{"arxivqa_test_subsampled": {"ndcg_at_1": 0.872, "ndcg_at_3": 0.90624, "ndcg_at_5": 0.91605, "ndcg_at_10": 0.91983, "ndcg_at_20": 0.92472, "ndcg_at_100": 0.92704, "ndcg_at_1000": 0.9273, "map_at_1": 0.872, "map_at_3": 0.898, "map_at_5": 0.9034, "map_at_10": 0.90491, "map_at_20": 0.90617, "map_at_100": 0.90652, "map_at_1000": 0.90653, "recall_at_1": 0.872, "recall_at_3": 0.93, "recall_at_5": 0.954, "recall_at_10": 0.966, "recall_at_20": 0.986, "recall_at_100": 0.998, "recall_at_1000": 1.0, "precision_at_1": 0.872, "precision_at_3": 0.31, "precision_at_5": 0.1908, "precision_at_10": 0.0966, "precision_at_20": 0.0493, "precision_at_100": 0.00998, "precision_at_1000": 0.001, "mrr_at_1": 0.872, "mrr_at_3": 0.8983333333333332, "mrr_at_5": 0.9027333333333332, "mrr_at_10": 0.9050246031746031, "mrr_at_20": 0.9061947356135435, "mrr_at_100": 0.9066581246088399, "mrr_at_1000": 0.906667833346704, "naucs_at_1_max": 0.78117866154031, "naucs_at_1_std": -0.2690586327045542, "naucs_at_1_diff1": 0.941427369938724, "naucs_at_3_max": 0.8743497398959608, "naucs_at_3_std": -0.20349473122582729, "naucs_at_3_diff1": 0.9191009737228247, "naucs_at_5_max": 0.9239840863881768, "naucs_at_5_std": -0.0771120042219855, "naucs_at_5_diff1": 0.9287541103397898, "naucs_at_10_max": 0.9288735101883935, "naucs_at_10_std": 0.0749437029713847, "naucs_at_10_diff1": 0.9189872027242296, "naucs_at_20_max": 0.9229691876750666, "naucs_at_20_std": -0.051420568227293066, "naucs_at_20_diff1": 0.8802854475123367, "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_test_subsampled": {"ndcg_at_1": 0.55876, "ndcg_at_3": 0.62937, "ndcg_at_5": 0.65332, "ndcg_at_10": 0.67583, "ndcg_at_20": 0.69045, "ndcg_at_100": 0.70636, "ndcg_at_1000": 0.71315, "map_at_1": 0.55876, "map_at_3": 0.61234, "map_at_5": 0.62576, "map_at_10": 0.63523, "map_at_20": 0.63925, "map_at_100": 0.64139, "map_at_1000": 0.64168, "recall_at_1": 0.55876, "recall_at_3": 0.67849, "recall_at_5": 0.73614, "recall_at_10": 0.80488, "recall_at_20": 0.86253, "recall_at_100": 0.949, "recall_at_1000": 1.0, "precision_at_1": 0.55876, "precision_at_3": 0.22616, "precision_at_5": 0.14723, "precision_at_10": 0.08049, "precision_at_20": 0.04313, "precision_at_100": 0.00949, "precision_at_1000": 0.001, "mrr_at_1": 0.5521064301552107, "mrr_at_3": 0.6104951958610497, "mrr_at_5": 0.6230229120473023, "mrr_at_10": 0.6323980220321683, "mrr_at_20": 0.636301287429156, "mrr_at_100": 0.6385718084996487, "mrr_at_1000": 0.6388595018654679, "naucs_at_1_max": 0.47898015796346216, "naucs_at_1_std": -0.31401905806891717, "naucs_at_1_diff1": 0.8490375522154754, "naucs_at_3_max": 0.4361723535093254, "naucs_at_3_std": -0.40210007216450594, "naucs_at_3_diff1": 0.7812770594092832, "naucs_at_5_max": 0.43864302105213626, "naucs_at_5_std": -0.36794334667406037, "naucs_at_5_diff1": 0.7527735797331181, "naucs_at_10_max": 0.38646639530703636, "naucs_at_10_std": -0.2805750831877236, "naucs_at_10_diff1": 0.7334243393537739, "naucs_at_20_max": 0.3838054648809118, "naucs_at_20_std": -0.1310605806976941, "naucs_at_20_diff1": 0.7259684756503129, "naucs_at_100_max": 0.502904125951142, "naucs_at_100_std": 0.3923565469987927, "naucs_at_100_diff1": 0.6479405708342569, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "infovqa_test_subsampled": {"ndcg_at_1": 0.90486, "ndcg_at_3": 0.93488, "ndcg_at_5": 0.93802, "ndcg_at_10": 0.94127, "ndcg_at_20": 0.94329, "ndcg_at_100": 0.94405, "ndcg_at_1000": 0.94565, "map_at_1": 0.90486, "map_at_3": 0.92713, "map_at_5": 0.92874, "map_at_10": 0.93007, "map_at_20": 0.93061, "map_at_100": 0.93071, "map_at_1000": 0.93078, "recall_at_1": 0.90486, "recall_at_3": 0.95749, "recall_at_5": 0.96559, "recall_at_10": 0.97571, "recall_at_20": 0.98381, "recall_at_100": 0.98785, "recall_at_1000": 1.0, "precision_at_1": 0.90486, "precision_at_3": 0.31916, "precision_at_5": 0.19312, "precision_at_10": 0.09757, "precision_at_20": 0.04919, "precision_at_100": 0.00988, "precision_at_1000": 0.001, "mrr_at_1": 0.9068825910931174, "mrr_at_3": 0.9281376518218624, "mrr_at_5": 0.9294534412955465, "mrr_at_10": 0.9309475612107192, "mrr_at_20": 0.9316585461322304, "mrr_at_100": 0.9317688817880067, "mrr_at_1000": 0.9318324180507253, "naucs_at_1_max": 0.6334629679799084, "naucs_at_1_std": -0.24301437009609028, "naucs_at_1_diff1": 0.9482237165679124, "naucs_at_3_max": 0.6233629697463214, "naucs_at_3_std": -0.19939440668055744, "naucs_at_3_diff1": 0.9416662583110353, "naucs_at_5_max": 0.6990158901841317, "naucs_at_5_std": -0.18602616298839614, "naucs_at_5_diff1": 0.9279406720312746, "naucs_at_10_max": 0.7958520970778115, "naucs_at_10_std": 0.2662975621020652, "naucs_at_10_diff1": 0.9319439680295455, "naucs_at_20_max": 0.8189249320515473, "naucs_at_20_std": 0.42232371311537836, "naucs_at_20_diff1": 0.9489579760221489, "naucs_at_100_max": 0.7585665760687373, "naucs_at_100_std": 0.32581599582508164, "naucs_at_100_diff1": 0.9537108770403242, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_test_subsampled": {"ndcg_at_1": 0.93214, "ndcg_at_3": 0.96144, "ndcg_at_5": 0.96743, "ndcg_at_10": 0.96856, "ndcg_at_20": 0.9695, "ndcg_at_100": 0.9695, "ndcg_at_1000": 0.9695, "map_at_1": 0.93214, "map_at_3": 0.95536, "map_at_5": 0.95875, "map_at_10": 0.9592, "map_at_20": 0.95947, "map_at_100": 0.95947, "map_at_1000": 0.95947, "recall_at_1": 0.93214, "recall_at_3": 0.97857, "recall_at_5": 0.99286, "recall_at_10": 0.99643, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.93214, "precision_at_3": 0.32619, "precision_at_5": 0.19857, "precision_at_10": 0.09964, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.9357142857142857, "mrr_at_3": 0.956547619047619, "mrr_at_5": 0.9592261904761904, "mrr_at_10": 0.9602465986394557, "mrr_at_20": 0.960521323914181, "mrr_at_100": 0.960521323914181, "mrr_at_1000": 0.960521323914181, "naucs_at_1_max": 0.4931937687355659, "naucs_at_1_std": 0.3008255933952535, "naucs_at_1_diff1": 0.9034350582338209, "naucs_at_3_max": 0.7394179894179925, "naucs_at_3_std": 0.6195922813569864, "naucs_at_3_diff1": 0.9564270152505565, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.9346405228758269, "naucs_at_5_diff1": 0.9346405228758269, "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": 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_test": {"ndcg_at_1": 0.69259, "ndcg_at_3": 0.78713, "ndcg_at_5": 0.81014, "ndcg_at_10": 0.82209, "ndcg_at_20": 0.82758, "ndcg_at_100": 0.83311, "ndcg_at_1000": 0.83385, "map_at_1": 0.69259, "map_at_3": 0.76468, "map_at_5": 0.77744, "map_at_10": 0.78247, "map_at_20": 0.78404, "map_at_100": 0.78484, "map_at_1000": 0.78488, "recall_at_1": 0.69259, "recall_at_3": 0.85176, "recall_at_5": 0.90765, "recall_at_10": 0.94411, "recall_at_20": 0.96537, "recall_at_100": 0.99453, "recall_at_1000": 1.0, "precision_at_1": 0.69259, "precision_at_3": 0.28392, "precision_at_5": 0.18153, "precision_at_10": 0.09441, "precision_at_20": 0.04827, "precision_at_100": 0.00995, "precision_at_1000": 0.001, "mrr_at_1": 0.6931956257594167, "mrr_at_3": 0.764985824220332, "mrr_at_5": 0.777257999189956, "mrr_at_10": 0.78269253023202, "mrr_at_20": 0.7842680275688904, "mrr_at_100": 0.7850725589609645, "mrr_at_1000": 0.7851141705086578, "naucs_at_1_max": 0.20398371414783106, "naucs_at_1_std": -0.24034782425231832, "naucs_at_1_diff1": 0.8063676387904894, "naucs_at_3_max": 0.2396636623614596, "naucs_at_3_std": -0.2340385941277604, "naucs_at_3_diff1": 0.7193674186229371, "naucs_at_5_max": 0.25725555975625924, "naucs_at_5_std": -0.12367180254322775, "naucs_at_5_diff1": 0.6723018243887673, "naucs_at_10_max": 0.3394170156946574, "naucs_at_10_std": 0.031367481157820884, "naucs_at_10_diff1": 0.6416885995392956, "naucs_at_20_max": 0.47858979115790484, "naucs_at_20_std": 0.23759528593663565, "naucs_at_20_diff1": 0.6638387312367023, "naucs_at_100_max": 0.4269541256283218, "naucs_at_100_std": 0.5057660562646209, "naucs_at_100_diff1": 0.6411286045870721, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shiftproject_test": {"ndcg_at_1": 0.75, "ndcg_at_3": 0.87595, "ndcg_at_5": 0.88026, "ndcg_at_10": 0.88341, "ndcg_at_20": 0.8862, "ndcg_at_100": 0.88791, "ndcg_at_1000": 0.88791, "map_at_1": 0.75, "map_at_3": 0.84667, "map_at_5": 0.84917, "map_at_10": 0.85042, "map_at_20": 0.85133, "map_at_100": 0.8515, "map_at_1000": 0.8515, "recall_at_1": 0.75, "recall_at_3": 0.96, "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": 0.75, "precision_at_3": 0.32, "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": 0.78, "mrr_at_3": 0.865, "mrr_at_5": 0.8675, "mrr_at_10": 0.8675, "mrr_at_20": 0.8684090909090909, "mrr_at_100": 0.8685876623376625, "mrr_at_1000": 0.8685876623376625, "naucs_at_1_max": 0.03667189952904228, "naucs_at_1_std": -0.4420303506017796, "naucs_at_1_diff1": 0.8742019884877025, "naucs_at_3_max": 0.5875350140056042, "naucs_at_3_std": -0.01447245564892935, "naucs_at_3_diff1": 0.7280578898225921, "naucs_at_5_max": 0.4936196700902597, "naucs_at_5_std": -0.06022408963585601, "naucs_at_5_diff1": 0.8513849984438217, "naucs_at_10_max": 0.24042950513538955, "naucs_at_10_std": -0.004668534080301362, "naucs_at_10_diff1": 0.7770774976657324, "naucs_at_20_max": 0.35807656395891135, "naucs_at_20_std": 0.5541549953314738, "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_artificial_intelligence_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.99262, "ndcg_at_5": 0.99262, "ndcg_at_10": 0.99262, "ndcg_at_20": 0.99262, "ndcg_at_100": 0.99262, "ndcg_at_1000": 0.99262, "map_at_1": 0.98, "map_at_3": 0.99, "map_at_5": 0.99, "map_at_10": 0.99, "map_at_20": 0.99, "map_at_100": 0.99, "map_at_1000": 0.99, "recall_at_1": 0.98, "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": 0.98, "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": 0.98, "mrr_at_3": 0.99, "mrr_at_5": 0.99, "mrr_at_10": 0.99, "mrr_at_20": 0.99, "mrr_at_100": 0.99, "mrr_at_1000": 0.99, "naucs_at_1_max": 0.71171802054155, "naucs_at_1_std": -0.367413632119516, "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}, "syntheticDocQA_energy_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.95393, "ndcg_at_5": 0.95393, "ndcg_at_10": 0.95682, "ndcg_at_20": 0.95682, "ndcg_at_100": 0.96104, "ndcg_at_1000": 0.96104, "map_at_1": 0.93, "map_at_3": 0.94833, "map_at_5": 0.94833, "map_at_10": 0.94933, "map_at_20": 0.94933, "map_at_100": 0.95012, "map_at_1000": 0.95012, "recall_at_1": 0.93, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.93, "mrr_at_3": 0.9483333333333333, "mrr_at_5": 0.9483333333333333, "mrr_at_10": 0.9494444444444444, "mrr_at_20": 0.9499444444444444, "mrr_at_100": 0.9502569444444444, "mrr_at_1000": 0.9502569444444444, "naucs_at_1_max": 0.44384420434840643, "naucs_at_1_std": -0.29718554088302146, "naucs_at_1_diff1": 0.9813258636788056, "naucs_at_3_max": 0.807812013694371, "naucs_at_3_std": -0.922969187675073, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 0.807812013694364, "naucs_at_5_std": -0.9229691876750711, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 0.7117180205415541, "naucs_at_10_std": -1.445845004668519, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.7117180205415541, "naucs_at_20_std": -1.445845004668519, "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_test": {"ndcg_at_1": 0.9, "ndcg_at_3": 0.94786, "ndcg_at_5": 0.95172, "ndcg_at_10": 0.95506, "ndcg_at_20": 0.95506, "ndcg_at_100": 0.95506, "ndcg_at_1000": 0.95506, "map_at_1": 0.9, "map_at_3": 0.93667, "map_at_5": 0.93867, "map_at_10": 0.9401, "map_at_20": 0.9401, "map_at_100": 0.9401, "map_at_1000": 0.9401, "recall_at_1": 0.9, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.9, "precision_at_3": 0.32667, "precision_at_5": 0.198, "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": 0.9416666666666668, "mrr_at_5": 0.9436666666666667, "mrr_at_10": 0.945095238095238, "mrr_at_20": 0.945095238095238, "mrr_at_100": 0.945095238095238, "mrr_at_1000": 0.945095238095238, "naucs_at_1_max": 0.6363678804855271, "naucs_at_1_std": 0.4060690943043871, "naucs_at_1_diff1": 0.8622782446311862, "naucs_at_3_max": 0.6790382819794457, "naucs_at_3_std": 0.4561157796451816, "naucs_at_3_diff1": 0.8692810457516296, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.5541549953314738, "naucs_at_5_diff1": 0.8692810457516413, "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_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96655, "ndcg_at_5": 0.97085, "ndcg_at_10": 0.97085, "ndcg_at_20": 0.97085, "ndcg_at_100": 0.97085, "ndcg_at_1000": 0.97085, "map_at_1": 0.93, "map_at_3": 0.95833, "map_at_5": 0.96083, "map_at_10": 0.96083, "map_at_20": 0.96083, "map_at_100": 0.96083, "map_at_1000": 0.96083, "recall_at_1": 0.93, "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": 0.93, "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": 0.94, "mrr_at_3": 0.9666666666666667, "mrr_at_5": 0.9666666666666667, "mrr_at_10": 0.9666666666666667, "mrr_at_20": 0.9666666666666667, "mrr_at_100": 0.9666666666666667, "mrr_at_1000": 0.9666666666666667, "naucs_at_1_max": 0.673536081099108, "naucs_at_1_std": -0.18914232359610428, "naucs_at_1_diff1": 0.9626517273576113, "naucs_at_3_max": 1.0, "naucs_at_3_std": -1.7399626517274398, "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}} |