vidore
baseline-results / Metric-AI_ColQwen2.5-3b-multilingual-v1.0_metrics.json
QuentinJG's picture
Rename metricsai-colqwen2.5-3B_metrics.json to Metric-AI_ColQwen2.5-3b-multilingual-v1.0_metrics.json
bb15d19 verified
{"vidore/restaurant_esg_reports_beir":{"ndcg_at_1": 0.5641, "ndcg_at_3": 0.61604, "ndcg_at_5": 0.64523, "ndcg_at_10": 0.66319, "ndcg_at_20": 0.69104, "ndcg_at_50": 0.71575, "ndcg_at_100": 0.72387, "map_at_1": 0.4234, "map_at_3": 0.54407, "map_at_5": 0.58557, "map_at_10": 0.60212, "map_at_20": 0.61211, "map_at_50": 0.61967, "map_at_100": 0.62199, "recall_at_1": 0.4234, "recall_at_3": 0.62533, "recall_at_5": 0.70482, "recall_at_10": 0.75962, "recall_at_20": 0.85034, "recall_at_50": 0.93423, "recall_at_100": 0.96774, "precision_at_1": 0.57692, "precision_at_3": 0.34615, "precision_at_5": 0.26154, "precision_at_10": 0.14808, "precision_at_20": 0.08558, "precision_at_50": 0.04077, "precision_at_100": 0.02212, "mrr_at_1": 0.5576923076923077, "mrr_at_3": 0.6474358974358974, "mrr_at_5": 0.6743589743589743, "mrr_at_10": 0.6786858974358972, "mrr_at_20": 0.6825587606837605, "mrr_at_50": 0.6839578245828245, "mrr_at_100": 0.6839578245828245, "naucs_at_1_max": 0.12470284876770442, "naucs_at_1_std": 0.06817750621913438, "naucs_at_1_diff1": 0.4584043207202866, "naucs_at_3_max": -0.11006237135309298, "naucs_at_3_std": 0.05921171205563436, "naucs_at_3_diff1": 0.13723460622180583, "naucs_at_5_max": -0.023873126058899085, "naucs_at_5_std": 0.214743578620473, "naucs_at_5_diff1": 0.09099077341669573, "naucs_at_10_max": -0.11645646003591865, "naucs_at_10_std": 0.1330695190974458, "naucs_at_10_diff1": 0.013768789077886163, "naucs_at_20_max": -0.1194792293159246, "naucs_at_20_std": 0.13293416045352552, "naucs_at_20_diff1": -0.06239592008145245, "naucs_at_50_max": -0.03153740708273005, "naucs_at_50_std": 0.11848179477156962, "naucs_at_50_diff1": -0.15565870739263224, "naucs_at_100_max": -0.08672829811752045, "naucs_at_100_std": 0.07436098918794656, "naucs_at_100_diff1": -0.1864938163314166}, "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {"ndcg_at_1": 0.61875, "ndcg_at_3": 0.62246, "ndcg_at_5": 0.63924, "ndcg_at_10": 0.67163, "ndcg_at_20": 0.70058, "ndcg_at_50": 0.72114, "ndcg_at_100": 0.73266, "map_at_1": 0.37939, "map_at_3": 0.51083, "map_at_5": 0.5477, "map_at_10": 0.58314, "map_at_20": 0.59994, "map_at_50": 0.6088, "map_at_100": 0.61147, "recall_at_1": 0.37939, "recall_at_3": 0.58446, "recall_at_5": 0.66836, "recall_at_10": 0.75971, "recall_at_20": 0.84104, "recall_at_50": 0.89754, "recall_at_100": 0.93919, "precision_at_1": 0.61875, "precision_at_3": 0.3875, "precision_at_5": 0.28625, "precision_at_10": 0.18375, "precision_at_20": 0.10906, "precision_at_50": 0.0515, "precision_at_100": 0.02831, "mrr_at_1": 0.625, "mrr_at_3": 0.7145833333333332, "mrr_at_5": 0.7333333333333332, "mrr_at_10": 0.7384523809523809, "mrr_at_20": 0.7395886199874686, "mrr_at_50": 0.7401749056380924, "mrr_at_100": 0.7401749056380924, "naucs_at_1_max": 0.24217483476742752, "naucs_at_1_std": -0.014350532869050992, "naucs_at_1_diff1": 0.3571133941504312, "naucs_at_3_max": 0.028529885089923428, "naucs_at_3_std": 0.03359778649877172, "naucs_at_3_diff1": -0.15262994438013527, "naucs_at_5_max": -0.08017448912595918, "naucs_at_5_std": -0.02145504048785724, "naucs_at_5_diff1": -0.2135785479270142, "naucs_at_10_max": -0.16205586960924298, "naucs_at_10_std": -0.011953486162608103, "naucs_at_10_diff1": -0.2726174909430024, "naucs_at_20_max": -0.15859152064800566, "naucs_at_20_std": 0.033451185198922324, "naucs_at_20_diff1": -0.32086616135934415, "naucs_at_50_max": -0.22031664106122587, "naucs_at_50_std": 0.045775721090992906, "naucs_at_50_diff1": -0.33672470050916925, "naucs_at_100_max": -0.2622643427422235, "naucs_at_100_std": 0.05165502689693449, "naucs_at_100_diff1": -0.3538361787121341}, "vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {"ndcg_at_1": 0.56897, "ndcg_at_3": 0.60357, "ndcg_at_5": 0.56582, "ndcg_at_10": 0.55097, "ndcg_at_20": 0.57423, "ndcg_at_50": 0.63184, "ndcg_at_100": 0.67525, "map_at_1": 0.05039, "map_at_3": 0.17113, "map_at_5": 0.22362, "map_at_10": 0.29776, "map_at_20": 0.36096, "map_at_50": 0.41381, "map_at_100": 0.44305, "recall_at_1": 0.05039, "recall_at_3": 0.22927, "recall_at_5": 0.31688, "recall_at_10": 0.44932, "recall_at_20": 0.58884, "recall_at_50": 0.77631, "recall_at_100": 0.90594, "precision_at_1": 0.56897, "precision_at_3": 0.59195, "precision_at_5": 0.51379, "precision_at_10": 0.41897, "precision_at_20": 0.31724, "precision_at_50": 0.19172, "precision_at_100": 0.12672, "mrr_at_1": 0.5689655172413793, "mrr_at_3": 0.6810344827586207, "mrr_at_5": 0.7008620689655174, "mrr_at_10": 0.7066091954022988, "mrr_at_20": 0.7099204825724791, "mrr_at_50": 0.7104429486121865, "mrr_at_100": 0.7104429486121865, "naucs_at_1_max": 0.3715241007741746, "naucs_at_1_std": 0.3854378396413163, "naucs_at_1_diff1": 0.21655716946668674, "naucs_at_3_max": 0.3147758992368106, "naucs_at_3_std": 0.2910247237245379, "naucs_at_3_diff1": 0.04001902276067528, "naucs_at_5_max": 0.1899152364264139, "naucs_at_5_std": 0.21745586589213664, "naucs_at_5_diff1": -0.017663459414469763, "naucs_at_10_max": 0.22945389322996618, "naucs_at_10_std": 0.2521459635460854, "naucs_at_10_diff1": 0.03960293197195496, "naucs_at_20_max": 0.15169305877630887, "naucs_at_20_std": 0.28589240822323597, "naucs_at_20_diff1": -0.05496752614168009, "naucs_at_50_max": 0.03587064969586194, "naucs_at_50_std": 0.2867365692912274, "naucs_at_50_diff1": -0.10935587593462023, "naucs_at_100_max": 0.011057467966996595, "naucs_at_100_std": 0.2510859293326388, "naucs_at_100_diff1": -0.08209071935179629}, "vidore/synthetic_rse_restaurant_filtered_v1.0": {"ndcg_at_1": 0.45614, "ndcg_at_3": 0.45464, "ndcg_at_5": 0.49615, "ndcg_at_10": 0.57804, "ndcg_at_20": 0.61136, "ndcg_at_50": 0.64324, "ndcg_at_100": 0.65657, "map_at_1": 0.22124, "map_at_3": 0.33462, "map_at_5": 0.38929, "map_at_10": 0.45014, "map_at_20": 0.47013, "map_at_50": 0.48782, "map_at_100": 0.494, "recall_at_1": 0.22124, "recall_at_3": 0.42343, "recall_at_5": 0.54029, "recall_at_10": 0.7547, "recall_at_20": 0.85524, "recall_at_50": 0.9386, "recall_at_100": 0.98246, "precision_at_1": 0.45614, "precision_at_3": 0.30409, "precision_at_5": 0.25614, "precision_at_10": 0.20175, "precision_at_20": 0.12632, "precision_at_50": 0.06912, "precision_at_100": 0.03877, "mrr_at_1": 0.47368421052631576, "mrr_at_3": 0.5701754385964912, "mrr_at_5": 0.5947368421052631, "mrr_at_10": 0.609983291562239, "mrr_at_20": 0.6138267992757156, "mrr_at_50": 0.6138267992757156, "mrr_at_100": 0.614005818251727, "naucs_at_1_max": -0.01733635828350866, "naucs_at_1_std": -0.044076320229319794, "naucs_at_1_diff1": 0.1835073718640758, "naucs_at_3_max": -0.006662681678139684, "naucs_at_3_std": -0.011188734407207942, "naucs_at_3_diff1": 0.049177700756489064, "naucs_at_5_max": -0.13348632164162694, "naucs_at_5_std": -0.11584756128595214, "naucs_at_5_diff1": 0.0474744158995849, "naucs_at_10_max": -0.26470759855448495, "naucs_at_10_std": -0.16940654464974741, "naucs_at_10_diff1": 0.03714803856970068, "naucs_at_20_max": -0.33026024462988285, "naucs_at_20_std": -0.18040730492069199, "naucs_at_20_diff1": 0.054413140570721504, "naucs_at_50_max": -0.3864934233165129, "naucs_at_50_std": -0.2097869533635532, "naucs_at_50_diff1": 0.054785418418783406, "naucs_at_100_max": -0.37827626160245187, "naucs_at_100_std": -0.17336702492207443, "naucs_at_100_diff1": 0.014345810433447107}, "vidore/synthetic_axa_filtered_v1.0": {"ndcg_at_1": 0.44444, "ndcg_at_3": 0.54134, "ndcg_at_5": 0.57922, "ndcg_at_10": 0.59619, "ndcg_at_20": 0.63277, "ndcg_at_50": 0.69139, "ndcg_at_100": 0.6979, "map_at_1": 0.22094, "map_at_3": 0.33189, "map_at_5": 0.40199, "map_at_10": 0.46332, "map_at_20": 0.50668, "map_at_50": 0.53607, "map_at_100": 0.53825, "recall_at_1": 0.22094, "recall_at_3": 0.43269, "recall_at_5": 0.56018, "recall_at_10": 0.70549, "recall_at_20": 0.80172, "recall_at_50": 0.97412, "recall_at_100": 0.99383, "precision_at_1": 0.44444, "precision_at_3": 0.40741, "precision_at_5": 0.37778, "precision_at_10": 0.26667, "precision_at_20": 0.17778, "precision_at_50": 0.09111, "precision_at_100": 0.04722, "mrr_at_1": 0.5, "mrr_at_3": 0.6388888888888888, "mrr_at_5": 0.6527777777777778, "mrr_at_10": 0.6597222222222222, "mrr_at_20": 0.6597222222222222, "mrr_at_50": 0.6618589743589743, "mrr_at_100": 0.6618589743589743, "naucs_at_1_max": 0.19453428854480095, "naucs_at_1_std": 0.32084602260218703, "naucs_at_1_diff1": 0.5074282674102887, "naucs_at_3_max": -0.46245302510493896, "naucs_at_3_std": -0.28478032300691175, "naucs_at_3_diff1": 0.030155736053876774, "naucs_at_5_max": -0.6059242124142128, "naucs_at_5_std": -0.33302211851387065, "naucs_at_5_diff1": 0.014390566070762573, "naucs_at_10_max": -0.7005430075232664, "naucs_at_10_std": -0.3106111226016172, "naucs_at_10_diff1": -0.0828736814205641, "naucs_at_20_max": -0.6975836911085798, "naucs_at_20_std": -0.29545664066101124, "naucs_at_20_diff1": -0.04874696052356921, "naucs_at_50_max": -0.670887258386394, "naucs_at_50_std": -0.2712286428298831, "naucs_at_50_diff1": 0.052959094659779896, "naucs_at_100_max": -0.6620422220682198, "naucs_at_100_std": -0.27687335368934246, "naucs_at_100_diff1": 0.07141325898077575}, "vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {"ndcg_at_1": 0.42982, "ndcg_at_3": 0.44603, "ndcg_at_5": 0.49184, "ndcg_at_10": 0.56375, "ndcg_at_20": 0.60372, "ndcg_at_50": 0.6343, "ndcg_at_100": 0.6469, "map_at_1": 0.20398, "map_at_3": 0.32395, "map_at_5": 0.37945, "map_at_10": 0.43453, "map_at_20": 0.45863, "map_at_50": 0.47581, "map_at_100": 0.48178, "recall_at_1": 0.20398, "recall_at_3": 0.42094, "recall_at_5": 0.54973, "recall_at_10": 0.74521, "recall_at_20": 0.86313, "recall_at_50": 0.94217, "recall_at_100": 0.98081, "precision_at_1": 0.42982, "precision_at_3": 0.30994, "precision_at_5": 0.26228, "precision_at_10": 0.19693, "precision_at_20": 0.12741, "precision_at_50": 0.06904, "precision_at_100": 0.03864, "mrr_at_1": 0.4342105263157895, "mrr_at_3": 0.5467836257309939, "mrr_at_5": 0.5698099415204677, "mrr_at_10": 0.584910192147034, "mrr_at_20": 0.5891878685899581, "mrr_at_50": 0.5893003292287347, "mrr_at_100": 0.5893927575043927, "naucs_at_1_max": 0.028773106614816593, "naucs_at_1_std": -0.01227168080572191, "naucs_at_1_diff1": 0.261999801612164, "naucs_at_3_max": 0.06320843001620492, "naucs_at_3_std": 0.02448035777467696, "naucs_at_3_diff1": 0.12347435597829141, "naucs_at_5_max": -0.06768340725423425, "naucs_at_5_std": -0.04326633154478447, "naucs_at_5_diff1": 0.04701540931244815, "naucs_at_10_max": -0.15422204781201998, "naucs_at_10_std": -0.07602648742051556, "naucs_at_10_diff1": -0.013152350769180752, "naucs_at_20_max": -0.21236899343442736, "naucs_at_20_std": -0.07748156777464571, "naucs_at_20_diff1": -0.08927440688507983, "naucs_at_50_max": -0.28244567307891744, "naucs_at_50_std": -0.0843939078809122, "naucs_at_50_diff1": -0.14314843647612213, "naucs_at_100_max": -0.27418980276409255, "naucs_at_100_std": -0.030958516824444608, "naucs_at_100_diff1": -0.14464206913768546}, "vidore/synthetic_axa_filtered_v1.0_multilingual": {"ndcg_at_1": 0.48611, "ndcg_at_3": 0.53828, "ndcg_at_5": 0.55694, "ndcg_at_10": 0.57481, "ndcg_at_20": 0.61199, "ndcg_at_50": 0.67482, "ndcg_at_100": 0.68632, "map_at_1": 0.26775, "map_at_3": 0.35466, "map_at_5": 0.40434, "map_at_10": 0.46115, "map_at_20": 0.49766, "map_at_50": 0.52628, "map_at_100": 0.52994, "recall_at_1": 0.26775, "recall_at_3": 0.42119, "recall_at_5": 0.5044, "recall_at_10": 0.62782, "recall_at_20": 0.73012, "recall_at_50": 0.92657, "recall_at_100": 0.95966, "precision_at_1": 0.48611, "precision_at_3": 0.375, "precision_at_5": 0.33889, "precision_at_10": 0.24306, "precision_at_20": 0.16319, "precision_at_50": 0.08583, "precision_at_100": 0.04597, "mrr_at_1": 0.4722222222222222, "mrr_at_3": 0.613425925925926, "mrr_at_5": 0.6280092592592593, "mrr_at_10": 0.6297453703703704, "mrr_at_20": 0.630516975308642, "mrr_at_50": 0.6336686847103515, "mrr_at_100": 0.6336686847103515, "naucs_at_1_max": 0.1350772742190403, "naucs_at_1_std": 0.21189164235133062, "naucs_at_1_diff1": 0.23576808402436364, "naucs_at_3_max": -0.14592116408987701, "naucs_at_3_std": -0.06152369373183266, "naucs_at_3_diff1": 0.05527260864748933, "naucs_at_5_max": -0.2694957954789358, "naucs_at_5_std": -0.09350786443497999, "naucs_at_5_diff1": -0.035801948159121924, "naucs_at_10_max": -0.32434457813011514, "naucs_at_10_std": -0.06776889009513298, "naucs_at_10_diff1": -0.13289375685583563, "naucs_at_20_max": -0.36729393284463624, "naucs_at_20_std": -0.06309691219473056, "naucs_at_20_diff1": -0.056209061185939185, "naucs_at_50_max": -0.3841553516023212, "naucs_at_50_std": -0.08003710910418253, "naucs_at_50_diff1": -0.014559142800261932, "naucs_at_100_max": -0.41007476497436096, "naucs_at_100_std": -0.11922627536018932, "naucs_at_100_diff1": -0.0352295998971925}, "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {"ndcg_at_1": 0.52656, "ndcg_at_3": 0.54415, "ndcg_at_5": 0.56906, "ndcg_at_10": 0.60613, "ndcg_at_20": 0.63488, "ndcg_at_50": 0.66351, "ndcg_at_100": 0.67465, "map_at_1": 0.32636, "map_at_3": 0.44251, "map_at_5": 0.48102, "map_at_10": 0.51518, "map_at_20": 0.53062, "map_at_50": 0.54127, "map_at_100": 0.54382, "recall_at_1": 0.32636, "recall_at_3": 0.51257, "recall_at_5": 0.60359, "recall_at_10": 0.70975, "recall_at_20": 0.79222, "recall_at_50": 0.88019, "recall_at_100": 0.92155, "precision_at_1": 0.52656, "precision_at_3": 0.3375, "precision_at_5": 0.26031, "precision_at_10": 0.17016, "precision_at_20": 0.10187, "precision_at_50": 0.05019, "precision_at_100": 0.0275, "mrr_at_1": 0.5203125, "mrr_at_3": 0.6247395833333329, "mrr_at_5": 0.6444270833333328, "mrr_at_10": 0.6527430555555551, "mrr_at_20": 0.655260195305425, "mrr_at_50": 0.6563678325752555, "mrr_at_100": 0.656577705561255, "naucs_at_1_max": 0.1551721555124219, "naucs_at_1_std": -0.05688440146293143, "naucs_at_1_diff1": 0.4317530565120342, "naucs_at_3_max": 0.038282811145043734, "naucs_at_3_std": -0.028317403762772073, "naucs_at_3_diff1": 0.013837047091203326, "naucs_at_5_max": -0.004463681612190409, "naucs_at_5_std": 0.0005219442099639731, "naucs_at_5_diff1": -0.08250400663522683, "naucs_at_10_max": -0.05286684420946859, "naucs_at_10_std": 0.02376503508240581, "naucs_at_10_diff1": -0.16928916005470457, "naucs_at_20_max": -0.07243553026697565, "naucs_at_20_std": 0.05563159911892475, "naucs_at_20_diff1": -0.22632687828771358, "naucs_at_50_max": -0.11541055602854267, "naucs_at_50_std": 0.07155125450955375, "naucs_at_50_diff1": -0.2563772186524716, "naucs_at_100_max": -0.14692403911156454, "naucs_at_100_std": 0.05735761014189554, "naucs_at_100_diff1": -0.27055668775388475}, "vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {"ndcg_at_1": 0.58621, "ndcg_at_3": 0.56771, "ndcg_at_5": 0.53511, "ndcg_at_10": 0.52603, "ndcg_at_20": 0.55219, "ndcg_at_50": 0.61728, "ndcg_at_100": 0.66044, "map_at_1": 0.06404, "map_at_3": 0.16423, "map_at_5": 0.21192, "map_at_10": 0.28224, "map_at_20": 0.33909, "map_at_50": 0.39224, "map_at_100": 0.42118, "recall_at_1": 0.06404, "recall_at_3": 0.21385, "recall_at_5": 0.2904, "recall_at_10": 0.42597, "recall_at_20": 0.5651, "recall_at_50": 0.7668, "recall_at_100": 0.89431, "precision_at_1": 0.58621, "precision_at_3": 0.53448, "precision_at_5": 0.47414, "precision_at_10": 0.39397, "precision_at_20": 0.30172, "precision_at_50": 0.18836, "precision_at_100": 0.12491, "mrr_at_1": 0.5818965517241379, "mrr_at_3": 0.6853448275862072, "mrr_at_5": 0.7058189655172417, "mrr_at_10": 0.7122417214012045, "mrr_at_20": 0.7148534586306489, "mrr_at_50": 0.7156355812840557, "mrr_at_100": 0.7156355812840557, "naucs_at_1_max": 0.2151388421635017, "naucs_at_1_std": 0.27934995694361714, "naucs_at_1_diff1": 0.14634867764483128, "naucs_at_3_max": 0.1291661981297352, "naucs_at_3_std": 0.19885094609770032, "naucs_at_3_diff1": -0.003152183148586596, "naucs_at_5_max": 0.13549090646665257, "naucs_at_5_std": 0.20840849049246657, "naucs_at_5_diff1": -0.021327419583879733, "naucs_at_10_max": 0.13994272736992702, "naucs_at_10_std": 0.21763575959477638, "naucs_at_10_diff1": -0.06959345160803267, "naucs_at_20_max": 0.11145998149923564, "naucs_at_20_std": 0.28241587823019054, "naucs_at_20_diff1": -0.08674858979061946, "naucs_at_50_max": 0.04690473599151389, "naucs_at_50_std": 0.2972849287119878, "naucs_at_50_diff1": -0.13032414979520593, "naucs_at_100_max": 0.009502598266557754, "naucs_at_100_std": 0.2585591495803475, "naucs_at_100_diff1": -0.12941355850408606}, "arxivqa_subsampled": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.91676, "ndcg_at_5": 0.92244, "ndcg_at_10": 0.92694, "ndcg_at_20": 0.92951, "ndcg_at_100": 0.93352, "ndcg_at_1000": 0.93352, "map_at_1": 0.88, "map_at_3": 0.908, "map_at_5": 0.9111, "map_at_10": 0.91295, "map_at_20": 0.91368, "map_at_100": 0.91434, "map_at_1000": 0.91434, "recall_at_1": 0.88, "recall_at_3": 0.942, "recall_at_5": 0.956, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.314, "precision_at_5": 0.1912, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.88, "mrr_at_3": 0.9079999999999999, "mrr_at_5": 0.9107999999999998, "mrr_at_10": 0.9130079365079364, "mrr_at_20": 0.9138274518738912, "mrr_at_100": 0.9143900697712918, "mrr_at_1000": 0.9143900697712918, "naucs_at_1_max": 0.782341711740376, "naucs_at_1_std": -0.14517181037225524, "naucs_at_1_diff1": 0.9443207126948777, "naucs_at_3_max": 0.8482887407836682, "naucs_at_3_std": -0.08648056923919158, "naucs_at_3_diff1": 0.9459093982420557, "naucs_at_5_max": 0.9032340208810806, "naucs_at_5_std": 0.05192683133859547, "naucs_at_5_diff1": 0.9524658348187762, "naucs_at_10_max": 0.8853096794273262, "naucs_at_10_std": -0.17223778400249365, "naucs_at_10_diff1": 0.9564270152505474, "naucs_at_20_max": 0.8949579831932757, "naucs_at_20_std": 0.0233893557422963, "naucs_at_20_diff1": 0.9607843137254862, "naucs_at_100_max": 1.0, "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}, "docvqa_subsampled": {"ndcg_at_1": 0.54989, "ndcg_at_3": 0.6272, "ndcg_at_5": 0.64447, "ndcg_at_10": 0.66722, "ndcg_at_20": 0.68113, "ndcg_at_100": 0.69422, "ndcg_at_1000": 0.70437, "map_at_1": 0.54989, "map_at_3": 0.60865, "map_at_5": 0.61818, "map_at_10": 0.62746, "map_at_20": 0.63122, "map_at_100": 0.63287, "map_at_1000": 0.63328, "recall_at_1": 0.54989, "recall_at_3": 0.68071, "recall_at_5": 0.72284, "recall_at_10": 0.79379, "recall_at_20": 0.84922, "recall_at_100": 0.92239, "recall_at_1000": 1.0, "precision_at_1": 0.54989, "precision_at_3": 0.2269, "precision_at_5": 0.14457, "precision_at_10": 0.07938, "precision_at_20": 0.04246, "precision_at_100": 0.00922, "precision_at_1000": 0.001, "mrr_at_1": 0.5587583148558758, "mrr_at_3": 0.6130820399113082, "mrr_at_5": 0.6231707317073171, "mrr_at_10": 0.6318692147960442, "mrr_at_20": 0.6354293062372974, "mrr_at_100": 0.6373227650448284, "mrr_at_1000": 0.637754578561162, "naucs_at_1_max": 0.6626446233829012, "naucs_at_1_std": 0.02058080661271672, "naucs_at_1_diff1": 0.8687412101807956, "naucs_at_3_max": 0.6794601721961877, "naucs_at_3_std": 0.06185764496543819, "naucs_at_3_diff1": 0.7728703329559015, "naucs_at_5_max": 0.6676424400555316, "naucs_at_5_std": 0.12888850524239007, "naucs_at_5_diff1": 0.7580804398339002, "naucs_at_10_max": 0.6389757378756173, "naucs_at_10_std": 0.32256488584252335, "naucs_at_10_diff1": 0.744102835781862, "naucs_at_20_max": 0.6224489347919718, "naucs_at_20_std": 0.5363125392531453, "naucs_at_20_diff1": 0.7175713575781184, "naucs_at_100_max": 0.6404116660832495, "naucs_at_100_std": 0.7094528544475855, "naucs_at_100_diff1": 0.7671064727074209, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "infovqa_subsampled": {"ndcg_at_1": 0.89676, "ndcg_at_3": 0.92965, "ndcg_at_5": 0.93471, "ndcg_at_10": 0.93678, "ndcg_at_20": 0.93888, "ndcg_at_100": 0.94181, "ndcg_at_1000": 0.94261, "map_at_1": 0.89676, "map_at_3": 0.92206, "map_at_5": 0.9249, "map_at_10": 0.92581, "map_at_20": 0.92642, "map_at_100": 0.92679, "map_at_1000": 0.92683, "recall_at_1": 0.89676, "recall_at_3": 0.95142, "recall_at_5": 0.96356, "recall_at_10": 0.96964, "recall_at_20": 0.97773, "recall_at_100": 0.99393, "recall_at_1000": 1.0, "precision_at_1": 0.89676, "precision_at_3": 0.31714, "precision_at_5": 0.19271, "precision_at_10": 0.09696, "precision_at_20": 0.04889, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.8967611336032388, "mrr_at_3": 0.9217273954116058, "mrr_at_5": 0.9245614035087718, "mrr_at_10": 0.9254771544245227, "mrr_at_20": 0.9260782045611765, "mrr_at_100": 0.9264483101466887, "mrr_at_1000": 0.9264798727472631, "naucs_at_1_max": 0.6109225337520844, "naucs_at_1_std": -0.28746226687710974, "naucs_at_1_diff1": 0.9377884442360623, "naucs_at_3_max": 0.7513425815887516, "naucs_at_3_std": -0.1831182034901586, "naucs_at_3_diff1": 0.9448939012384912, "naucs_at_5_max": 0.8499324771117274, "naucs_at_5_std": 0.1674786026708613, "naucs_at_5_diff1": 0.9410364743251854, "naucs_at_10_max": 0.8460392633470242, "naucs_at_10_std": 0.26520856149085326, "naucs_at_10_diff1": 0.9292437691902227, "naucs_at_20_max": 0.8964958869122784, "naucs_at_20_std": 0.4196427770061891, "naucs_at_20_diff1": 0.927259949634811, "naucs_at_100_max": 0.9564661819784259, "naucs_at_100_std": 0.39174816052979483, "naucs_at_100_diff1": 0.9564661819784259, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.88571, "ndcg_at_3": 0.92704, "ndcg_at_5": 0.93749, "ndcg_at_10": 0.942, "ndcg_at_20": 0.94297, "ndcg_at_100": 0.94297, "ndcg_at_1000": 0.94297, "map_at_1": 0.88571, "map_at_3": 0.91667, "map_at_5": 0.92256, "map_at_10": 0.92436, "map_at_20": 0.92465, "map_at_100": 0.92465, "map_at_1000": 0.92465, "recall_at_1": 0.88571, "recall_at_3": 0.95714, "recall_at_5": 0.98214, "recall_at_10": 0.99643, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88571, "precision_at_3": 0.31905, "precision_at_5": 0.19643, "precision_at_10": 0.09964, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.8892857142857142, "mrr_at_3": 0.917261904761905, "mrr_at_5": 0.9240476190476191, "mrr_at_10": 0.9258432539682538, "mrr_at_20": 0.9261408730158731, "mrr_at_100": 0.9261408730158731, "mrr_at_1000": 0.9261408730158731, "naucs_at_1_max": 0.6158489558614146, "naucs_at_1_std": 0.3338573801613662, "naucs_at_1_diff1": 0.8969209776934031, "naucs_at_3_max": 0.8942187986305661, "naucs_at_3_std": 0.6969732337379421, "naucs_at_3_diff1": 0.8620837223778431, "naucs_at_5_max": 0.9738562091503306, "naucs_at_5_std": 0.7899159663865564, "naucs_at_5_diff1": 0.8585434173669502, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.35807656395890114, "naucs_at_10_diff1": 0.8692810457516478, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.68287, "ndcg_at_3": 0.78314, "ndcg_at_5": 0.80681, "ndcg_at_10": 0.82018, "ndcg_at_20": 0.82459, "ndcg_at_100": 0.82908, "ndcg_at_1000": 0.83033, "map_at_1": 0.68287, "map_at_3": 0.75932, "map_at_5": 0.77253, "map_at_10": 0.77817, "map_at_20": 0.77936, "map_at_100": 0.78001, "map_at_1000": 0.78007, "recall_at_1": 0.68287, "recall_at_3": 0.85176, "recall_at_5": 0.90887, "recall_at_10": 0.94957, "recall_at_20": 0.96719, "recall_at_100": 0.99089, "recall_at_1000": 1.0, "precision_at_1": 0.68287, "precision_at_3": 0.28392, "precision_at_5": 0.18177, "precision_at_10": 0.09496, "precision_at_20": 0.04836, "precision_at_100": 0.00991, "precision_at_1000": 0.001, "mrr_at_1": 0.6828675577156743, "mrr_at_3": 0.760024301336574, "mrr_at_5": 0.7729040097205355, "mrr_at_10": 0.7787074003355903, "mrr_at_20": 0.77981048225919, "mrr_at_100": 0.7804686644236308, "mrr_at_1000": 0.780530417746667, "naucs_at_1_max": 0.24316282742534667, "naucs_at_1_std": -0.2387486728504555, "naucs_at_1_diff1": 0.826824088265965, "naucs_at_3_max": 0.2785431946829428, "naucs_at_3_std": -0.21874668661261307, "naucs_at_3_diff1": 0.7258821333794314, "naucs_at_5_max": 0.37017261736106777, "naucs_at_5_std": -0.08964377104816615, "naucs_at_5_diff1": 0.6751762634115527, "naucs_at_10_max": 0.40798144776696565, "naucs_at_10_std": 0.0749134175280517, "naucs_at_10_diff1": 0.6195155652340053, "naucs_at_20_max": 0.3854116148741947, "naucs_at_20_std": 0.13880928341137488, "naucs_at_20_diff1": 0.6123683933054809, "naucs_at_100_max": 0.4016547830791494, "naucs_at_100_std": 0.3369662663486349, "naucs_at_100_diff1": 0.5452087419859556, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.78, "ndcg_at_3": 0.86309, "ndcg_at_5": 0.88375, "ndcg_at_10": 0.88708, "ndcg_at_20": 0.88979, "ndcg_at_100": 0.89155, "ndcg_at_1000": 0.89155, "map_at_1": 0.78, "map_at_3": 0.84333, "map_at_5": 0.85483, "map_at_10": 0.85626, "map_at_20": 0.8571, "map_at_100": 0.8573, "map_at_1000": 0.8573, "recall_at_1": 0.78, "recall_at_3": 0.92, "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": 0.78, "precision_at_3": 0.30667, "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": 0.79, "mrr_at_3": 0.8516666666666667, "mrr_at_5": 0.8636666666666667, "mrr_at_10": 0.8636666666666667, "mrr_at_20": 0.8643809523809525, "mrr_at_100": 0.8645850340136054, "mrr_at_1000": 0.8645850340136054, "naucs_at_1_max": -0.053646775165762495, "naucs_at_1_std": -0.4592664719246995, "naucs_at_1_diff1": 0.8246394955255713, "naucs_at_3_max": 0.3510154061624642, "naucs_at_3_std": 0.11437908496732017, "naucs_at_3_diff1": 0.7782446311858068, "naucs_at_5_max": 0.5169623404917556, "naucs_at_5_std": -0.22362278244631117, "naucs_at_5_diff1": 0.9074074074074108, "naucs_at_10_max": 0.27544351073763346, "naucs_at_10_std": -0.3968253968253954, "naucs_at_10_diff1": 0.861111111111116, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": 0.35807656395891135, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.985, "ndcg_at_5": 0.98931, "ndcg_at_10": 0.98931, "ndcg_at_20": 0.98931, "ndcg_at_100": 0.98931, "ndcg_at_1000": 0.98931, "map_at_1": 0.98, "map_at_3": 0.98333, "map_at_5": 0.98583, "map_at_10": 0.98583, "map_at_20": 0.98583, "map_at_100": 0.98583, "map_at_1000": 0.98583, "recall_at_1": 0.98, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.98, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.98, "mrr_at_3": 0.9833333333333334, "mrr_at_5": 0.9858333333333335, "mrr_at_10": 0.9858333333333335, "mrr_at_20": 0.9858333333333335, "mrr_at_100": 0.9858333333333335, "mrr_at_1000": 0.9858333333333335, "naucs_at_1_max": 0.9346405228758133, "naucs_at_1_std": 0.41433239962652196, "naucs_at_1_diff1": 0.9346405228758133, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 0.8692810457516356, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_energy": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96024, "ndcg_at_5": 0.96454, "ndcg_at_10": 0.96454, "ndcg_at_20": 0.96454, "ndcg_at_100": 0.96658, "ndcg_at_1000": 0.96658, "map_at_1": 0.93, "map_at_3": 0.95333, "map_at_5": 0.95583, "map_at_10": 0.95583, "map_at_20": 0.95583, "map_at_100": 0.95618, "map_at_1000": 0.95618, "recall_at_1": 0.93, "recall_at_3": 0.98, "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": 0.93, "precision_at_3": 0.32667, "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": 0.9633333333333333, "mrr_at_5": 0.9658333333333333, "mrr_at_10": 0.9658333333333333, "mrr_at_20": 0.9658333333333333, "mrr_at_100": 0.9662333333333332, "mrr_at_1000": 0.9662333333333332, "naucs_at_1_max": 0.625917033480058, "naucs_at_1_std": -0.5382819794584509, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8611111111111119, "naucs_at_3_std": -0.2987861811391324, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": -1.1517273576097316, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": -1.1517273576097316, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": -1.1517273576097316, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.96417, "ndcg_at_5": 0.96417, "ndcg_at_10": 0.96417, "ndcg_at_20": 0.96417, "ndcg_at_100": 0.96417, "ndcg_at_1000": 0.96417, "map_at_1": 0.91, "map_at_3": 0.95167, "map_at_5": 0.95167, "map_at_10": 0.95167, "map_at_20": 0.95167, "map_at_100": 0.95167, "map_at_1000": 0.95167, "recall_at_1": 0.91, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.91, "mrr_at_3": 0.9533333333333335, "mrr_at_5": 0.9533333333333335, "mrr_at_10": 0.9533333333333335, "mrr_at_20": 0.9533333333333335, "mrr_at_100": 0.9533333333333335, "mrr_at_1000": 0.9533333333333335, "naucs_at_1_max": 0.8433447453055296, "naucs_at_1_std": 0.24981844589687535, "naucs_at_1_diff1": 0.9564270152505436, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.96, "ndcg_at_3": 0.98393, "ndcg_at_5": 0.98393, "ndcg_at_10": 0.98393, "ndcg_at_20": 0.98393, "ndcg_at_100": 0.98393, "ndcg_at_1000": 0.98393, "map_at_1": 0.96, "map_at_3": 0.97833, "map_at_5": 0.97833, "map_at_10": 0.97833, "map_at_20": 0.97833, "map_at_100": 0.97833, "map_at_1000": 0.97833, "recall_at_1": 0.96, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.96, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.96, "mrr_at_3": 0.9783333333333334, "mrr_at_5": 0.9783333333333334, "mrr_at_10": 0.9783333333333334, "mrr_at_20": 0.9783333333333334, "mrr_at_100": 0.9783333333333334, "mrr_at_1000": 0.9783333333333334, "naucs_at_1_max": 0.7496498599439807, "naucs_at_1_std": -0.19304388422035748, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}