mrr_at_20": 0.6379618770431741, "mrr_at_50": 0.6403947405923297, "mrr_at_100": 0.6416450055922677, "naucs_at_1_max": 0.15868730409527165, "naucs_at_1_std": 0.005476384052524141, "naucs_at_1_diff1": 0.6898556504931816, "naucs_at_3_max": 0.2265285828624092, "naucs_at_3_std": 0.07120249326962727, "naucs_at_3_diff1": 0.6460005820862944, "naucs_at_5_max": 0.18104774909508717, "naucs_at_5_std": 0.049974351749500545, "naucs_at_5_diff1": 0.599728345290476, "naucs_at_10_max": 0.08937034529451629, "naucs_at_10_std": 0.021830460219087747, "naucs_at_10_diff1": 0.5156241862403002, "naucs_at_20_max": -0.015480451861837658, "naucs_at_20_std": -0.04558133048207932, "naucs_at_20_diff1": 0.5020338431500163, "naucs_at_50_max": 0.02670401493930801, "naucs_at_50_std": -0.1887955182072852, "naucs_at_50_diff1": 0.31573295985060545, "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": 0.88, "ndcg_at_3": 0.92786, "ndcg_at_5": 0.94421, "ndcg_at_10": 0.94421, "ndcg_at_20": 0.94421, "ndcg_at_50": 0.94421, "ndcg_at_100": 0.94421, "map_at_1": 0.88, "map_at_3": 0.91667, "map_at_5": 0.92567, "map_at_10": 0.92567, "map_at_20": 0.92567, "map_at_50": 0.92567, "map_at_100": 0.92567, "recall_at_1": 0.88, "recall_at_3": 0.96, "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": 0.88, "precision_at_3": 0.32, "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": 0.91, "mrr_at_3": 0.9333333333333332, "mrr_at_5": 0.9423333333333334, "mrr_at_10": 0.9423333333333334, "mrr_at_20": 0.9423333333333334, "mrr_at_50": 0.9423333333333334, "mrr_at_100": 0.9423333333333334, "naucs_at_1_max": 0.45863824371619505, "naucs_at_1_std": 0.23079064587973264, "naucs_at_1_diff1": 0.8033725739739099, "naucs_at_3_max": 0.8068394024276336, "naucs_at_3_std": 0.5087535014005626, "naucs_at_3_diff1": 0.6038748832866443, "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": 0.45, "ndcg_at_3": 0.59464, "ndcg_at_5": 0.63982, "ndcg_at_10": 0.66889, "ndcg_at_20": 0.67709, "ndcg_at_50": 0.68517, "ndcg_at_100": 0.68853, "map_at_1": 0.45, "map_at_3": 0.55833, "map_at_5": 0.58333, "map_at_10": 0.59531, "map_at_20": 0.59789, "map_at_50": 0.59924, "map_at_100": 0.59957, "recall_at_1": 0.45, "recall_at_3": 0.7, "recall_at_5": 0.81, "recall_at_10": 0.9, "recall_at_20": 0.93, "recall_at_50": 0.97, "recall_at_100": 0.99, "precision_at_1": 0.45, "precision_at_3": 0.23333, "precision_at_5": 0.162, "precision_at_10": 0.09, "precision_at_20": 0.0465, "precision_at_50": 0.0194, "precision_at_100": 0.0099, "mrr_at_1": 0.47, "mrr_at_3": 0.5833333333333334, "mrr_at_5": 0.6018333333333333, "mrr_at_10": 0.615718253968254, "mrr_at_20": 0.6165515873015873, "mrr_at_50": 0.6179859646889059, "mrr_at_100": 0.6183226650256062, "naucs_at_1_max": 0.105925489425784, "naucs_at_1_std": -0.060066784521705045, "naucs_at_1_diff1": 0.49797682184246717, "naucs_at_3_max": 0.11120518825436876, "naucs_at_3_std": -0.10580075662042858, "naucs_at_3_diff1": 0.46674473067915695, "naucs_at_5_max": 0.03777044371103874, "naucs_at_5_std": -0.21048771543820866, "naucs_at_5_diff1": 0.38344072502488297, "naucs_at_10_max": 0.09103641456582774, "naucs_at_10_std": -0.14047619047618726, "naucs_at_10_diff1": 0.32413632119514585, "naucs_at_20_max": -0.0814992663732126, "naucs_at_20_std": -0.3702147525676927, "naucs_at_20_diff1": 0.34020274776577397, "naucs_at_50_max": -0.20401493930905526, "naucs_at_50_std": -0.5308123249299683, "naucs_at_50_diff1": 0.7860255213196357, "naucs_at_100_max": -0.5634920634920583, "naucs_at_100_std": -0.5634920634920583, "naucs_at_100_diff1": 0.35807656395892007}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.95786, "ndcg_at_5": 0.96172, "ndcg_at_10": 0.96172, "ndcg_at_20": 0.96172, "ndcg_at_50": 0.96172, "ndcg_at_100": 0.96332, "map_at_1": 0.92, "map_at_3": 0.95, "map_at_5": 0.952, "map_at_10": 0.952, "map_at_20": 0.952, "map_at_50": 0.952, "map_at_100": 0.95213, "recall_at_1": 0.92, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.92, "mrr_at_3": 0.95, "mrr_at_5": 0.9525, "mrr_at_10": 0.9525, "mrr_at_20": 0.9525, "mrr_at_50": 0.9525, "mrr_at_100": 0.9526315789473684, "naucs_at_1_max": 0.749649859943977, "naucs_at_1_std": 0.25116713352007414, "naucs_at_1_diff1": 0.9279295051353874, "naucs_at_3_max": 0.8611111111111119, "naucs_at_3_std": 0.6790382819794457, "naucs_at_3_diff1": 0.7117180205415458, "naucs_at_5_max": 0.7222222222222276, "naucs_at_5_std": 0.35807656395891135, "naucs_at_5_diff1": 0.8692810457516413, "naucs_at_10_max": 0.7222222222222276, "naucs_at_10_std": 0.35807656395891135, "naucs_at_10_diff1": 0.8692810457516413, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": 0.35807656395891135, "naucs_at_20_diff1": 0.8692810457516413, "naucs_at_50_max": 0.7222222222222041, "naucs_at_50_std": 0.35807656395892007, "naucs_at_50_diff1": 0.8692810457516374, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}}
|