colSmol-500M / results.json
QuentinJG's picture
Update results.json
1aa9325 verified
{"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.44872, "ndcg_at_3": 0.51996, "ndcg_at_5": 0.52232, "ndcg_at_10": 0.57763, "ndcg_at_20": 0.62215, "ndcg_at_50": 0.64665, "ndcg_at_100": 0.65281, "map_at_1": 0.30481, "map_at_3": 0.44263, "map_at_5": 0.46343, "map_at_10": 0.49741, "map_at_20": 0.51592, "map_at_50": 0.52237, "map_at_100": 0.52398, "recall_at_1": 0.30481, "recall_at_3": 0.54615, "recall_at_5": 0.57807, "recall_at_10": 0.71877, "recall_at_20": 0.86108, "recall_at_50": 0.95162, "recall_at_100": 0.97216, "precision_at_1": 0.46154, "precision_at_3": 0.30769, "precision_at_5": 0.21538, "precision_at_10": 0.14038, "precision_at_20": 0.08654, "precision_at_50": 0.04154, "precision_at_100": 0.0225, "mrr_at_1": 0.4423076923076923, "mrr_at_3": 0.5448717948717949, "mrr_at_5": 0.5583333333333333, "mrr_at_10": 0.5792353479853479, "mrr_at_20": 0.5826894961763383, "mrr_at_50": 0.5850171075017945, "mrr_at_100": 0.5850171075017945, "naucs_at_1_max": 0.24419022886817585, "naucs_at_1_std": 0.20913530757518103, "naucs_at_1_diff1": 0.18956477760151022, "naucs_at_3_max": 0.021538678019016246, "naucs_at_3_std": 0.10725557234497837, "naucs_at_3_diff1": -0.04875457481754448, "naucs_at_5_max": 0.014645022986549194, "naucs_at_5_std": 0.044129824597325146, "naucs_at_5_diff1": -0.11174495404454246, "naucs_at_10_max": -0.11448340055341263, "naucs_at_10_std": -0.10902704168644266, "naucs_at_10_diff1": -0.30406392580200137, "naucs_at_20_max": -0.2404702117925663, "naucs_at_20_std": -0.22313364654433895, "naucs_at_20_diff1": -0.31695759183309535, "naucs_at_50_max": -0.31937538050402253, "naucs_at_50_std": -0.2759760110803978, "naucs_at_50_diff1": -0.24888406251943948, "naucs_at_100_max": -0.259723966830786, "naucs_at_100_std": -0.21333793632671658, "naucs_at_100_diff1": -0.23851384327512057},
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.39224,
"ndcg_at_3": 0.37476,
"ndcg_at_5": 0.36148,
"ndcg_at_10": 0.36794,
"ndcg_at_20": 0.40776,
"ndcg_at_50": 0.48463,
"ndcg_at_100": 0.53033,
"map_at_1": 0.04401,
"map_at_3": 0.0993,
"map_at_5": 0.13005,
"map_at_10": 0.17704,
"map_at_20": 0.21969,
"map_at_50": 0.26748,
"map_at_100": 0.29042,
"recall_at_1": 0.04401,
"recall_at_3": 0.13187,
"recall_at_5": 0.192,
"recall_at_10": 0.3039,
"recall_at_20": 0.45606,
"recall_at_50": 0.67169,
"recall_at_100": 0.80877,
"precision_at_1": 0.39224,
"precision_at_3": 0.35632,
"precision_at_5": 0.325,
"precision_at_10": 0.28319,
"precision_at_20": 0.2306,
"precision_at_50": 0.15836,
"precision_at_100": 0.10789,
"mrr_at_1": 0.3922413793103448,
"mrr_at_3": 0.49856321839080464,
"mrr_at_5": 0.5224856321839081,
"mrr_at_10": 0.5373648741105638,
"mrr_at_20": 0.5419287783917268,
"mrr_at_50": 0.5442446092894189,
"mrr_at_100": 0.5445144362126614,
"naucs_at_1_max": -0.09046956137538088,
"naucs_at_1_std": -0.029272928593796467,
"naucs_at_1_diff1": -0.01949330501218432,
"naucs_at_3_max": 0.019777226299839537,
"naucs_at_3_std": 0.05400545367360109,
"naucs_at_3_diff1": -0.07318677988609872,
"naucs_at_5_max": 0.0035718336913224936,
"naucs_at_5_std": 0.027188298117242122,
"naucs_at_5_diff1": -0.07827063058686147,
"naucs_at_10_max": 0.008049347237839717,
"naucs_at_10_std": 0.03145707085203085,
"naucs_at_10_diff1": -0.07144093527570813,
"naucs_at_20_max": -0.003043019306168713,
"naucs_at_20_std": 0.04245224333344333,
"naucs_at_20_diff1": -0.0974791685465552,
"naucs_at_50_max": -0.008203803722240203,
"naucs_at_50_std": 0.004296600594517341,
"naucs_at_50_diff1": -0.08202642486940749,
"naucs_at_100_max": -0.05980969604715223,
"naucs_at_100_std": -0.07215268813689295,
"naucs_at_100_diff1": -0.05108060621594025
},
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.31944,
"ndcg_at_3": 0.36735,
"ndcg_at_5": 0.37705,
"ndcg_at_10": 0.40069,
"ndcg_at_20": 0.43513,
"ndcg_at_50": 0.49148,
"ndcg_at_100": 0.52626,
"map_at_1": 0.1883,
"map_at_3": 0.24848,
"map_at_5": 0.27905,
"map_at_10": 0.30821,
"map_at_20": 0.32807,
"map_at_50": 0.34999,
"map_at_100": 0.35742,
"recall_at_1": 0.1883,
"recall_at_3": 0.30968,
"recall_at_5": 0.38218,
"recall_at_10": 0.47556,
"recall_at_20": 0.56898,
"recall_at_50": 0.72054,
"recall_at_100": 0.86053,
"precision_at_1": 0.31944,
"precision_at_3": 0.25,
"precision_at_5": 0.20278,
"precision_at_10": 0.15,
"precision_at_20": 0.10694,
"precision_at_50": 0.06556,
"precision_at_100": 0.03972,
"mrr_at_1": 0.3194444444444444,
"mrr_at_3": 0.41435185185185186,
"mrr_at_5": 0.44143518518518515,
"mrr_at_10": 0.45383597883597887,
"mrr_at_20": 0.4603018758656014,
"mrr_at_50": 0.46184289024143715,
"mrr_at_100": 0.46279641774158087,
"naucs_at_1_max": 0.25256807521642977,
"naucs_at_1_std": 0.5222755178306032,
"naucs_at_1_diff1": 0.22322127062494312,
"naucs_at_3_max": 0.01027997935801778,
"naucs_at_3_std": 0.26082012822073436,
"naucs_at_3_diff1": 0.18412709220174425,
"naucs_at_5_max": -0.023540307718607937,
"naucs_at_5_std": 0.20590277989329697,
"naucs_at_5_diff1": 0.1394140867278813,
"naucs_at_10_max": -0.1530545347893013,
"naucs_at_10_std": 0.07281002973646711,
"naucs_at_10_diff1": 0.1087825983057161,
"naucs_at_20_max": -0.24948473963259538,
"naucs_at_20_std": -0.052063417282516324,
"naucs_at_20_diff1": 0.04499575326148708,
"naucs_at_50_max": -0.3456643349075049,
"naucs_at_50_std": -0.14962525206807992,
"naucs_at_50_diff1": -0.1032344032141534,
"naucs_at_100_max": -0.41065527201035196,
"naucs_at_100_std": -0.24631195551976134,
"naucs_at_100_diff1": -0.1270004114792933
},
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
"ndcg_at_1": 0.475,
"ndcg_at_3": 0.50399,
"ndcg_at_5": 0.5426,
"ndcg_at_10": 0.56572,
"ndcg_at_20": 0.59334,
"ndcg_at_50": 0.62054,
"ndcg_at_100": 0.63584,
"map_at_1": 0.29844,
"map_at_3": 0.40685,
"map_at_5": 0.44582,
"map_at_10": 0.46931,
"map_at_20": 0.48245,
"map_at_50": 0.49251,
"map_at_100": 0.49533,
"recall_at_1": 0.29844,
"recall_at_3": 0.48891,
"recall_at_5": 0.59575,
"recall_at_10": 0.67602,
"recall_at_20": 0.75242,
"recall_at_50": 0.83386,
"recall_at_100": 0.89769,
"precision_at_1": 0.475,
"precision_at_3": 0.30833,
"precision_at_5": 0.24875,
"precision_at_10": 0.15125,
"precision_at_20": 0.09344,
"precision_at_50": 0.0465,
"precision_at_100": 0.026,
"mrr_at_1": 0.49375,
"mrr_at_3": 0.5958333333333333,
"mrr_at_5": 0.6202083333333334,
"mrr_at_10": 0.6287375992063492,
"mrr_at_20": 0.6311754670660437,
"mrr_at_50": 0.6321625072817313,
"mrr_at_100": 0.6324052960661868,
"naucs_at_1_max": 0.288181487963544,
"naucs_at_1_std": -0.05426311792094572,
"naucs_at_1_diff1": 0.4584585410956644,
"naucs_at_3_max": 0.17191913339472156,
"naucs_at_3_std": -0.020066630109774056,
"naucs_at_3_diff1": 0.09632913618821975,
"naucs_at_5_max": 0.09215639006811155,
"naucs_at_5_std": 0.0012666140953723163,
"naucs_at_5_diff1": -0.06192925755984746,
"naucs_at_10_max": 0.035222797177968716,
"naucs_at_10_std": 0.007929567555839194,
"naucs_at_10_diff1": -0.15828889663289214,
"naucs_at_20_max": -0.013133460063983105,
"naucs_at_20_std": 0.045498580990890984,
"naucs_at_20_diff1": -0.18372934627970697,
"naucs_at_50_max": -0.05231228123361153,
"naucs_at_50_std": 0.08122908162109731,
"naucs_at_50_diff1": -0.18562366170287978,
"naucs_at_100_max": -0.09050436131033135,
"naucs_at_100_std": 0.07301259934095748,
"naucs_at_100_diff1": -0.18245241325838332
},
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
"ndcg_at_1": 0.26316,
"ndcg_at_3": 0.36311,
"ndcg_at_5": 0.39176,
"ndcg_at_10": 0.4454,
"ndcg_at_20": 0.50519,
"ndcg_at_50": 0.55061,
"ndcg_at_100": 0.56466,
"map_at_1": 0.15482,
"map_at_3": 0.27015,
"map_at_5": 0.29589,
"map_at_10": 0.33078,
"map_at_20": 0.36126,
"map_at_50": 0.3824,
"map_at_100": 0.38909,
"recall_at_1": 0.15482,
"recall_at_3": 0.37362,
"recall_at_5": 0.44749,
"recall_at_10": 0.60324,
"recall_at_20": 0.78193,
"recall_at_50": 0.91531,
"recall_at_100": 0.95395,
"precision_at_1": 0.26316,
"precision_at_3": 0.25146,
"precision_at_5": 0.20702,
"precision_at_10": 0.15088,
"precision_at_20": 0.11228,
"precision_at_50": 0.06667,
"precision_at_100": 0.03789,
"mrr_at_1": 0.3157894736842105,
"mrr_at_3": 0.4473684210526316,
"mrr_at_5": 0.46754385964912276,
"mrr_at_10": 0.48647312726260095,
"mrr_at_20": 0.49202021175705385,
"mrr_at_50": 0.49322536427799585,
"mrr_at_100": 0.49322536427799585,
"naucs_at_1_max": -0.05405282049792571,
"naucs_at_1_std": 0.023445855968560407,
"naucs_at_1_diff1": 0.21928586224649782,
"naucs_at_3_max": -0.011620395920182198,
"naucs_at_3_std": 0.08615056848034938,
"naucs_at_3_diff1": -0.15099634717817523,
"naucs_at_5_max": -0.1652385842485644,
"naucs_at_5_std": -0.1076298647113443,
"naucs_at_5_diff1": -0.26773917349447285,
"naucs_at_10_max": -0.20948212317741371,
"naucs_at_10_std": -0.04217452519607505,
"naucs_at_10_diff1": -0.17241123984858953,
"naucs_at_20_max": -0.3585661146008277,
"naucs_at_20_std": -0.11294869002059522,
"naucs_at_20_diff1": -0.27144993416761004,
"naucs_at_50_max": -0.33543648981957763,
"naucs_at_50_std": -0.014416596192293988,
"naucs_at_50_diff1": -0.2783603795291369,
"naucs_at_100_max": -0.3125483341345789,
"naucs_at_100_std": 0.04759656217556336,
"naucs_at_100_diff1": -0.27748680314970026
},
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.3114,
"ndcg_at_3": 0.35716,
"ndcg_at_5": 0.39093,
"ndcg_at_10": 0.45776,
"ndcg_at_20": 0.51442,
"ndcg_at_50": 0.55435,
"ndcg_at_100": 0.57057,
"map_at_1": 0.1635,
"map_at_3": 0.26015,
"map_at_5": 0.29428,
"map_at_10": 0.33703,
"map_at_20": 0.36703,
"map_at_50": 0.38532,
"map_at_100": 0.39218,
"recall_at_1": 0.1635,
"recall_at_3": 0.34212,
"recall_at_5": 0.43294,
"recall_at_10": 0.62713,
"recall_at_20": 0.80024,
"recall_at_50": 0.9216,
"recall_at_100": 0.97058,
"precision_at_1": 0.3114,
"precision_at_3": 0.25,
"precision_at_5": 0.21228,
"precision_at_10": 0.16272,
"precision_at_20": 0.11732,
"precision_at_50": 0.06509,
"precision_at_100": 0.03768,
"mrr_at_1": 0.3201754385964912,
"mrr_at_3": 0.4276315789473684,
"mrr_at_5": 0.45570175438596494,
"mrr_at_10": 0.4726991088833194,
"mrr_at_20": 0.47990133359766324,
"mrr_at_50": 0.4817393870105699,
"mrr_at_100": 0.48179098659777314,
"naucs_at_1_max": -0.043051520891704526,
"naucs_at_1_std": 0.04332255792861466,
"naucs_at_1_diff1": 0.25290228804176196,
"naucs_at_3_max": -0.015276644061893118,
"naucs_at_3_std": 0.05163750744485839,
"naucs_at_3_diff1": 0.040189218663360116,
"naucs_at_5_max": -0.05235721102136031,
"naucs_at_5_std": 0.005811214103192345,
"naucs_at_5_diff1": 0.019471817185607386,
"naucs_at_10_max": -0.15526718391563657,
"naucs_at_10_std": -0.030920730403369213,
"naucs_at_10_diff1": -0.009103205213602163,
"naucs_at_20_max": -0.16361665459184682,
"naucs_at_20_std": -0.006377615107252758,
"naucs_at_20_diff1": -0.11234618830619728,
"naucs_at_50_max": -0.15363708207480695,
"naucs_at_50_std": 0.07280318534401509,
"naucs_at_50_diff1": -0.15710162022601212,
"naucs_at_100_max": -0.1483886076804903,
"naucs_at_100_std": 0.10513102578338192,
"naucs_at_100_diff1": -0.15391945667071522
},
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
"ndcg_at_1": 0.38125,
"ndcg_at_3": 0.39476,
"ndcg_at_5": 0.4206,
"ndcg_at_10": 0.45509,
"ndcg_at_20": 0.48714,
"ndcg_at_50": 0.51836,
"ndcg_at_100": 0.53432,
"map_at_1": 0.24209,
"map_at_3": 0.31985,
"map_at_5": 0.34726,
"map_at_10": 0.3711,
"map_at_20": 0.38475,
"map_at_50": 0.39391,
"map_at_100": 0.39676,
"recall_at_1": 0.24209,
"recall_at_3": 0.38347,
"recall_at_5": 0.45975,
"recall_at_10": 0.56148,
"recall_at_20": 0.65407,
"recall_at_50": 0.75821,
"recall_at_100": 0.82192,
"precision_at_1": 0.38125,
"precision_at_3": 0.23333,
"precision_at_5": 0.18344,
"precision_at_10": 0.12031,
"precision_at_20": 0.07758,
"precision_at_50": 0.04006,
"precision_at_100": 0.02297,
"mrr_at_1": 0.3984375,
"mrr_at_3": 0.47890625,
"mrr_at_5": 0.497734375,
"mrr_at_10": 0.5095529513888889,
"mrr_at_20": 0.5151586381105779,
"mrr_at_50": 0.5174101160297588,
"mrr_at_100": 0.5178826588862087,
"naucs_at_1_max": 0.13899599795432951,
"naucs_at_1_std": 0.0368281555683635,
"naucs_at_1_diff1": 0.5053982968982114,
"naucs_at_3_max": 0.07054641540082532,
"naucs_at_3_std": 0.05000850601457527,
"naucs_at_3_diff1": 0.21532701510229157,
"naucs_at_5_max": 0.01417845342936614,
"naucs_at_5_std": 0.020526726379349457,
"naucs_at_5_diff1": 0.10818783419375576,
"naucs_at_10_max": -0.020678341996715813,
"naucs_at_10_std": 0.02320094009445125,
"naucs_at_10_diff1": 0.006460602129137368,
"naucs_at_20_max": -0.056359581334902174,
"naucs_at_20_std": 0.022492779057438163,
"naucs_at_20_diff1": -0.04495830300371242,
"naucs_at_50_max": -0.08195205931936514,
"naucs_at_50_std": 0.036322084125175555,
"naucs_at_50_diff1": -0.07768679112951372,
"naucs_at_100_max": -0.10382076960662541,
"naucs_at_100_std": 0.017015419651631922,
"naucs_at_100_diff1": -0.08434098316520129
},
"vidore/synthetic_axa_filtered_v1.0": {
"ndcg_at_1": 0.5,
"ndcg_at_3": 0.56184,
"ndcg_at_5": 0.587,
"ndcg_at_10": 0.60148,
"ndcg_at_20": 0.62635,
"ndcg_at_50": 0.67819,
"ndcg_at_100": 0.69787,
"map_at_1": 0.28611,
"map_at_3": 0.36587,
"map_at_5": 0.43319,
"map_at_10": 0.47842,
"map_at_20": 0.50424,
"map_at_50": 0.53292,
"map_at_100": 0.53674,
"recall_at_1": 0.28611,
"recall_at_3": 0.42945,
"recall_at_5": 0.58465,
"recall_at_10": 0.68747,
"recall_at_20": 0.75855,
"recall_at_50": 0.88111,
"recall_at_100": 0.97026,
"precision_at_1": 0.5,
"precision_at_3": 0.40741,
"precision_at_5": 0.33333,
"precision_at_10": 0.23333,
"precision_at_20": 0.15278,
"precision_at_50": 0.08444,
"precision_at_100": 0.045,
"mrr_at_1": 0.5,
"mrr_at_3": 0.6203703703703703,
"mrr_at_5": 0.6481481481481481,
"mrr_at_10": 0.6574074074074074,
"mrr_at_20": 0.6574074074074074,
"mrr_at_50": 0.65854119425548,
"mrr_at_100": 0.65854119425548,
"naucs_at_1_max": 0.42651593299790197,
"naucs_at_1_std": 0.5071500249117564,
"naucs_at_1_diff1": 0.30239223033901025,
"naucs_at_3_max": -0.2757769266874663,
"naucs_at_3_std": -0.205926822886879,
"naucs_at_3_diff1": 0.06908403486928417,
"naucs_at_5_max": -0.3693499917580161,
"naucs_at_5_std": -0.2923131576624302,
"naucs_at_5_diff1": -0.050910460634029486,
"naucs_at_10_max": -0.572254001138292,
"naucs_at_10_std": -0.46716738275931796,
"naucs_at_10_diff1": -0.0735594830753536,
"naucs_at_20_max": -0.6311605275619012,
"naucs_at_20_std": -0.493877197928487,
"naucs_at_20_diff1": -0.08810700944293344,
"naucs_at_50_max": -0.5994854185823998,
"naucs_at_50_std": -0.3880377145984835,
"naucs_at_50_diff1": -0.2337980752344902,
"naucs_at_100_max": -0.5975814841373683,
"naucs_at_100_std": -0.3931594317744619,
"naucs_at_100_diff1": -0.20608009190940405
},
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
"ndcg_at_1": 0.56897,
"ndcg_at_3": 0.5211,
"ndcg_at_5": 0.50298,
"ndcg_at_10": 0.52258,
"ndcg_at_20": 0.55507,
"ndcg_at_50": 0.62454,
"ndcg_at_100": 0.65668,
"map_at_1": 0.06658,
"map_at_3": 0.14611,
"map_at_5": 0.19305,
"map_at_10": 0.27576,
"map_at_20": 0.33378,
"map_at_50": 0.39269,
"map_at_100": 0.41666,
"recall_at_1": 0.06658,
"recall_at_3": 0.18538,
"recall_at_5": 0.26874,
"recall_at_10": 0.44378,
"recall_at_20": 0.5979,
"recall_at_50": 0.79293,
"recall_at_100": 0.89795,
"precision_at_1": 0.56897,
"precision_at_3": 0.48851,
"precision_at_5": 0.44483,
"precision_at_10": 0.3931,
"precision_at_20": 0.30431,
"precision_at_50": 0.19517,
"precision_at_100": 0.12379,
"mrr_at_1": 0.5862068965517241,
"mrr_at_3": 0.675287356321839,
"mrr_at_5": 0.6985632183908046,
"mrr_at_10": 0.7113711001642037,
"mrr_at_20": 0.71252052545156,
"mrr_at_50": 0.7133415435139574,
"mrr_at_100": 0.7133415435139574,
"naucs_at_1_max": -0.40040744598442884,
"naucs_at_1_std": -0.2985416538266988,
"naucs_at_1_diff1": 0.12036209692812928,
"naucs_at_3_max": -0.3377813006714379,
"naucs_at_3_std": -0.2501659993033734,
"naucs_at_3_diff1": -0.03738351632070548,
"naucs_at_5_max": -0.1125861127198914,
"naucs_at_5_std": -0.06443718988916795,
"naucs_at_5_diff1": -0.03965316546372891,
"naucs_at_10_max": -0.009590286755270482,
"naucs_at_10_std": 0.006695305574988969,
"naucs_at_10_diff1": -0.09088428457053505,
"naucs_at_20_max": 0.05383858850417515,
"naucs_at_20_std": 0.05335828984185507,
"naucs_at_20_diff1": -0.12843644755345873,
"naucs_at_50_max": 0.016749758399340033,
"naucs_at_50_std": 0.006620482393505167,
"naucs_at_50_diff1": -0.09393030796852221,
"naucs_at_100_max": -0.069387597095011,
"naucs_at_100_std": -0.09518999664037518,
"naucs_at_100_diff1": -0.05750748161503184
}, "./data_dir/eval_vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.67, "ndcg_at_3": 0.73664, "ndcg_at_5": 0.74886, "ndcg_at_10": 0.76608, "ndcg_at_20": 0.77508, "ndcg_at_50": 0.78465, "ndcg_at_100": 0.78928, "map_at_1": 0.67, "map_at_3": 0.71967, "map_at_5": 0.72637, "map_at_10": 0.73332, "map_at_20": 0.73575, "map_at_50": 0.7373, "map_at_100": 0.73774, "recall_at_1": 0.67, "recall_at_3": 0.786, "recall_at_5": 0.816, "recall_at_10": 0.87, "recall_at_20": 0.906, "recall_at_50": 0.954, "recall_at_100": 0.982, "precision_at_1": 0.67, "precision_at_3": 0.262, "precision_at_5": 0.1632, "precision_at_10": 0.087, "precision_at_20": 0.0453, "precision_at_50": 0.01908, "precision_at_100": 0.00982, "mrr_at_1": 0.674, "mrr_at_3": 0.723, "mrr_at_5": 0.7291, "mrr_at_10": 0.7366095238095238, "mrr_at_20": 0.7391611043325439, "mrr_at_50": 0.7409444251953623, "mrr_at_100": 0.7413271325461593, "naucs_at_1_max": 0.5444803710788707, "naucs_at_1_std": -0.09109715427197845, "naucs_at_1_diff1": 0.9253203771732317, "naucs_at_3_max": 0.5919376009932287, "naucs_at_3_std": -0.04496538390458086, "naucs_at_3_diff1": 0.8649522103597137, "naucs_at_5_max": 0.6306070025471655, "naucs_at_5_std": 0.001678323187842219, "naucs_at_5_diff1": 0.8645469067046583, "naucs_at_10_max": 0.6801229356439317, "naucs_at_10_std": 0.03928756572613559, "naucs_at_10_diff1": 0.8395171443382958, "naucs_at_20_max": 0.7005979696843283, "naucs_at_20_std": 0.04557283906470355, "naucs_at_20_diff1": 0.8023322804299033, "naucs_at_50_max": 0.7126212803962136, "naucs_at_50_std": -0.09452766613891975, "naucs_at_50_diff1": 0.8312223440100683, "naucs_at_100_max": 0.85968461458657, "naucs_at_100_std": -0.10281149496835222, "naucs_at_100_diff1": 0.896514161220045}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.50554, "ndcg_at_3": 0.55831, "ndcg_at_5": 0.58055, "ndcg_at_10": 0.60677, "ndcg_at_20": 0.62553, "ndcg_at_50": 0.63388, "ndcg_at_100": 0.64093, "map_at_1": 0.50554, "map_at_3": 0.54582, "map_at_5": 0.55835, "map_at_10": 0.569, "map_at_20": 0.5743, "map_at_50": 0.57564, "map_at_100": 0.57622, "recall_at_1": 0.50554, "recall_at_3": 0.59424, "recall_at_5": 0.64745, "recall_at_10": 0.72949, "recall_at_20": 0.80266, "recall_at_50": 0.84479, "recall_at_100": 0.88914, "precision_at_1": 0.50554, "precision_at_3": 0.19808, "precision_at_5": 0.12949, "precision_at_10": 0.07295, "precision_at_20": 0.04013, "precision_at_50": 0.0169, "precision_at_100": 0.00889, "mrr_at_1": 0.5033259423503326, "mrr_at_3": 0.5476718403547672, "mrr_at_5": 0.5574279379157429, "mrr_at_10": 0.5684528208918452, "mrr_at_20": 0.573404311645784, "mrr_at_50": 0.5749334030411379, "mrr_at_100": 0.575603354450426, "naucs_at_1_max": 0.2625490776539377, "naucs_at_1_std": 0.3310850636640096, "naucs_at_1_diff1": 0.8285865433933254, "naucs_at_3_max": 0.18953190824386826, "naucs_at_3_std": 0.38629715857674524, "naucs_at_3_diff1": 0.769918430991528, "naucs_at_5_max": 0.14915660669648698, "naucs_at_5_std": 0.39060413735358934, "naucs_at_5_diff1": 0.7373299633405666, "naucs_at_10_max": 0.008734548704545675, "naucs_at_10_std": 0.5053066426323437, "naucs_at_10_diff1": 0.7260812769949216, "naucs_at_20_max": -0.1110192872274276, "naucs_at_20_std": 0.6213072109985829, "naucs_at_20_diff1": 0.6964830158995551, "naucs_at_50_max": -0.16049662657697744, "naucs_at_50_std": 0.7364897688356142, "naucs_at_50_diff1": 0.7182771454403309, "naucs_at_100_max": -0.19221684927376187, "naucs_at_100_std": 0.8505984612548488, "naucs_at_100_diff1": 0.7419613287710981}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.93417, "ndcg_at_5": 0.93847, "ndcg_at_10": 0.93847, "ndcg_at_20": 0.93847, "ndcg_at_50": 0.94063, "ndcg_at_100": 0.9422, "map_at_1": 0.88, "map_at_3": 0.92167, "map_at_5": 0.92417, "map_at_10": 0.92417, "map_at_20": 0.92417, "map_at_50": 0.92458, "map_at_100": 0.92471, "recall_at_1": 0.88, "recall_at_3": 0.97, "recall_at_5": 0.98, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.32333, "precision_at_5": 0.196, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.89, "mrr_at_3": 0.93, "mrr_at_5": 0.9325, "mrr_at_10": 0.9325, "mrr_at_20": 0.9325, "mrr_at_50": 0.9329166666666667, "mrr_at_100": 0.9330448717948718, "naucs_at_1_max": 0.36497772828507796, "naucs_at_1_std": -0.272231944002546, "naucs_at_1_diff1": 0.9777282850779508, "naucs_at_3_max": 0.693432928727046, "naucs_at_3_std": -0.15452847805789072, "naucs_at_3_diff1": 0.9564270152505466, "naucs_at_5_max": 0.6790382819794609, "naucs_at_5_std": -0.5929038281979465, "naucs_at_5_diff1": 0.9346405228758136, "naucs_at_10_max": 0.6790382819794609, "naucs_at_10_std": -0.5929038281979465, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.6790382819794609, "naucs_at_20_std": -0.5929038281979465, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.554154995331464, "naucs_at_50_diff1": 0.8692810457516374, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tatdqa_test": {"ndcg_at_1": 0.64581, "ndcg_at_3": 0.73981, "ndcg_at_5": 0.7668, "ndcg_at_10": 0.787, "ndcg_at_20": 0.79364, "ndcg_at_50": 0.79698, "ndcg_at_100": 0.79864, "map_at_1": 0.64581, "map_at_3": 0.71648, "map_at_5": 0.73158, "map_at_10": 0.74001, "map_at_20": 0.74185, "map_at_50": 0.74242, "map_at_100": 0.74256, "recall_at_1": 0.64581, "recall_at_3": 0.80741, "recall_at_5": 0.87242, "recall_at_10": 0.93439, "recall_at_20": 0.96051, "recall_at_50": 0.97691, "recall_at_100": 0.98724, "precision_at_1": 0.64581, "precision_at_3": 0.26914, "precision_at_5": 0.17448, "precision_at_10": 0.09344, "precision_at_20": 0.04803, "precision_at_50": 0.01954, "precision_at_100": 0.00987, "mrr_at_1": 0.6433778857837181, "mrr_at_3": 0.7150668286755771, "mrr_at_5": 0.7304981773997571, "mrr_at_10": 0.7387049412717699, "mrr_at_20": 0.7404579555191415, "mrr_at_50": 0.7410660643728302, "mrr_at_100": 0.7412038533898355, "naucs_at_1_max": 0.13431737923823708, "naucs_at_1_std": -0.3067075571650227, "naucs_at_1_diff1": 0.8067592167032371, "naucs_at_3_max": 0.18727434840097998, "naucs_at_3_std": -0.27607320609227726, "naucs_at_3_diff1": 0.6950163190033429, "naucs_at_5_max": 0.2109382115959134, "naucs_at_5_std": -0.22542299636024854, "naucs_at_5_diff1": 0.6560772753501689, "naucs_at_10_max": 0.3049581820340452, "naucs_at_10_std": 0.10695854160572203, "naucs_at_10_diff1": 0.5979569201987198, "naucs_at_20_max": 0.3524427577390326, "naucs_at_20_std": 0.2838037847480218, "naucs_at_20_diff1": 0.5748977828288308, "naucs_at_50_max": 0.39877531195470334, "naucs_at_50_std": 0.47760692333540594, "naucs_at_50_diff1": 0.48464495157589027, "naucs_at_100_max": 0.3531041790707774, "naucs_at_100_std": 0.4303621036969795, "naucs_at_100_diff1": 0.42655633089874984}, "./data_dir/eval_vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.80769, "ndcg_at_3": 0.86119, "ndcg_at_5": 0.86799, "ndcg_at_10": 0.87508, "ndcg_at_20": 0.8788, "ndcg_at_50": 0.88321, "ndcg_at_100": 0.88418, "map_at_1": 0.80769, "map_at_3": 0.84818, "map_at_5": 0.85202, "map_at_10": 0.85488, "map_at_20": 0.85598, "map_at_50": 0.85668, "map_at_100": 0.85677, "recall_at_1": 0.80769, "recall_at_3": 0.89879, "recall_at_5": 0.91498, "recall_at_10": 0.93725, "recall_at_20": 0.95142, "recall_at_50": 0.97368, "recall_at_100": 0.97976, "precision_at_1": 0.80769, "precision_at_3": 0.2996, "precision_at_5": 0.183, "precision_at_10": 0.09372, "precision_at_20": 0.04757, "precision_at_50": 0.01947, "precision_at_100": 0.0098, "mrr_at_1": 0.8117408906882592, "mrr_at_3": 0.8488529014844804, "mrr_at_5": 0.8532051282051283, "mrr_at_10": 0.8560359231411864, "mrr_at_20": 0.8570996255206782, "mrr_at_50": 0.8577900744824616, "mrr_at_100": 0.8578711146551276, "naucs_at_1_max": 0.5181292739994149, "naucs_at_1_std": -0.12587128411667012, "naucs_at_1_diff1": 0.9118360487145103, "naucs_at_3_max": 0.5428075702339784, "naucs_at_3_std": -0.133844833983956, "naucs_at_3_diff1": 0.8487810208609975, "naucs_at_5_max": 0.570342039887235, "naucs_at_5_std": -0.1629741497251075, "naucs_at_5_diff1": 0.8403883247563, "naucs_at_10_max": 0.7076634965650749, "naucs_at_10_std": 0.14379204929117678, "naucs_at_10_diff1": 0.8238016143503649, "naucs_at_20_max": 0.8079586920995654, "naucs_at_20_std": 0.21002182843283598, "naucs_at_20_diff1": 0.825877668290874, "naucs_at_50_max": 0.8233669400006994, "naucs_at_50_std": 0.18166589601039382, "naucs_at_50_diff1": 0.8057881231371927, "naucs_at_100_max": 0.8922124708224929, "naucs_at_100_std": 0.6406492513828425, "naucs_at_100_diff1": 0.7867049962977823}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.97893, "ndcg_at_5": 0.97893, "ndcg_at_10": 0.97893, "ndcg_at_20": 0.97893, "ndcg_at_50": 0.97893, "ndcg_at_100": 0.97893, "map_at_1": 0.95, "map_at_3": 0.97167, "map_at_5": 0.97167, "map_at_10": 0.97167, "map_at_20": 0.97167, "map_at_50": 0.97167, "map_at_100": 0.97167, "recall_at_1": 0.95, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.95, "mrr_at_3": 0.9716666666666667, "mrr_at_5": 0.9716666666666667, "mrr_at_10": 0.9716666666666667, "mrr_at_20": 0.9716666666666667, "mrr_at_50": 0.9716666666666667, "mrr_at_100": 0.9716666666666667, "naucs_at_1_max": 0.5808590102707767, "naucs_at_1_std": -0.1164332399626522, "naucs_at_1_diff1": 0.9477124183006508, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/tabfquad_test_subsampled": {"ndcg_at_1": 0.68929, "ndcg_at_3": 0.74413, "ndcg_at_5": 0.75167, "ndcg_at_10": 0.77118, "ndcg_at_20": 0.78112, "ndcg_at_50": 0.79873, "ndcg_at_100": 0.80054, "map_at_1": 0.68929, "map_at_3": 0.73095, "map_at_5": 0.73524, "map_at_10": 0.74323, "map_at_20": 0.74596, "map_at_50": 0.74876, "map_at_100": 0.74894, "recall_at_1": 0.68929, "recall_at_3": 0.78214, "recall_at_5": 0.8, "recall_at_10": 0.86071, "recall_at_20": 0.9, "recall_at_50": 0.98929, "recall_at_100": 1.0, "precision_at_1": 0.68929, "precision_at_3": 0.26071, "precision_at_5": 0.16, "precision_at_10": 0.08607, "precision_at_20": 0.045, "precision_at_50": 0.01979, "precision_at_100": 0.01, "mrr_at_1": 0.6857142857142857, "mrr_at_3": 0.7273809523809524, "mrr_at_5": 0.7332738095238095, "mrr_at_10": 0.7413988095238095, "mrr_at_20": 0.7440813863424158, "mrr_at_50": 0.7468722884841633, "mrr_at_100": 0.7470525854039923, "naucs_at_1_max": 0.2870009874897007, "naucs_at_1_std": 0.04204064432130546, "naucs_at_1_diff1": 0.7891552245752849, "naucs_at_3_max": 0.29717890310145373, "naucs_at_3_std": 0.10697806369788107, "naucs_at_3_diff1": 0.6949610753710974, "naucs_at_5_max": 0.2523369487655202, "naucs_at_5_std": 0.06743256743256658, "naucs_at_5_diff1": 0.6558976737548161, "naucs_at_10_max": 0.24856446841830593, "naucs_at_10_std": 0.02682144721469618, "naucs_at_10_diff1": 0.6389296278803848, "naucs_at_20_max": 0.16003067893824288, "naucs_at_20_std": -0.11236161131119002, "naucs_at_20_diff1": 0.601724022942509, "naucs_at_50_max": 0.8202614379084879, "naucs_at_50_std": 0.7424525365701868, "naucs_at_50_diff1": 0.7587924058512231, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.94178, "ndcg_at_5": 0.94609, "ndcg_at_10": 0.94609, "ndcg_at_20": 0.94609, "ndcg_at_50": 0.94609, "ndcg_at_100": 0.94609, "map_at_1": 0.87, "map_at_3": 0.925, "map_at_5": 0.9275, "map_at_10": 0.9275, "map_at_20": 0.9275, "map_at_50": 0.9275, "map_at_100": 0.9275, "recall_at_1": 0.87, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.89, "mrr_at_3": 0.935, "mrr_at_5": 0.9375, "mrr_at_10": 0.9375, "mrr_at_20": 0.9375, "mrr_at_50": 0.9375, "mrr_at_100": 0.9375, "naucs_at_1_max": 0.5187736058653628, "naucs_at_1_std": 0.22202473524402008, "naucs_at_1_diff1": 0.7872694956676297, "naucs_at_3_max": 0.5541549953314585, "naucs_at_3_std": 0.35807656395889226, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/shiftproject_test": {"ndcg_at_1": 0.48, "ndcg_at_3": 0.62226, "ndcg_at_5": 0.66313, "ndcg_at_10": 0.70227, "ndcg_at_20": 0.70762, "ndcg_at_50": 0.71377, "ndcg_at_100": 0.71377, "map_at_1": 0.48, "map_at_3": 0.58833, "map_at_5": 0.61083, "map_at_10": 0.62718, "map_at_20": 0.6288, "map_at_50": 0.62987, "map_at_100": 0.62987, "recall_at_1": 0.48, "recall_at_3": 0.72, "recall_at_5": 0.82, "recall_at_10": 0.94, "recall_at_20": 0.96, "recall_at_50": 0.99, "recall_at_100": 0.99, "precision_at_1": 0.48, "precision_at_3": 0.24, "precision_at_5": 0.164, "precision_at_10": 0.094, "precision_at_20": 0.048, "precision_at_50": 0.0198, "precision_at_100": 0.0099, "mrr_at_1": 0.51, "mrr_at_3": 0.6133333333333334, "mrr_at_5": 0.6333333333333333, "mrr_at_10": 0.6481230158730159, "mrr_at_20": 0.6503713924963925, "mrr_at_50": 0.6509864903528697, "mrr_at_100": 0.6509864903528697, "naucs_at_1_max": 0.01784958187784493, "naucs_at_1_std": -0.21715888641896902, "naucs_at_1_diff1": 0.7087302847464805, "naucs_at_3_max": 0.08859890109890145, "naucs_at_3_std": -0.28323412698412614, "naucs_at_3_diff1": 0.4830586080586077, "naucs_at_5_max": 0.10656459962550972, "naucs_at_5_std": -0.10389360061680472, "naucs_at_5_diff1": 0.40610199361163074, "naucs_at_10_max": -0.18744164332399568, "naucs_at_10_std": -0.024042950513536908, "naucs_at_10_diff1": 0.6868969810146294, "naucs_at_20_max": -0.22980859010270466, "naucs_at_20_std": -0.1562791783379993, "naucs_at_20_diff1": 0.7112511671335194, "naucs_at_50_max": -0.17133520074697067, "naucs_at_50_std": 0.12278244631185525, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": -0.17133520074697067, "naucs_at_100_std": 0.12278244631185525, "naucs_at_100_diff1": 1.0}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.98762, "ndcg_at_5": 0.98762, "ndcg_at_10": 0.98762, "ndcg_at_20": 0.98762, "ndcg_at_50": 0.98762, "ndcg_at_100": 0.98762, "map_at_1": 0.97, "map_at_3": 0.98333, "map_at_5": 0.98333, "map_at_10": 0.98333, "map_at_20": 0.98333, "map_at_50": 0.98333, "map_at_100": 0.98333, "recall_at_1": 0.97, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_50": 1.0, "recall_at_100": 1.0, "precision_at_1": 0.97, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.97, "mrr_at_3": 0.9833333333333333, "mrr_at_5": 0.9833333333333333, "mrr_at_10": 0.9833333333333333, "mrr_at_20": 0.9833333333333333, "mrr_at_50": 0.9833333333333333, "mrr_at_100": 0.9833333333333333, "naucs_at_1_max": 0.912854030501093, "naucs_at_1_std": 0.6934329287270453, "naucs_at_1_diff1": 0.912854030501093, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": NaN, "naucs_at_50_std": NaN, "naucs_at_50_diff1": NaN, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}}