Update results.json
Browse files- results.json +465 -1
results.json
CHANGED
|
@@ -1 +1,465 @@
|
|
| 1 |
-
{"validation_set": {"ndcg_at_1": 0.782, "ndcg_at_3": 0.83869, "ndcg_at_5": 0.84945, "ndcg_at_10": 0.86122, "ndcg_at_20": 0.86639, "ndcg_at_100": 0.87296, "ndcg_at_1000": 0.87382, "map_at_1": 0.782, "map_at_3": 0.82567, "map_at_5": 0.83167, "map_at_10": 0.83659, "map_at_20": 0.83807, "map_at_100": 0.83894, "map_at_1000": 0.83899, "recall_at_1": 0.782, "recall_at_3": 0.876, "recall_at_5": 0.902, "recall_at_10": 0.938, "recall_at_20": 0.958, "recall_at_100": 0.994, "recall_at_1000": 1.0, "precision_at_1": 0.782, "precision_at_3": 0.292, "precision_at_5": 0.1804, "precision_at_10": 0.0938, "precision_at_20": 0.0479, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.786, "mrr_at_3": 0.8293333333333331, "mrr_at_5": 0.8353333333333332, "mrr_at_10": 0.8401857142857142, "mrr_at_20": 0.8413927173703489, "mrr_at_100": 0.842343017479603, "mrr_at_1000": 0.84237119907226, "naucs_at_1_max": 0.1287204083634169, "naucs_at_1_std": 0.04394670353021356, "naucs_at_1_diff1": 0.9147079015332307, "naucs_at_3_max": 0.15408207410154462, "naucs_at_3_std": 0.24171070115262258, "naucs_at_3_diff1": 0.8671703593832085, "naucs_at_5_max": 0.14837363516835303, "naucs_at_5_std": 0.31976600163875035, "naucs_at_5_diff1": 0.8631452581032408, "naucs_at_10_max": 0.1179633143579976, "naucs_at_10_std": 0.597316345893196, "naucs_at_10_diff1": 0.8860124695039325, "naucs_at_20_max": 0.12424969987995331, "naucs_at_20_std": 0.7891823396025082, "naucs_at_20_diff1": 0.9336401227157501, "naucs_at_100_max": -0.17133520074699127, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.91917, "ndcg_at_5": 0.92347, "ndcg_at_10": 0.92937, "ndcg_at_20": 0.92937, "ndcg_at_100": 0.93128, "ndcg_at_1000": 0.93277, "map_at_1": 0.87, "map_at_3": 0.90833, "map_at_5": 0.91083, "map_at_10": 0.91294, "map_at_20": 0.91294, "map_at_100": 0.91321, "map_at_1000": 0.91331, "recall_at_1": 0.87, "recall_at_3": 0.95, "recall_at_5": 0.96, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.31667, "precision_at_5": 0.192, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.88, "mrr_at_3": 0.9133333333333333, "mrr_at_5": 0.9158333333333333, "mrr_at_10": 0.9183730158730158, "mrr_at_20": 0.9183730158730158, "mrr_at_100": 0.9187453269596126, "mrr_at_1000": 0.9187453269596126, "naucs_at_1_max": 0.24364955935718074, "naucs_at_1_std": -0.12800859068355205, "naucs_at_1_diff1": 0.9218692142486855, "naucs_at_3_max": 0.21577964519141157, "naucs_at_3_std": -0.2550887021475216, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": 0.05240429505135564, "naucs_at_5_std": -0.5361811391223089, "naucs_at_5_diff1": 0.9346405228758139, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": 0.07936507936508234, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.7957516339869297, "naucs_at_20_std": 0.07936507936508234, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": 0.8692810457516374, "naucs_at_100_std": 0.7222222222222041, "naucs_at_100_diff1": 0.8692810457516374, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.94893, "ndcg_at_5": 0.94893, "ndcg_at_10": 0.94893, "ndcg_at_20": 0.95163, "ndcg_at_100": 0.95554, "ndcg_at_1000": 0.95554, "map_at_1": 0.92, "map_at_3": 0.94167, "map_at_5": 0.94167, "map_at_10": 0.94167, "map_at_20": 0.9425, "map_at_100": 0.94313, "map_at_1000": 0.94313, "recall_at_1": 0.92, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.9416666666666665, "mrr_at_5": 0.9416666666666665, "mrr_at_10": 0.9426666666666665, "mrr_at_20": 0.9426666666666665, "mrr_at_100": 0.9433152709359603, "mrr_at_1000": 0.9433152709359603, "naucs_at_1_max": 0.129493464052287, "naucs_at_1_std": -0.1989379084967342, "naucs_at_1_diff1": 0.8468137254901948, "naucs_at_3_max": -0.00964830376594965, "naucs_at_3_std": -0.7268907563025196, "naucs_at_3_diff1": 0.8638344226579548, "naucs_at_5_max": -0.009648303765951795, "naucs_at_5_std": -0.7268907563025226, "naucs_at_5_diff1": 0.8638344226579531, "naucs_at_10_max": -0.009648303765951795, "naucs_at_10_std": -0.7268907563025226, "naucs_at_10_diff1": 0.8638344226579531, "naucs_at_20_max": -0.5144724556489195, "naucs_at_20_std": -1.1517273576097127, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.97393, "ndcg_at_5": 0.97393, "ndcg_at_10": 0.97393, "ndcg_at_20": 0.97393, "ndcg_at_100": 0.97581, "ndcg_at_1000": 0.97581, "map_at_1": 0.95, "map_at_3": 0.96833, "map_at_5": 0.96833, "map_at_10": 0.96833, "map_at_20": 0.96833, "map_at_100": 0.96859, "map_at_1000": 0.96859, "recall_at_1": 0.95, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.95, "mrr_at_3": 0.9683333333333334, "mrr_at_5": 0.9683333333333334, "mrr_at_10": 0.9683333333333334, "mrr_at_20": 0.9683333333333334, "mrr_at_100": 0.9686111111111111, "mrr_at_1000": 0.9686111111111111, "naucs_at_1_max": -0.2407096171802055, "naucs_at_1_std": -0.8749766573295958, "naucs_at_1_diff1": 0.8846872082166202, "naucs_at_3_max": -1.7399626517274398, "naucs_at_3_std": -1.7399626517274398, "naucs_at_3_diff1": 0.5541549953314585, "naucs_at_5_max": -1.7399626517273863, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.5541549953314738, "naucs_at_10_max": -1.7399626517273863, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.5541549953314738, "naucs_at_20_max": -1.7399626517273863, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 0.5541549953314738, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.86, "ndcg_at_3": 0.91286, "ndcg_at_5": 0.92147, "ndcg_at_10": 0.92448, "ndcg_at_20": 0.92727, "ndcg_at_100": 0.92929, "ndcg_at_1000": 0.92929, "map_at_1": 0.86, "map_at_3": 0.9, "map_at_5": 0.905, "map_at_10": 0.90611, "map_at_20": 0.90702, "map_at_100": 0.90735, "map_at_1000": 0.90735, "recall_at_1": 0.86, "recall_at_3": 0.95, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.86, "precision_at_3": 0.31667, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.9, "mrr_at_5": 0.905, "mrr_at_10": 0.90625, "mrr_at_20": 0.907159090909091, "mrr_at_100": 0.9075039184952978, "mrr_at_1000": 0.9075039184952978, "naucs_at_1_max": 0.43501454898157155, "naucs_at_1_std": 0.2136275460717749, "naucs_at_1_diff1": 0.9035263960094214, "naucs_at_3_max": 0.6491129785247453, "naucs_at_3_std": 0.4804855275443501, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 0.9128540305010848, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 0.8692810457516413, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.732, "ndcg_at_3": 0.79395, "ndcg_at_5": 0.81366, "ndcg_at_10": 0.82475, "ndcg_at_20": 0.82906, "ndcg_at_100": 0.83691, "ndcg_at_1000": 0.83975, "map_at_1": 0.732, "map_at_3": 0.77933, "map_at_5": 0.79023, "map_at_10": 0.79487, "map_at_20": 0.79593, "map_at_100": 0.79706, "map_at_1000": 0.79717, "recall_at_1": 0.732, "recall_at_3": 0.836, "recall_at_5": 0.884, "recall_at_10": 0.918, "recall_at_20": 0.936, "recall_at_100": 0.978, "recall_at_1000": 1.0, "precision_at_1": 0.732, "precision_at_3": 0.27867, "precision_at_5": 0.1768, "precision_at_10": 0.0918, "precision_at_20": 0.0468, "precision_at_100": 0.00978, "precision_at_1000": 0.001, "mrr_at_1": 0.732, "mrr_at_3": 0.7786666666666665, "mrr_at_5": 0.7900666666666664, "mrr_at_10": 0.794449206349206, "mrr_at_20": 0.7953232247284874, "mrr_at_100": 0.7966255910510839, "mrr_at_1000": 0.7967190443508116, "naucs_at_1_max": 0.4347700535605503, "naucs_at_1_std": 0.0052057373871626685, "naucs_at_1_diff1": 0.865643715535724, "naucs_at_3_max": 0.6048031004775511, "naucs_at_3_std": 0.15614576084087275, "naucs_at_3_diff1": 0.8398166590674573, "naucs_at_5_max": 0.5930604282107613, "naucs_at_5_std": 0.1861700383619125, "naucs_at_5_diff1": 0.7956080527230405, "naucs_at_10_max": 0.6479242103345397, "naucs_at_10_std": 0.25604062763316404, "naucs_at_10_diff1": 0.7970326341918881, "naucs_at_20_max": 0.6982668067226916, "naucs_at_20_std": 0.40970763305321833, "naucs_at_20_diff1": 0.7613941409897302, "naucs_at_100_max": 0.9762329174093898, "naucs_at_100_std": 0.8936847466259251, "naucs_at_100_diff1": 0.80561921738392, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.458, "ndcg_at_3": 0.5249, "ndcg_at_5": 0.54987, "ndcg_at_10": 0.5691, "ndcg_at_20": 0.58534, "ndcg_at_100": 0.60898, "ndcg_at_1000": 0.62315, "map_at_1": 0.458, "map_at_3": 0.508, "map_at_5": 0.522, "map_at_10": 0.52983, "map_at_20": 0.53432, "map_at_100": 0.53744, "map_at_1000": 0.53795, "recall_at_1": 0.458, "recall_at_3": 0.574, "recall_at_5": 0.634, "recall_at_10": 0.694, "recall_at_20": 0.758, "recall_at_100": 0.888, "recall_at_1000": 1.0, "precision_at_1": 0.458, "precision_at_3": 0.19133, "precision_at_5": 0.1268, "precision_at_10": 0.0694, "precision_at_20": 0.0379, "precision_at_100": 0.00888, "precision_at_1000": 0.001, "mrr_at_1": 0.462, "mrr_at_3": 0.5103333333333334, "mrr_at_5": 0.5240333333333334, "mrr_at_10": 0.5330150793650792, "mrr_at_20": 0.5363530102594342, "mrr_at_100": 0.5398099695126392, "mrr_at_1000": 0.540360971784682, "naucs_at_1_max": 0.14478705160292352, "naucs_at_1_std": 0.3721140942241178, "naucs_at_1_diff1": 0.8556357724943732, "naucs_at_3_max": 0.0955052454658937, "naucs_at_3_std": 0.4342882512519065, "naucs_at_3_diff1": 0.7991501163256658, "naucs_at_5_max": 0.01343769437454414, "naucs_at_5_std": 0.48670912254002735, "naucs_at_5_diff1": 0.7732231206645599, "naucs_at_10_max": -0.024673527538943748, "naucs_at_10_std": 0.5356353895792051, "naucs_at_10_diff1": 0.7689667071014644, "naucs_at_20_max": -0.12562798953100113, "naucs_at_20_std": 0.5620597626854955, "naucs_at_20_diff1": 0.7722820785003025, "naucs_at_100_max": -0.23859408820346314, "naucs_at_100_std": 0.864870806277056, "naucs_at_100_diff1": 0.7339945211038957, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.712, "ndcg_at_3": 0.76712, "ndcg_at_5": 0.78364, "ndcg_at_10": 0.80123, "ndcg_at_20": 0.812, "ndcg_at_100": 0.81995, "ndcg_at_1000": 0.82209, "map_at_1": 0.712, "map_at_3": 0.75367, "map_at_5": 0.76287, "map_at_10": 0.77019, "map_at_20": 0.77323, "map_at_100": 0.7744, "map_at_1000": 0.77449, "recall_at_1": 0.712, "recall_at_3": 0.806, "recall_at_5": 0.846, "recall_at_10": 0.9, "recall_at_20": 0.942, "recall_at_100": 0.984, "recall_at_1000": 1.0, "precision_at_1": 0.712, "precision_at_3": 0.26867, "precision_at_5": 0.1692, "precision_at_10": 0.09, "precision_at_20": 0.0471, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.724, "mrr_at_3": 0.7626666666666667, "mrr_at_5": 0.7716666666666666, "mrr_at_10": 0.7785738095238096, "mrr_at_20": 0.7814459001782531, "mrr_at_100": 0.7824821791237915, "mrr_at_1000": 0.7825927236311448, "naucs_at_1_max": 0.5179261037469994, "naucs_at_1_std": 0.0715515827456125, "naucs_at_1_diff1": 0.8994028359700004, "naucs_at_3_max": 0.5866330274286543, "naucs_at_3_std": 0.15098605444623744, "naucs_at_3_diff1": 0.8370723586175715, "naucs_at_5_max": 0.6037655521242381, "naucs_at_5_std": 0.16178021782505292, "naucs_at_5_diff1": 0.8241259674406191, "naucs_at_10_max": 0.5842483660130722, "naucs_at_10_std": 0.20487394957983113, "naucs_at_10_diff1": 0.7742016806722692, "naucs_at_20_max": 0.735455101580865, "naucs_at_20_std": 0.3710035738433312, "naucs_at_20_diff1": 0.7694871051869058, "naucs_at_100_max": 0.8503151260504297, "naucs_at_100_std": 0.5717787114846009, "naucs_at_100_diff1": 0.8129668534080331, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.76429, "ndcg_at_3": 0.83078, "ndcg_at_5": 0.84353, "ndcg_at_10": 0.85388, "ndcg_at_20": 0.86455, "ndcg_at_100": 0.86741, "ndcg_at_1000": 0.86741, "map_at_1": 0.76429, "map_at_3": 0.81429, "map_at_5": 0.82107, "map_at_10": 0.82532, "map_at_20": 0.82817, "map_at_100": 0.82864, "map_at_1000": 0.82864, "recall_at_1": 0.76429, "recall_at_3": 0.87857, "recall_at_5": 0.91071, "recall_at_10": 0.94286, "recall_at_20": 0.98571, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.76429, "precision_at_3": 0.29286, "precision_at_5": 0.18214, "precision_at_10": 0.09429, "precision_at_20": 0.04929, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.7571428571428571, "mrr_at_3": 0.8095238095238096, "mrr_at_5": 0.8179166666666666, "mrr_at_10": 0.8214625850340135, "mrr_at_20": 0.8241040305215449, "mrr_at_100": 0.8247231380884232, "mrr_at_1000": 0.8247231380884232, "naucs_at_1_max": 0.4032387013842082, "naucs_at_1_std": 0.20721575143829152, "naucs_at_1_diff1": 0.8371243592356286, "naucs_at_3_max": 0.37018609096531074, "naucs_at_3_std": 0.19961207623545132, "naucs_at_3_diff1": 0.7850677461067068, "naucs_at_5_max": 0.49086834733893503, "naucs_at_5_std": 0.26750700280112155, "naucs_at_5_diff1": 0.7712791783380023, "naucs_at_10_max": 0.5342845471521948, "naucs_at_10_std": 0.382148692810459, "naucs_at_10_diff1": 0.7389122315592906, "naucs_at_20_max": 0.42938842203549277, "naucs_at_20_std": 0.5764472455649069, "naucs_at_20_diff1": 0.8978758169934754, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.51714, "ndcg_at_3": 0.63347, "ndcg_at_5": 0.65997, "ndcg_at_10": 0.68432, "ndcg_at_20": 0.69776, "ndcg_at_100": 0.71265, "ndcg_at_1000": 0.7148, "map_at_1": 0.51714, "map_at_3": 0.60543, "map_at_5": 0.62013, "map_at_10": 0.63032, "map_at_20": 0.63413, "map_at_100": 0.63629, "map_at_1000": 0.63639, "recall_at_1": 0.51714, "recall_at_3": 0.71437, "recall_at_5": 0.77871, "recall_at_10": 0.85328, "recall_at_20": 0.90559, "recall_at_100": 0.98437, "recall_at_1000": 1.0, "precision_at_1": 0.51714, "precision_at_3": 0.23812, "precision_at_5": 0.15574, "precision_at_10": 0.08533, "precision_at_20": 0.04528, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.5189416716776909, "mrr_at_3": 0.6063339346562444, "mrr_at_5": 0.6203447584686321, "mrr_at_10": 0.6304701295230465, "mrr_at_20": 0.6343502614596628, "mrr_at_100": 0.6366034259317307, "mrr_at_1000": 0.6366958159270893, "naucs_at_1_max": 0.16652309459558007, "naucs_at_1_std": -0.06670433006927416, "naucs_at_1_diff1": 0.6953792910740597, "naucs_at_3_max": 0.16902492509679246, "naucs_at_3_std": -0.03701362337519723, "naucs_at_3_diff1": 0.5494053126321319, "naucs_at_5_max": 0.21105315084874532, "naucs_at_5_std": 0.04611791703673267, "naucs_at_5_diff1": 0.5162174552139975, "naucs_at_10_max": 0.23091913809374726, "naucs_at_10_std": 0.10830125135311366, "naucs_at_10_diff1": 0.4866871626269709, "naucs_at_20_max": 0.2725948129883982, "naucs_at_20_std": 0.24954038307560938, "naucs_at_20_diff1": 0.4588931923467883, "naucs_at_100_max": 0.6502319824989845, "naucs_at_100_std": 0.6011619544721175, "naucs_at_100_diff1": 0.7480994634253559, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.56, "ndcg_at_3": 0.70095, "ndcg_at_5": 0.72934, "ndcg_at_10": 0.74318, "ndcg_at_20": 0.7537, "ndcg_at_100": 0.75912, "ndcg_at_1000": 0.76194, "map_at_1": 0.56, "map_at_3": 0.66667, "map_at_5": 0.68217, "map_at_10": 0.68842, "map_at_20": 0.69152, "map_at_100": 0.69222, "map_at_1000": 0.69237, "recall_at_1": 0.56, "recall_at_3": 0.8, "recall_at_5": 0.87, "recall_at_10": 0.91, "recall_at_20": 0.95, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.56, "precision_at_3": 0.26667, "precision_at_5": 0.174, "precision_at_10": 0.091, "precision_at_20": 0.0475, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.59, "mrr_at_3": 0.69, "mrr_at_5": 0.7055, "mrr_at_10": 0.7100833333333334, "mrr_at_20": 0.7131832236391059, "mrr_at_100": 0.7139141492175927, "mrr_at_1000": 0.7140687525760177, "naucs_at_1_max": -0.06823472632296203, "naucs_at_1_std": -0.21851578469225566, "naucs_at_1_diff1": 0.6402168975698381, "naucs_at_3_max": -0.5083416583416578, "naucs_at_3_std": -0.719330669330669, "naucs_at_3_diff1": 0.49285714285714205, "naucs_at_5_max": -0.40505813522920514, "naucs_at_5_std": -0.5592460934607096, "naucs_at_5_diff1": 0.3987632377990074, "naucs_at_10_max": -0.4162776221599734, "naucs_at_10_std": -0.47852474323062383, "naucs_at_10_diff1": 0.4046062869592272, "naucs_at_20_max": -0.5808590102707625, "naucs_at_20_std": -0.5164332399626398, "naucs_at_20_diff1": 0.4697478991596656, "naucs_at_100_max": -1.4458450046685247, "naucs_at_100_std": -1.4458450046685247, "naucs_at_100_diff1": 0.6790382819794637, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.44872, "ndcg_at_3": 0.45583, "ndcg_at_5": 0.46482, "ndcg_at_10": 0.49929, "ndcg_at_20": 0.53319, "ndcg_at_50": 0.56088, "ndcg_at_100": 0.57521, "map_at_1": 0.31282, "map_at_3": 0.38643, "map_at_5": 0.40662, "map_at_10": 0.427, "map_at_20": 0.44037, "map_at_50": 0.44779, "map_at_100": 0.45087, "recall_at_1": 0.31282, "recall_at_3": 0.45801, "recall_at_5": 0.51314, "recall_at_10": 0.59474, "recall_at_20": 0.70006, "recall_at_50": 0.81018, "recall_at_100": 0.8687, "precision_at_1": 0.46154, "precision_at_3": 0.25, "precision_at_5": 0.17692, "precision_at_10": 0.11538, "precision_at_20": 0.07212, "precision_at_50": 0.03577, "precision_at_100": 0.02019, "mrr_at_1": 0.46153846153846156, "mrr_at_3": 0.5352564102564102, "mrr_at_5": 0.5400641025641025, "mrr_at_10": 0.5563568376068376, "mrr_at_20": 0.5619123931623933, "mrr_at_50": 0.5636433095866326, "mrr_at_100": 0.5639692548278321, "naucs_at_1_max": -0.041251407771801335, "naucs_at_1_std": -0.13440738438251756, "naucs_at_1_diff1": 0.34187346444583533, "naucs_at_3_max": 0.0490709257221608, "naucs_at_3_std": 0.08564793906924244, "naucs_at_3_diff1": 0.22646725274417273, "naucs_at_5_max": -0.03672914700583298, "naucs_at_5_std": 0.007447202410573791, "naucs_at_5_diff1": 0.042815771441324466, "naucs_at_10_max": 0.08103519471354535, "naucs_at_10_std": 0.19402598514845554, "naucs_at_10_diff1": -0.0033559370819179145, "naucs_at_20_max": 0.0456379886246012, "naucs_at_20_std": 0.1498156050133747, "naucs_at_20_diff1": -0.08008666562091712, "naucs_at_50_max": -0.08067464433322966, "naucs_at_50_std": 0.09130916830990066, "naucs_at_50_diff1": -0.15272607839988653, "naucs_at_100_max": -0.096748886881875, "naucs_at_100_std": 0.07721280649171645, "naucs_at_100_diff1": -0.18731989904451377},
|
| 2 |
+
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
|
| 3 |
+
"ndcg_at_1": 0.46121,
|
| 4 |
+
"ndcg_at_3": 0.44678,
|
| 5 |
+
"ndcg_at_5": 0.43801,
|
| 6 |
+
"ndcg_at_10": 0.43733,
|
| 7 |
+
"ndcg_at_20": 0.46433,
|
| 8 |
+
"ndcg_at_50": 0.54611,
|
| 9 |
+
"ndcg_at_100": 0.59004,
|
| 10 |
+
"map_at_1": 0.04211,
|
| 11 |
+
"map_at_3": 0.11076,
|
| 12 |
+
"map_at_5": 0.14977,
|
| 13 |
+
"map_at_10": 0.20422,
|
| 14 |
+
"map_at_20": 0.25084,
|
| 15 |
+
"map_at_50": 0.30884,
|
| 16 |
+
"map_at_100": 0.33619,
|
| 17 |
+
"recall_at_1": 0.04211,
|
| 18 |
+
"recall_at_3": 0.14649,
|
| 19 |
+
"recall_at_5": 0.23071,
|
| 20 |
+
"recall_at_10": 0.35624,
|
| 21 |
+
"recall_at_20": 0.49418,
|
| 22 |
+
"recall_at_50": 0.73377,
|
| 23 |
+
"recall_at_100": 0.86682,
|
| 24 |
+
"precision_at_1": 0.46121,
|
| 25 |
+
"precision_at_3": 0.43103,
|
| 26 |
+
"precision_at_5": 0.40172,
|
| 27 |
+
"precision_at_10": 0.34138,
|
| 28 |
+
"precision_at_20": 0.26659,
|
| 29 |
+
"precision_at_50": 0.18138,
|
| 30 |
+
"precision_at_100": 0.12047,
|
| 31 |
+
"mrr_at_1": 0.46551724137931033,
|
| 32 |
+
"mrr_at_3": 0.574712643678161,
|
| 33 |
+
"mrr_at_5": 0.6042385057471265,
|
| 34 |
+
"mrr_at_10": 0.6164939107827039,
|
| 35 |
+
"mrr_at_20": 0.6183285285117182,
|
| 36 |
+
"mrr_at_50": 0.6200764537159825,
|
| 37 |
+
"mrr_at_100": 0.6200764537159825,
|
| 38 |
+
"naucs_at_1_max": 0.11544462366696459,
|
| 39 |
+
"naucs_at_1_std": 0.22176658057960205,
|
| 40 |
+
"naucs_at_1_diff1": 0.025762330855377692,
|
| 41 |
+
"naucs_at_3_max": 0.026780292524540915,
|
| 42 |
+
"naucs_at_3_std": 0.11948865529860946,
|
| 43 |
+
"naucs_at_3_diff1": 0.061454401010208035,
|
| 44 |
+
"naucs_at_5_max": 0.03371203358255765,
|
| 45 |
+
"naucs_at_5_std": 0.09636809061801069,
|
| 46 |
+
"naucs_at_5_diff1": 0.05757750385636382,
|
| 47 |
+
"naucs_at_10_max": 0.09232655846367765,
|
| 48 |
+
"naucs_at_10_std": 0.12953593426424662,
|
| 49 |
+
"naucs_at_10_diff1": 0.040531120842163905,
|
| 50 |
+
"naucs_at_20_max": 0.05932447597915658,
|
| 51 |
+
"naucs_at_20_std": 0.12194225080385523,
|
| 52 |
+
"naucs_at_20_diff1": 0.056576190947956906,
|
| 53 |
+
"naucs_at_50_max": -0.0032140618165206,
|
| 54 |
+
"naucs_at_50_std": 0.0871134378372482,
|
| 55 |
+
"naucs_at_50_diff1": 0.07003126914242656,
|
| 56 |
+
"naucs_at_100_max": -0.06221058793886302,
|
| 57 |
+
"naucs_at_100_std": 0.045883933099133634,
|
| 58 |
+
"naucs_at_100_diff1": 0.060445445102082516
|
| 59 |
+
},
|
| 60 |
+
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
| 61 |
+
"ndcg_at_1": 0.43056,
|
| 62 |
+
"ndcg_at_3": 0.49932,
|
| 63 |
+
"ndcg_at_5": 0.48405,
|
| 64 |
+
"ndcg_at_10": 0.52572,
|
| 65 |
+
"ndcg_at_20": 0.55276,
|
| 66 |
+
"ndcg_at_50": 0.60698,
|
| 67 |
+
"ndcg_at_100": 0.63664,
|
| 68 |
+
"map_at_1": 0.21657,
|
| 69 |
+
"map_at_3": 0.34458,
|
| 70 |
+
"map_at_5": 0.37077,
|
| 71 |
+
"map_at_10": 0.41524,
|
| 72 |
+
"map_at_20": 0.43457,
|
| 73 |
+
"map_at_50": 0.45648,
|
| 74 |
+
"map_at_100": 0.46422,
|
| 75 |
+
"recall_at_1": 0.21657,
|
| 76 |
+
"recall_at_3": 0.42428,
|
| 77 |
+
"recall_at_5": 0.47428,
|
| 78 |
+
"recall_at_10": 0.62959,
|
| 79 |
+
"recall_at_20": 0.70556,
|
| 80 |
+
"recall_at_50": 0.84926,
|
| 81 |
+
"recall_at_100": 0.95773,
|
| 82 |
+
"precision_at_1": 0.43056,
|
| 83 |
+
"precision_at_3": 0.35185,
|
| 84 |
+
"precision_at_5": 0.26389,
|
| 85 |
+
"precision_at_10": 0.19722,
|
| 86 |
+
"precision_at_20": 0.12569,
|
| 87 |
+
"precision_at_50": 0.07361,
|
| 88 |
+
"precision_at_100": 0.04333,
|
| 89 |
+
"mrr_at_1": 0.4166666666666667,
|
| 90 |
+
"mrr_at_3": 0.5532407407407408,
|
| 91 |
+
"mrr_at_5": 0.5712962962962963,
|
| 92 |
+
"mrr_at_10": 0.5773533950617283,
|
| 93 |
+
"mrr_at_20": 0.5814130892255892,
|
| 94 |
+
"mrr_at_50": 0.5838168891293891,
|
| 95 |
+
"mrr_at_100": 0.5844176970242605,
|
| 96 |
+
"naucs_at_1_max": -0.014383321441278112,
|
| 97 |
+
"naucs_at_1_std": 0.010022808571214561,
|
| 98 |
+
"naucs_at_1_diff1": 0.16262213048124577,
|
| 99 |
+
"naucs_at_3_max": -0.14129169116985835,
|
| 100 |
+
"naucs_at_3_std": -0.12262775724308239,
|
| 101 |
+
"naucs_at_3_diff1": 0.05572121475836582,
|
| 102 |
+
"naucs_at_5_max": -0.2028179459941851,
|
| 103 |
+
"naucs_at_5_std": -0.19014286776522518,
|
| 104 |
+
"naucs_at_5_diff1": -0.03939136391492235,
|
| 105 |
+
"naucs_at_10_max": -0.2776293653133337,
|
| 106 |
+
"naucs_at_10_std": -0.07795973417623336,
|
| 107 |
+
"naucs_at_10_diff1": -0.11387806735285985,
|
| 108 |
+
"naucs_at_20_max": -0.3526757050657489,
|
| 109 |
+
"naucs_at_20_std": -0.148976855330587,
|
| 110 |
+
"naucs_at_20_diff1": -0.16249219953551627,
|
| 111 |
+
"naucs_at_50_max": -0.45275662271581857,
|
| 112 |
+
"naucs_at_50_std": -0.2226644502919943,
|
| 113 |
+
"naucs_at_50_diff1": -0.27123799331086546,
|
| 114 |
+
"naucs_at_100_max": -0.4908484200717289,
|
| 115 |
+
"naucs_at_100_std": -0.27215698272245575,
|
| 116 |
+
"naucs_at_100_diff1": -0.3197175808368999
|
| 117 |
+
},
|
| 118 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
|
| 119 |
+
"ndcg_at_1": 0.49375,
|
| 120 |
+
"ndcg_at_3": 0.55246,
|
| 121 |
+
"ndcg_at_5": 0.56401,
|
| 122 |
+
"ndcg_at_10": 0.59824,
|
| 123 |
+
"ndcg_at_20": 0.62263,
|
| 124 |
+
"ndcg_at_50": 0.64864,
|
| 125 |
+
"ndcg_at_100": 0.66058,
|
| 126 |
+
"map_at_1": 0.2925,
|
| 127 |
+
"map_at_3": 0.43514,
|
| 128 |
+
"map_at_5": 0.46557,
|
| 129 |
+
"map_at_10": 0.49886,
|
| 130 |
+
"map_at_20": 0.51211,
|
| 131 |
+
"map_at_50": 0.52151,
|
| 132 |
+
"map_at_100": 0.52438,
|
| 133 |
+
"recall_at_1": 0.2925,
|
| 134 |
+
"recall_at_3": 0.53945,
|
| 135 |
+
"recall_at_5": 0.6104,
|
| 136 |
+
"recall_at_10": 0.70946,
|
| 137 |
+
"recall_at_20": 0.7779,
|
| 138 |
+
"recall_at_50": 0.85907,
|
| 139 |
+
"recall_at_100": 0.90203,
|
| 140 |
+
"precision_at_1": 0.49375,
|
| 141 |
+
"precision_at_3": 0.35625,
|
| 142 |
+
"precision_at_5": 0.25875,
|
| 143 |
+
"precision_at_10": 0.1675,
|
| 144 |
+
"precision_at_20": 0.09969,
|
| 145 |
+
"precision_at_50": 0.04825,
|
| 146 |
+
"precision_at_100": 0.02656,
|
| 147 |
+
"mrr_at_1": 0.49375,
|
| 148 |
+
"mrr_at_3": 0.6302083333333333,
|
| 149 |
+
"mrr_at_5": 0.6464583333333334,
|
| 150 |
+
"mrr_at_10": 0.6537053571428572,
|
| 151 |
+
"mrr_at_20": 0.6556828526865291,
|
| 152 |
+
"mrr_at_50": 0.6562852746898132,
|
| 153 |
+
"mrr_at_100": 0.6565007919311926,
|
| 154 |
+
"naucs_at_1_max": 0.25020981693991323,
|
| 155 |
+
"naucs_at_1_std": 0.032523703082023604,
|
| 156 |
+
"naucs_at_1_diff1": 0.44486177010711037,
|
| 157 |
+
"naucs_at_3_max": 0.048297692258767976,
|
| 158 |
+
"naucs_at_3_std": -0.07236336772684801,
|
| 159 |
+
"naucs_at_3_diff1": 0.09676661823198773,
|
| 160 |
+
"naucs_at_5_max": -0.06773618538324375,
|
| 161 |
+
"naucs_at_5_std": -0.14039062350257736,
|
| 162 |
+
"naucs_at_5_diff1": 0.03386425929120516,
|
| 163 |
+
"naucs_at_10_max": -0.13344403724710174,
|
| 164 |
+
"naucs_at_10_std": -0.14472428952006045,
|
| 165 |
+
"naucs_at_10_diff1": -0.08197496515301053,
|
| 166 |
+
"naucs_at_20_max": -0.19347832736838858,
|
| 167 |
+
"naucs_at_20_std": -0.18669183742139606,
|
| 168 |
+
"naucs_at_20_diff1": -0.13648142564357998,
|
| 169 |
+
"naucs_at_50_max": -0.2592522621386659,
|
| 170 |
+
"naucs_at_50_std": -0.2065593807292728,
|
| 171 |
+
"naucs_at_50_diff1": -0.1772156473626456,
|
| 172 |
+
"naucs_at_100_max": -0.27974871039818505,
|
| 173 |
+
"naucs_at_100_std": -0.2129965871516818,
|
| 174 |
+
"naucs_at_100_diff1": -0.20025636973950994
|
| 175 |
+
},
|
| 176 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
|
| 177 |
+
"ndcg_at_1": 0.40351,
|
| 178 |
+
"ndcg_at_3": 0.43353,
|
| 179 |
+
"ndcg_at_5": 0.46071,
|
| 180 |
+
"ndcg_at_10": 0.50098,
|
| 181 |
+
"ndcg_at_20": 0.54228,
|
| 182 |
+
"ndcg_at_50": 0.59505,
|
| 183 |
+
"ndcg_at_100": 0.60794,
|
| 184 |
+
"map_at_1": 0.20443,
|
| 185 |
+
"map_at_3": 0.31443,
|
| 186 |
+
"map_at_5": 0.35309,
|
| 187 |
+
"map_at_10": 0.3892,
|
| 188 |
+
"map_at_20": 0.41348,
|
| 189 |
+
"map_at_50": 0.43382,
|
| 190 |
+
"map_at_100": 0.43953,
|
| 191 |
+
"recall_at_1": 0.20443,
|
| 192 |
+
"recall_at_3": 0.39252,
|
| 193 |
+
"recall_at_5": 0.49607,
|
| 194 |
+
"recall_at_10": 0.61245,
|
| 195 |
+
"recall_at_20": 0.74221,
|
| 196 |
+
"recall_at_50": 0.91648,
|
| 197 |
+
"recall_at_100": 0.95209,
|
| 198 |
+
"precision_at_1": 0.40351,
|
| 199 |
+
"precision_at_3": 0.29825,
|
| 200 |
+
"precision_at_5": 0.23509,
|
| 201 |
+
"precision_at_10": 0.16667,
|
| 202 |
+
"precision_at_20": 0.1114,
|
| 203 |
+
"precision_at_50": 0.06491,
|
| 204 |
+
"precision_at_100": 0.03702,
|
| 205 |
+
"mrr_at_1": 0.42105263157894735,
|
| 206 |
+
"mrr_at_3": 0.5321637426900585,
|
| 207 |
+
"mrr_at_5": 0.5488304093567252,
|
| 208 |
+
"mrr_at_10": 0.5584029518240045,
|
| 209 |
+
"mrr_at_20": 0.5650255023523721,
|
| 210 |
+
"mrr_at_50": 0.5672874814106899,
|
| 211 |
+
"mrr_at_100": 0.5672874814106899,
|
| 212 |
+
"naucs_at_1_max": -0.0073958870644794655,
|
| 213 |
+
"naucs_at_1_std": 0.22311242186928293,
|
| 214 |
+
"naucs_at_1_diff1": 0.10748815653422916,
|
| 215 |
+
"naucs_at_3_max": -0.049083912454293395,
|
| 216 |
+
"naucs_at_3_std": 0.04039313351636922,
|
| 217 |
+
"naucs_at_3_diff1": 9.121647046468586e-6,
|
| 218 |
+
"naucs_at_5_max": -0.001472450245480797,
|
| 219 |
+
"naucs_at_5_std": 0.014701791353186453,
|
| 220 |
+
"naucs_at_5_diff1": -0.04924564749255387,
|
| 221 |
+
"naucs_at_10_max": -0.1960183643332104,
|
| 222 |
+
"naucs_at_10_std": -0.0751493709821589,
|
| 223 |
+
"naucs_at_10_diff1": -0.030450079021949194,
|
| 224 |
+
"naucs_at_20_max": -0.23585667739901595,
|
| 225 |
+
"naucs_at_20_std": -0.09380275141988259,
|
| 226 |
+
"naucs_at_20_diff1": 0.004796937988805973,
|
| 227 |
+
"naucs_at_50_max": -0.3740708956154588,
|
| 228 |
+
"naucs_at_50_std": -0.12647666604177382,
|
| 229 |
+
"naucs_at_50_diff1": 0.18883751281413164,
|
| 230 |
+
"naucs_at_100_max": -0.39872734925448805,
|
| 231 |
+
"naucs_at_100_std": -0.12133973144894185,
|
| 232 |
+
"naucs_at_100_diff1": 0.18715558055343207
|
| 233 |
+
},
|
| 234 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
|
| 235 |
+
"ndcg_at_1": 0.44298,
|
| 236 |
+
"ndcg_at_3": 0.45536,
|
| 237 |
+
"ndcg_at_5": 0.48065,
|
| 238 |
+
"ndcg_at_10": 0.52054,
|
| 239 |
+
"ndcg_at_20": 0.56428,
|
| 240 |
+
"ndcg_at_50": 0.60862,
|
| 241 |
+
"ndcg_at_100": 0.62233,
|
| 242 |
+
"map_at_1": 0.21064,
|
| 243 |
+
"map_at_3": 0.33068,
|
| 244 |
+
"map_at_5": 0.36713,
|
| 245 |
+
"map_at_10": 0.40403,
|
| 246 |
+
"map_at_20": 0.43049,
|
| 247 |
+
"map_at_50": 0.44959,
|
| 248 |
+
"map_at_100": 0.45475,
|
| 249 |
+
"recall_at_1": 0.21064,
|
| 250 |
+
"recall_at_3": 0.41209,
|
| 251 |
+
"recall_at_5": 0.50701,
|
| 252 |
+
"recall_at_10": 0.63557,
|
| 253 |
+
"recall_at_20": 0.77159,
|
| 254 |
+
"recall_at_50": 0.91455,
|
| 255 |
+
"recall_at_100": 0.95882,
|
| 256 |
+
"precision_at_1": 0.44298,
|
| 257 |
+
"precision_at_3": 0.32018,
|
| 258 |
+
"precision_at_5": 0.25263,
|
| 259 |
+
"precision_at_10": 0.17456,
|
| 260 |
+
"precision_at_20": 0.11732,
|
| 261 |
+
"precision_at_50": 0.06509,
|
| 262 |
+
"precision_at_100": 0.0368,
|
| 263 |
+
"mrr_at_1": 0.44298245614035087,
|
| 264 |
+
"mrr_at_3": 0.5511695906432749,
|
| 265 |
+
"mrr_at_5": 0.5632309941520467,
|
| 266 |
+
"mrr_at_10": 0.5748555416318574,
|
| 267 |
+
"mrr_at_20": 0.5813267293316584,
|
| 268 |
+
"mrr_at_50": 0.5829786723780774,
|
| 269 |
+
"mrr_at_100": 0.5831139537633588,
|
| 270 |
+
"naucs_at_1_max": 0.07051482047264329,
|
| 271 |
+
"naucs_at_1_std": 0.1958271006282557,
|
| 272 |
+
"naucs_at_1_diff1": 0.1942661226272023,
|
| 273 |
+
"naucs_at_3_max": -0.06153567044815501,
|
| 274 |
+
"naucs_at_3_std": 0.030866957364471828,
|
| 275 |
+
"naucs_at_3_diff1": 0.09346686092344683,
|
| 276 |
+
"naucs_at_5_max": -0.1001058508204584,
|
| 277 |
+
"naucs_at_5_std": 0.04694753152769551,
|
| 278 |
+
"naucs_at_5_diff1": -0.020745149639172823,
|
| 279 |
+
"naucs_at_10_max": -0.22434069455501207,
|
| 280 |
+
"naucs_at_10_std": -0.024981550214707424,
|
| 281 |
+
"naucs_at_10_diff1": 0.0217892641566212,
|
| 282 |
+
"naucs_at_20_max": -0.25677009699234504,
|
| 283 |
+
"naucs_at_20_std": -0.0682727441498392,
|
| 284 |
+
"naucs_at_20_diff1": 0.006600406019144755,
|
| 285 |
+
"naucs_at_50_max": -0.35279837382749224,
|
| 286 |
+
"naucs_at_50_std": -0.11860050488498859,
|
| 287 |
+
"naucs_at_50_diff1": 0.038218272907462776,
|
| 288 |
+
"naucs_at_100_max": -0.3770191365581463,
|
| 289 |
+
"naucs_at_100_std": -0.12210563039488978,
|
| 290 |
+
"naucs_at_100_diff1": 0.026981449415877188
|
| 291 |
+
},
|
| 292 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
|
| 293 |
+
"ndcg_at_1": 0.4625,
|
| 294 |
+
"ndcg_at_3": 0.48461,
|
| 295 |
+
"ndcg_at_5": 0.50748,
|
| 296 |
+
"ndcg_at_10": 0.54374,
|
| 297 |
+
"ndcg_at_20": 0.57313,
|
| 298 |
+
"ndcg_at_50": 0.60015,
|
| 299 |
+
"ndcg_at_100": 0.61619,
|
| 300 |
+
"map_at_1": 0.27248,
|
| 301 |
+
"map_at_3": 0.38318,
|
| 302 |
+
"map_at_5": 0.41661,
|
| 303 |
+
"map_at_10": 0.44791,
|
| 304 |
+
"map_at_20": 0.46236,
|
| 305 |
+
"map_at_50": 0.4712,
|
| 306 |
+
"map_at_100": 0.47443,
|
| 307 |
+
"recall_at_1": 0.27248,
|
| 308 |
+
"recall_at_3": 0.46329,
|
| 309 |
+
"recall_at_5": 0.54925,
|
| 310 |
+
"recall_at_10": 0.65759,
|
| 311 |
+
"recall_at_20": 0.74374,
|
| 312 |
+
"recall_at_50": 0.82939,
|
| 313 |
+
"recall_at_100": 0.89386,
|
| 314 |
+
"precision_at_1": 0.4625,
|
| 315 |
+
"precision_at_3": 0.30469,
|
| 316 |
+
"precision_at_5": 0.23187,
|
| 317 |
+
"precision_at_10": 0.1525,
|
| 318 |
+
"precision_at_20": 0.09328,
|
| 319 |
+
"precision_at_50": 0.04575,
|
| 320 |
+
"precision_at_100": 0.02583,
|
| 321 |
+
"mrr_at_1": 0.4640625,
|
| 322 |
+
"mrr_at_3": 0.5674479166666667,
|
| 323 |
+
"mrr_at_5": 0.5858854166666666,
|
| 324 |
+
"mrr_at_10": 0.5973053075396825,
|
| 325 |
+
"mrr_at_20": 0.6012510964160539,
|
| 326 |
+
"mrr_at_50": 0.6024522115162709,
|
| 327 |
+
"mrr_at_100": 0.6028758281345057,
|
| 328 |
+
"naucs_at_1_max": 0.26141725163984275,
|
| 329 |
+
"naucs_at_1_std": 0.05513611928520957,
|
| 330 |
+
"naucs_at_1_diff1": 0.42015938121619634,
|
| 331 |
+
"naucs_at_3_max": 0.1399680610762722,
|
| 332 |
+
"naucs_at_3_std": 0.045180219047584395,
|
| 333 |
+
"naucs_at_3_diff1": 0.11481164579324413,
|
| 334 |
+
"naucs_at_5_max": 0.04584991439766228,
|
| 335 |
+
"naucs_at_5_std": -0.04550137691456216,
|
| 336 |
+
"naucs_at_5_diff1": 0.004357676059305207,
|
| 337 |
+
"naucs_at_10_max": -0.06683145550701278,
|
| 338 |
+
"naucs_at_10_std": -0.10664376868245524,
|
| 339 |
+
"naucs_at_10_diff1": -0.08678934812600536,
|
| 340 |
+
"naucs_at_20_max": -0.1296230042230784,
|
| 341 |
+
"naucs_at_20_std": -0.14815581967152328,
|
| 342 |
+
"naucs_at_20_diff1": -0.14412731888436792,
|
| 343 |
+
"naucs_at_50_max": -0.19435807140448796,
|
| 344 |
+
"naucs_at_50_std": -0.16212181647094098,
|
| 345 |
+
"naucs_at_50_diff1": -0.1726383431655357,
|
| 346 |
+
"naucs_at_100_max": -0.23236001607504117,
|
| 347 |
+
"naucs_at_100_std": -0.17507627344711169,
|
| 348 |
+
"naucs_at_100_diff1": -0.18675384146781612
|
| 349 |
+
},
|
| 350 |
+
"vidore/synthetic_axa_filtered_v1.0": {
|
| 351 |
+
"ndcg_at_1": 0.5,
|
| 352 |
+
"ndcg_at_3": 0.5515,
|
| 353 |
+
"ndcg_at_5": 0.54656,
|
| 354 |
+
"ndcg_at_10": 0.58542,
|
| 355 |
+
"ndcg_at_20": 0.61074,
|
| 356 |
+
"ndcg_at_50": 0.66471,
|
| 357 |
+
"ndcg_at_100": 0.67865,
|
| 358 |
+
"map_at_1": 0.23561,
|
| 359 |
+
"map_at_3": 0.35526,
|
| 360 |
+
"map_at_5": 0.40288,
|
| 361 |
+
"map_at_10": 0.45602,
|
| 362 |
+
"map_at_20": 0.47984,
|
| 363 |
+
"map_at_50": 0.5053,
|
| 364 |
+
"map_at_100": 0.50979,
|
| 365 |
+
"recall_at_1": 0.23561,
|
| 366 |
+
"recall_at_3": 0.40357,
|
| 367 |
+
"recall_at_5": 0.50646,
|
| 368 |
+
"recall_at_10": 0.69428,
|
| 369 |
+
"recall_at_20": 0.7691,
|
| 370 |
+
"recall_at_50": 0.91971,
|
| 371 |
+
"recall_at_100": 0.96283,
|
| 372 |
+
"precision_at_1": 0.5,
|
| 373 |
+
"precision_at_3": 0.40741,
|
| 374 |
+
"precision_at_5": 0.32222,
|
| 375 |
+
"precision_at_10": 0.22778,
|
| 376 |
+
"precision_at_20": 0.14444,
|
| 377 |
+
"precision_at_50": 0.08111,
|
| 378 |
+
"precision_at_100": 0.04389,
|
| 379 |
+
"mrr_at_1": 0.4444444444444444,
|
| 380 |
+
"mrr_at_3": 0.5833333333333334,
|
| 381 |
+
"mrr_at_5": 0.6333333333333333,
|
| 382 |
+
"mrr_at_10": 0.6333333333333333,
|
| 383 |
+
"mrr_at_20": 0.6333333333333333,
|
| 384 |
+
"mrr_at_50": 0.6345410628019325,
|
| 385 |
+
"mrr_at_100": 0.6345410628019325,
|
| 386 |
+
"naucs_at_1_max": 0.07889050288999765,
|
| 387 |
+
"naucs_at_1_std": 0.06985911407713058,
|
| 388 |
+
"naucs_at_1_diff1": -0.05179633645139645,
|
| 389 |
+
"naucs_at_3_max": -0.4314479663108273,
|
| 390 |
+
"naucs_at_3_std": -0.2220643287660875,
|
| 391 |
+
"naucs_at_3_diff1": -0.1357836927675026,
|
| 392 |
+
"naucs_at_5_max": -0.6137311723661342,
|
| 393 |
+
"naucs_at_5_std": -0.4297107168497019,
|
| 394 |
+
"naucs_at_5_diff1": -0.282928276376364,
|
| 395 |
+
"naucs_at_10_max": -0.7132869751846498,
|
| 396 |
+
"naucs_at_10_std": -0.4029481109560288,
|
| 397 |
+
"naucs_at_10_diff1": -0.29283755342944695,
|
| 398 |
+
"naucs_at_20_max": -0.7476746519743882,
|
| 399 |
+
"naucs_at_20_std": -0.4383230899669276,
|
| 400 |
+
"naucs_at_20_diff1": -0.2568560566050879,
|
| 401 |
+
"naucs_at_50_max": -0.6810001577310205,
|
| 402 |
+
"naucs_at_50_std": -0.4592319089280611,
|
| 403 |
+
"naucs_at_50_diff1": -0.2697688110166736,
|
| 404 |
+
"naucs_at_100_max": -0.6920540059961603,
|
| 405 |
+
"naucs_at_100_std": -0.4975891795439652,
|
| 406 |
+
"naucs_at_100_diff1": -0.27228925118802566
|
| 407 |
+
},
|
| 408 |
+
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
|
| 409 |
+
"ndcg_at_1": 0.58621,
|
| 410 |
+
"ndcg_at_3": 0.56958,
|
| 411 |
+
"ndcg_at_5": 0.56747,
|
| 412 |
+
"ndcg_at_10": 0.55498,
|
| 413 |
+
"ndcg_at_20": 0.56167,
|
| 414 |
+
"ndcg_at_50": 0.63326,
|
| 415 |
+
"ndcg_at_100": 0.67651,
|
| 416 |
+
"map_at_1": 0.05512,
|
| 417 |
+
"map_at_3": 0.15633,
|
| 418 |
+
"map_at_5": 0.21393,
|
| 419 |
+
"map_at_10": 0.28249,
|
| 420 |
+
"map_at_20": 0.33276,
|
| 421 |
+
"map_at_50": 0.39554,
|
| 422 |
+
"map_at_100": 0.42521,
|
| 423 |
+
"recall_at_1": 0.05512,
|
| 424 |
+
"recall_at_3": 0.20041,
|
| 425 |
+
"recall_at_5": 0.31679,
|
| 426 |
+
"recall_at_10": 0.45216,
|
| 427 |
+
"recall_at_20": 0.56899,
|
| 428 |
+
"recall_at_50": 0.78061,
|
| 429 |
+
"recall_at_100": 0.92301,
|
| 430 |
+
"precision_at_1": 0.58621,
|
| 431 |
+
"precision_at_3": 0.54023,
|
| 432 |
+
"precision_at_5": 0.51034,
|
| 433 |
+
"precision_at_10": 0.42241,
|
| 434 |
+
"precision_at_20": 0.30603,
|
| 435 |
+
"precision_at_50": 0.19931,
|
| 436 |
+
"precision_at_100": 0.12897,
|
| 437 |
+
"mrr_at_1": 0.603448275862069,
|
| 438 |
+
"mrr_at_3": 0.7097701149425287,
|
| 439 |
+
"mrr_at_5": 0.7313218390804598,
|
| 440 |
+
"mrr_at_10": 0.7392241379310345,
|
| 441 |
+
"mrr_at_20": 0.7392241379310345,
|
| 442 |
+
"mrr_at_50": 0.7397030651340997,
|
| 443 |
+
"mrr_at_100": 0.7397030651340997,
|
| 444 |
+
"naucs_at_1_max": -0.010118734871006329,
|
| 445 |
+
"naucs_at_1_std": 0.10980876856822328,
|
| 446 |
+
"naucs_at_1_diff1": 0.10183634578730963,
|
| 447 |
+
"naucs_at_3_max": -0.1267323207616976,
|
| 448 |
+
"naucs_at_3_std": -0.05661790845083188,
|
| 449 |
+
"naucs_at_3_diff1": 0.07369354139119677,
|
| 450 |
+
"naucs_at_5_max": 0.019942753252902908,
|
| 451 |
+
"naucs_at_5_std": 0.06455436252441091,
|
| 452 |
+
"naucs_at_5_diff1": 0.06695101207889216,
|
| 453 |
+
"naucs_at_10_max": 0.041208495495496496,
|
| 454 |
+
"naucs_at_10_std": 0.09070057327978881,
|
| 455 |
+
"naucs_at_10_diff1": 0.030402393460177066,
|
| 456 |
+
"naucs_at_20_max": 0.025702140238159837,
|
| 457 |
+
"naucs_at_20_std": 0.0742736380683647,
|
| 458 |
+
"naucs_at_20_diff1": 0.0600844047880318,
|
| 459 |
+
"naucs_at_50_max": -0.0005572407939892689,
|
| 460 |
+
"naucs_at_50_std": 0.07144824248048325,
|
| 461 |
+
"naucs_at_50_diff1": 0.10429455029904204,
|
| 462 |
+
"naucs_at_100_max": -0.07307588097557434,
|
| 463 |
+
"naucs_at_100_std": -0.0036128034099943912,
|
| 464 |
+
"naucs_at_100_diff1": 0.14294030303877456
|
| 465 |
+
}, "validation_set": {"ndcg_at_1": 0.782, "ndcg_at_3": 0.83869, "ndcg_at_5": 0.84945, "ndcg_at_10": 0.86122, "ndcg_at_20": 0.86639, "ndcg_at_100": 0.87296, "ndcg_at_1000": 0.87382, "map_at_1": 0.782, "map_at_3": 0.82567, "map_at_5": 0.83167, "map_at_10": 0.83659, "map_at_20": 0.83807, "map_at_100": 0.83894, "map_at_1000": 0.83899, "recall_at_1": 0.782, "recall_at_3": 0.876, "recall_at_5": 0.902, "recall_at_10": 0.938, "recall_at_20": 0.958, "recall_at_100": 0.994, "recall_at_1000": 1.0, "precision_at_1": 0.782, "precision_at_3": 0.292, "precision_at_5": 0.1804, "precision_at_10": 0.0938, "precision_at_20": 0.0479, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.786, "mrr_at_3": 0.8293333333333331, "mrr_at_5": 0.8353333333333332, "mrr_at_10": 0.8401857142857142, "mrr_at_20": 0.8413927173703489, "mrr_at_100": 0.842343017479603, "mrr_at_1000": 0.84237119907226, "naucs_at_1_max": 0.1287204083634169, "naucs_at_1_std": 0.04394670353021356, "naucs_at_1_diff1": 0.9147079015332307, "naucs_at_3_max": 0.15408207410154462, "naucs_at_3_std": 0.24171070115262258, "naucs_at_3_diff1": 0.8671703593832085, "naucs_at_5_max": 0.14837363516835303, "naucs_at_5_std": 0.31976600163875035, "naucs_at_5_diff1": 0.8631452581032408, "naucs_at_10_max": 0.1179633143579976, "naucs_at_10_std": 0.597316345893196, "naucs_at_10_diff1": 0.8860124695039325, "naucs_at_20_max": 0.12424969987995331, "naucs_at_20_std": 0.7891823396025082, "naucs_at_20_diff1": 0.9336401227157501, "naucs_at_100_max": -0.17133520074699127, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.91917, "ndcg_at_5": 0.92347, "ndcg_at_10": 0.92937, "ndcg_at_20": 0.92937, "ndcg_at_100": 0.93128, "ndcg_at_1000": 0.93277, "map_at_1": 0.87, "map_at_3": 0.90833, "map_at_5": 0.91083, "map_at_10": 0.91294, "map_at_20": 0.91294, "map_at_100": 0.91321, "map_at_1000": 0.91331, "recall_at_1": 0.87, "recall_at_3": 0.95, "recall_at_5": 0.96, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.31667, "precision_at_5": 0.192, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.88, "mrr_at_3": 0.9133333333333333, "mrr_at_5": 0.9158333333333333, "mrr_at_10": 0.9183730158730158, "mrr_at_20": 0.9183730158730158, "mrr_at_100": 0.9187453269596126, "mrr_at_1000": 0.9187453269596126, "naucs_at_1_max": 0.24364955935718074, "naucs_at_1_std": -0.12800859068355205, "naucs_at_1_diff1": 0.9218692142486855, "naucs_at_3_max": 0.21577964519141157, "naucs_at_3_std": -0.2550887021475216, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": 0.05240429505135564, "naucs_at_5_std": -0.5361811391223089, "naucs_at_5_diff1": 0.9346405228758139, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": 0.07936507936508234, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.7957516339869297, "naucs_at_20_std": 0.07936507936508234, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": 0.8692810457516374, "naucs_at_100_std": 0.7222222222222041, "naucs_at_100_diff1": 0.8692810457516374, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.94893, "ndcg_at_5": 0.94893, "ndcg_at_10": 0.94893, "ndcg_at_20": 0.95163, "ndcg_at_100": 0.95554, "ndcg_at_1000": 0.95554, "map_at_1": 0.92, "map_at_3": 0.94167, "map_at_5": 0.94167, "map_at_10": 0.94167, "map_at_20": 0.9425, "map_at_100": 0.94313, "map_at_1000": 0.94313, "recall_at_1": 0.92, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.9416666666666665, "mrr_at_5": 0.9416666666666665, "mrr_at_10": 0.9426666666666665, "mrr_at_20": 0.9426666666666665, "mrr_at_100": 0.9433152709359603, "mrr_at_1000": 0.9433152709359603, "naucs_at_1_max": 0.129493464052287, "naucs_at_1_std": -0.1989379084967342, "naucs_at_1_diff1": 0.8468137254901948, "naucs_at_3_max": -0.00964830376594965, "naucs_at_3_std": -0.7268907563025196, "naucs_at_3_diff1": 0.8638344226579548, "naucs_at_5_max": -0.009648303765951795, "naucs_at_5_std": -0.7268907563025226, "naucs_at_5_diff1": 0.8638344226579531, "naucs_at_10_max": -0.009648303765951795, "naucs_at_10_std": -0.7268907563025226, "naucs_at_10_diff1": 0.8638344226579531, "naucs_at_20_max": -0.5144724556489195, "naucs_at_20_std": -1.1517273576097127, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.97393, "ndcg_at_5": 0.97393, "ndcg_at_10": 0.97393, "ndcg_at_20": 0.97393, "ndcg_at_100": 0.97581, "ndcg_at_1000": 0.97581, "map_at_1": 0.95, "map_at_3": 0.96833, "map_at_5": 0.96833, "map_at_10": 0.96833, "map_at_20": 0.96833, "map_at_100": 0.96859, "map_at_1000": 0.96859, "recall_at_1": 0.95, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.95, "mrr_at_3": 0.9683333333333334, "mrr_at_5": 0.9683333333333334, "mrr_at_10": 0.9683333333333334, "mrr_at_20": 0.9683333333333334, "mrr_at_100": 0.9686111111111111, "mrr_at_1000": 0.9686111111111111, "naucs_at_1_max": -0.2407096171802055, "naucs_at_1_std": -0.8749766573295958, "naucs_at_1_diff1": 0.8846872082166202, "naucs_at_3_max": -1.7399626517274398, "naucs_at_3_std": -1.7399626517274398, "naucs_at_3_diff1": 0.5541549953314585, "naucs_at_5_max": -1.7399626517273863, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.5541549953314738, "naucs_at_10_max": -1.7399626517273863, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.5541549953314738, "naucs_at_20_max": -1.7399626517273863, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 0.5541549953314738, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.86, "ndcg_at_3": 0.91286, "ndcg_at_5": 0.92147, "ndcg_at_10": 0.92448, "ndcg_at_20": 0.92727, "ndcg_at_100": 0.92929, "ndcg_at_1000": 0.92929, "map_at_1": 0.86, "map_at_3": 0.9, "map_at_5": 0.905, "map_at_10": 0.90611, "map_at_20": 0.90702, "map_at_100": 0.90735, "map_at_1000": 0.90735, "recall_at_1": 0.86, "recall_at_3": 0.95, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.86, "precision_at_3": 0.31667, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.9, "mrr_at_5": 0.905, "mrr_at_10": 0.90625, "mrr_at_20": 0.907159090909091, "mrr_at_100": 0.9075039184952978, "mrr_at_1000": 0.9075039184952978, "naucs_at_1_max": 0.43501454898157155, "naucs_at_1_std": 0.2136275460717749, "naucs_at_1_diff1": 0.9035263960094214, "naucs_at_3_max": 0.6491129785247453, "naucs_at_3_std": 0.4804855275443501, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 0.9128540305010848, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 0.8692810457516413, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.732, "ndcg_at_3": 0.79395, "ndcg_at_5": 0.81366, "ndcg_at_10": 0.82475, "ndcg_at_20": 0.82906, "ndcg_at_100": 0.83691, "ndcg_at_1000": 0.83975, "map_at_1": 0.732, "map_at_3": 0.77933, "map_at_5": 0.79023, "map_at_10": 0.79487, "map_at_20": 0.79593, "map_at_100": 0.79706, "map_at_1000": 0.79717, "recall_at_1": 0.732, "recall_at_3": 0.836, "recall_at_5": 0.884, "recall_at_10": 0.918, "recall_at_20": 0.936, "recall_at_100": 0.978, "recall_at_1000": 1.0, "precision_at_1": 0.732, "precision_at_3": 0.27867, "precision_at_5": 0.1768, "precision_at_10": 0.0918, "precision_at_20": 0.0468, "precision_at_100": 0.00978, "precision_at_1000": 0.001, "mrr_at_1": 0.732, "mrr_at_3": 0.7786666666666665, "mrr_at_5": 0.7900666666666664, "mrr_at_10": 0.794449206349206, "mrr_at_20": 0.7953232247284874, "mrr_at_100": 0.7966255910510839, "mrr_at_1000": 0.7967190443508116, "naucs_at_1_max": 0.4347700535605503, "naucs_at_1_std": 0.0052057373871626685, "naucs_at_1_diff1": 0.865643715535724, "naucs_at_3_max": 0.6048031004775511, "naucs_at_3_std": 0.15614576084087275, "naucs_at_3_diff1": 0.8398166590674573, "naucs_at_5_max": 0.5930604282107613, "naucs_at_5_std": 0.1861700383619125, "naucs_at_5_diff1": 0.7956080527230405, "naucs_at_10_max": 0.6479242103345397, "naucs_at_10_std": 0.25604062763316404, "naucs_at_10_diff1": 0.7970326341918881, "naucs_at_20_max": 0.6982668067226916, "naucs_at_20_std": 0.40970763305321833, "naucs_at_20_diff1": 0.7613941409897302, "naucs_at_100_max": 0.9762329174093898, "naucs_at_100_std": 0.8936847466259251, "naucs_at_100_diff1": 0.80561921738392, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.458, "ndcg_at_3": 0.5249, "ndcg_at_5": 0.54987, "ndcg_at_10": 0.5691, "ndcg_at_20": 0.58534, "ndcg_at_100": 0.60898, "ndcg_at_1000": 0.62315, "map_at_1": 0.458, "map_at_3": 0.508, "map_at_5": 0.522, "map_at_10": 0.52983, "map_at_20": 0.53432, "map_at_100": 0.53744, "map_at_1000": 0.53795, "recall_at_1": 0.458, "recall_at_3": 0.574, "recall_at_5": 0.634, "recall_at_10": 0.694, "recall_at_20": 0.758, "recall_at_100": 0.888, "recall_at_1000": 1.0, "precision_at_1": 0.458, "precision_at_3": 0.19133, "precision_at_5": 0.1268, "precision_at_10": 0.0694, "precision_at_20": 0.0379, "precision_at_100": 0.00888, "precision_at_1000": 0.001, "mrr_at_1": 0.462, "mrr_at_3": 0.5103333333333334, "mrr_at_5": 0.5240333333333334, "mrr_at_10": 0.5330150793650792, "mrr_at_20": 0.5363530102594342, "mrr_at_100": 0.5398099695126392, "mrr_at_1000": 0.540360971784682, "naucs_at_1_max": 0.14478705160292352, "naucs_at_1_std": 0.3721140942241178, "naucs_at_1_diff1": 0.8556357724943732, "naucs_at_3_max": 0.0955052454658937, "naucs_at_3_std": 0.4342882512519065, "naucs_at_3_diff1": 0.7991501163256658, "naucs_at_5_max": 0.01343769437454414, "naucs_at_5_std": 0.48670912254002735, "naucs_at_5_diff1": 0.7732231206645599, "naucs_at_10_max": -0.024673527538943748, "naucs_at_10_std": 0.5356353895792051, "naucs_at_10_diff1": 0.7689667071014644, "naucs_at_20_max": -0.12562798953100113, "naucs_at_20_std": 0.5620597626854955, "naucs_at_20_diff1": 0.7722820785003025, "naucs_at_100_max": -0.23859408820346314, "naucs_at_100_std": 0.864870806277056, "naucs_at_100_diff1": 0.7339945211038957, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.712, "ndcg_at_3": 0.76712, "ndcg_at_5": 0.78364, "ndcg_at_10": 0.80123, "ndcg_at_20": 0.812, "ndcg_at_100": 0.81995, "ndcg_at_1000": 0.82209, "map_at_1": 0.712, "map_at_3": 0.75367, "map_at_5": 0.76287, "map_at_10": 0.77019, "map_at_20": 0.77323, "map_at_100": 0.7744, "map_at_1000": 0.77449, "recall_at_1": 0.712, "recall_at_3": 0.806, "recall_at_5": 0.846, "recall_at_10": 0.9, "recall_at_20": 0.942, "recall_at_100": 0.984, "recall_at_1000": 1.0, "precision_at_1": 0.712, "precision_at_3": 0.26867, "precision_at_5": 0.1692, "precision_at_10": 0.09, "precision_at_20": 0.0471, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.724, "mrr_at_3": 0.7626666666666667, "mrr_at_5": 0.7716666666666666, "mrr_at_10": 0.7785738095238096, "mrr_at_20": 0.7814459001782531, "mrr_at_100": 0.7824821791237915, "mrr_at_1000": 0.7825927236311448, "naucs_at_1_max": 0.5179261037469994, "naucs_at_1_std": 0.0715515827456125, "naucs_at_1_diff1": 0.8994028359700004, "naucs_at_3_max": 0.5866330274286543, "naucs_at_3_std": 0.15098605444623744, "naucs_at_3_diff1": 0.8370723586175715, "naucs_at_5_max": 0.6037655521242381, "naucs_at_5_std": 0.16178021782505292, "naucs_at_5_diff1": 0.8241259674406191, "naucs_at_10_max": 0.5842483660130722, "naucs_at_10_std": 0.20487394957983113, "naucs_at_10_diff1": 0.7742016806722692, "naucs_at_20_max": 0.735455101580865, "naucs_at_20_std": 0.3710035738433312, "naucs_at_20_diff1": 0.7694871051869058, "naucs_at_100_max": 0.8503151260504297, "naucs_at_100_std": 0.5717787114846009, "naucs_at_100_diff1": 0.8129668534080331, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.76429, "ndcg_at_3": 0.83078, "ndcg_at_5": 0.84353, "ndcg_at_10": 0.85388, "ndcg_at_20": 0.86455, "ndcg_at_100": 0.86741, "ndcg_at_1000": 0.86741, "map_at_1": 0.76429, "map_at_3": 0.81429, "map_at_5": 0.82107, "map_at_10": 0.82532, "map_at_20": 0.82817, "map_at_100": 0.82864, "map_at_1000": 0.82864, "recall_at_1": 0.76429, "recall_at_3": 0.87857, "recall_at_5": 0.91071, "recall_at_10": 0.94286, "recall_at_20": 0.98571, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.76429, "precision_at_3": 0.29286, "precision_at_5": 0.18214, "precision_at_10": 0.09429, "precision_at_20": 0.04929, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.7571428571428571, "mrr_at_3": 0.8095238095238096, "mrr_at_5": 0.8179166666666666, "mrr_at_10": 0.8214625850340135, "mrr_at_20": 0.8241040305215449, "mrr_at_100": 0.8247231380884232, "mrr_at_1000": 0.8247231380884232, "naucs_at_1_max": 0.4032387013842082, "naucs_at_1_std": 0.20721575143829152, "naucs_at_1_diff1": 0.8371243592356286, "naucs_at_3_max": 0.37018609096531074, "naucs_at_3_std": 0.19961207623545132, "naucs_at_3_diff1": 0.7850677461067068, "naucs_at_5_max": 0.49086834733893503, "naucs_at_5_std": 0.26750700280112155, "naucs_at_5_diff1": 0.7712791783380023, "naucs_at_10_max": 0.5342845471521948, "naucs_at_10_std": 0.382148692810459, "naucs_at_10_diff1": 0.7389122315592906, "naucs_at_20_max": 0.42938842203549277, "naucs_at_20_std": 0.5764472455649069, "naucs_at_20_diff1": 0.8978758169934754, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.51714, "ndcg_at_3": 0.63347, "ndcg_at_5": 0.65997, "ndcg_at_10": 0.68432, "ndcg_at_20": 0.69776, "ndcg_at_100": 0.71265, "ndcg_at_1000": 0.7148, "map_at_1": 0.51714, "map_at_3": 0.60543, "map_at_5": 0.62013, "map_at_10": 0.63032, "map_at_20": 0.63413, "map_at_100": 0.63629, "map_at_1000": 0.63639, "recall_at_1": 0.51714, "recall_at_3": 0.71437, "recall_at_5": 0.77871, "recall_at_10": 0.85328, "recall_at_20": 0.90559, "recall_at_100": 0.98437, "recall_at_1000": 1.0, "precision_at_1": 0.51714, "precision_at_3": 0.23812, "precision_at_5": 0.15574, "precision_at_10": 0.08533, "precision_at_20": 0.04528, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.5189416716776909, "mrr_at_3": 0.6063339346562444, "mrr_at_5": 0.6203447584686321, "mrr_at_10": 0.6304701295230465, "mrr_at_20": 0.6343502614596628, "mrr_at_100": 0.6366034259317307, "mrr_at_1000": 0.6366958159270893, "naucs_at_1_max": 0.16652309459558007, "naucs_at_1_std": -0.06670433006927416, "naucs_at_1_diff1": 0.6953792910740597, "naucs_at_3_max": 0.16902492509679246, "naucs_at_3_std": -0.03701362337519723, "naucs_at_3_diff1": 0.5494053126321319, "naucs_at_5_max": 0.21105315084874532, "naucs_at_5_std": 0.04611791703673267, "naucs_at_5_diff1": 0.5162174552139975, "naucs_at_10_max": 0.23091913809374726, "naucs_at_10_std": 0.10830125135311366, "naucs_at_10_diff1": 0.4866871626269709, "naucs_at_20_max": 0.2725948129883982, "naucs_at_20_std": 0.24954038307560938, "naucs_at_20_diff1": 0.4588931923467883, "naucs_at_100_max": 0.6502319824989845, "naucs_at_100_std": 0.6011619544721175, "naucs_at_100_diff1": 0.7480994634253559, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.56, "ndcg_at_3": 0.70095, "ndcg_at_5": 0.72934, "ndcg_at_10": 0.74318, "ndcg_at_20": 0.7537, "ndcg_at_100": 0.75912, "ndcg_at_1000": 0.76194, "map_at_1": 0.56, "map_at_3": 0.66667, "map_at_5": 0.68217, "map_at_10": 0.68842, "map_at_20": 0.69152, "map_at_100": 0.69222, "map_at_1000": 0.69237, "recall_at_1": 0.56, "recall_at_3": 0.8, "recall_at_5": 0.87, "recall_at_10": 0.91, "recall_at_20": 0.95, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.56, "precision_at_3": 0.26667, "precision_at_5": 0.174, "precision_at_10": 0.091, "precision_at_20": 0.0475, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.59, "mrr_at_3": 0.69, "mrr_at_5": 0.7055, "mrr_at_10": 0.7100833333333334, "mrr_at_20": 0.7131832236391059, "mrr_at_100": 0.7139141492175927, "mrr_at_1000": 0.7140687525760177, "naucs_at_1_max": -0.06823472632296203, "naucs_at_1_std": -0.21851578469225566, "naucs_at_1_diff1": 0.6402168975698381, "naucs_at_3_max": -0.5083416583416578, "naucs_at_3_std": -0.719330669330669, "naucs_at_3_diff1": 0.49285714285714205, "naucs_at_5_max": -0.40505813522920514, "naucs_at_5_std": -0.5592460934607096, "naucs_at_5_diff1": 0.3987632377990074, "naucs_at_10_max": -0.4162776221599734, "naucs_at_10_std": -0.47852474323062383, "naucs_at_10_diff1": 0.4046062869592272, "naucs_at_20_max": -0.5808590102707625, "naucs_at_20_std": -0.5164332399626398, "naucs_at_20_diff1": 0.4697478991596656, "naucs_at_100_max": -1.4458450046685247, "naucs_at_100_std": -1.4458450046685247, "naucs_at_100_diff1": 0.6790382819794637, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|