Update results.json
Browse files- results.json +465 -1
results.json
CHANGED
@@ -1 +1,465 @@
|
|
1 |
-
{"./data_dir/eval_vidore/tatdqa_test": {"ndcg_at_1": 0.57108, "ndcg_at_3": 0.67493, "ndcg_at_5": 0.70361, "ndcg_at_10": 0.72693, "ndcg_at_20": 0.73559, "ndcg_at_50": 0.74195, "ndcg_at_100": 0.74529, "map_at_1": 0.57108, "map_at_3": 0.64895, "map_at_5": 0.6648, "map_at_10": 0.67439, "map_at_20": 0.6768, "map_at_50": 0.67786, "map_at_100": 0.67815, "recall_at_1": 0.57108, "recall_at_3": 0.7503, "recall_at_5": 0.82017, "recall_at_10": 0.89247, "recall_at_20": 0.92649, "recall_at_50": 0.95808, "recall_at_100": 0.97874, "precision_at_1": 0.57108, "precision_at_3": 0.2501, "precision_at_5": 0.16403, "precision_at_10": 0.08925, "precision_at_20": 0.04632, "precision_at_50": 0.01916, "precision_at_100": 0.00979, "mrr_at_1": 0.56865127582017, "mrr_at_3": 0.6471243418388012, "mrr_at_5": 0.6632239773187526, "mrr_at_10": 0.6727636984319852, "mrr_at_20": 0.6753542309195802, "mrr_at_50": 0.6765612284057695, "mrr_at_100": 0.6767635994564822, "naucs_at_1_max": 0.19627696906414918, "naucs_at_1_std": 0.25490113312887763, "naucs_at_1_diff1": 0.7311472112111653, "naucs_at_3_max": 0.12505762179060695, "naucs_at_3_std": 0.3250883135485268, "naucs_at_3_diff1": 0.6368932102920861, "naucs_at_5_max": 0.12681693174662004, "naucs_at_5_std": 0.36553579145484827, "naucs_at_5_diff1": 0.5963185435608184, "naucs_at_10_max": 0.2443283094718615, "naucs_at_10_std": 0.5378975291557723, "naucs_at_10_diff1": 0.6056682957261833, "naucs_at_20_max": 0.2941297289999579, "naucs_at_20_std": 0.5490669907768836, "naucs_at_20_diff1": 0.5965035030640417, "naucs_at_50_max": 0.21733999338436122, "naucs_at_50_std": 0.5631005588549655, "naucs_at_50_diff1": 0.6097410948123246, "naucs_at_100_max": 0.21831800388731984, "naucs_at_100_std": 0.710384903173119, "naucs_at_100_diff1": 0.6734222845071824}, "./data_dir/eval_vidore/shiftproject_test": {"ndcg_at_1": 0.63, "ndcg_at_3": 0.74071, "ndcg_at_5": 0.77385, "ndcg_at_10": 0.78346, "ndcg_at_20": 0.78886, "ndcg_at_50": 0.79529, "ndcg_at_100": 0.79852, "map_at_1": 0.63, "map_at_3": 0.71333, "map_at_5": 0.73183, "map_at_10": 0.73575, "map_at_20": 0.73742, "map_at_50": 0.73865, "map_at_100": 0.73894, "recall_at_1": 0.63, "recall_at_3": 0.82, "recall_at_5": 0.9, "recall_at_10": 0.93, "recall_at_20": 0.95, "recall_at_50": 0.98, "recall_at_100": 1.0, "precision_at_1": 0.63, "precision_at_3": 0.27333, "precision_at_5": 0.18, "precision_at_10": 0.093, "precision_at_20": 0.0475, "precision_at_50": 0.0196, "precision_at_100": 0.01, "mrr_at_1": 0.63, "mrr_at_3": 0.7183333333333333, "mrr_at_5": 0.7348333333333333, "mrr_at_10": 0.7408611111111111, "mrr_at_20": 0.741361111111111, "mrr_at_50": 0.7421598822324629, "mrr_at_100": 0.7424503305755428, "naucs_at_1_max": -0.0974004606778548, "naucs_at_1_std": -0.25468904244817375, "naucs_at_1_diff1": 0.6640185524687, "naucs_at_3_max": -0.3256691265557873, "naucs_at_3_std": -0.5354389249917381, "naucs_at_3_diff1": 0.624628263024562, "naucs_at_5_max": -0.22777777777777553, "naucs_at_5_std": -0.5987861811391184, "naucs_at_5_diff1": 0.46909430438842176, "naucs_at_10_max": -0.18354008269974378, "naucs_at_10_std": -0.4598506069094287, "naucs_at_10_diff1": 0.47258903561424775, "naucs_at_20_max": -0.1884220354808507, "naucs_at_20_std": -0.3007469654528384, "naucs_at_20_diff1": 0.4926237161531324, "naucs_at_50_max": 0.5401493930905731, "naucs_at_50_std": -0.22035480859009582, "naucs_at_50_diff1": 0.19140989729225052, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.97, "ndcg_at_5": 0.97431, "ndcg_at_10": 0.9812, "ndcg_at_20": 0.9812, "ndcg_at_50": 0.9812, "ndcg_at_100": 0.9812, "map_at_1": 0.97, "map_at_3": 0.97, "map_at_5": 0.9725, "map_at_10": 0.9756, "map_at_20": 0.9756, "map_at_50": 0.9756, "map_at_100": 0.9756, "recall_at_1": 0.97, "recall_at_3": 0.97, "recall_at_5": 0.98, "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": 0.32333, "precision_at_5": 0.196, "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": 0.9733333333333333, "mrr_at_5": 0.9733333333333333, "mrr_at_10": 0.9764285714285714, "mrr_at_20": 0.9764285714285714, "mrr_at_50": 0.9764285714285714, "mrr_at_100": 0.9764285714285714, "naucs_at_1_max": 0.5659819483348937, "naucs_at_1_std": -0.7791783380018684, "naucs_at_1_diff1": 0.9564270152505465, "naucs_at_3_max": 0.5659819483348902, "naucs_at_3_std": -0.7791783380018689, "naucs_at_3_diff1": 0.9564270152505466, "naucs_at_5_max": 0.9346405228758136, "naucs_at_5_std": -0.5929038281979465, "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/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.95786, "ndcg_at_5": 0.96216, "ndcg_at_10": 0.96216, "ndcg_at_20": 0.96216, "ndcg_at_50": 0.96216, "ndcg_at_100": 0.96216, "map_at_1": 0.91, "map_at_3": 0.94667, "map_at_5": 0.94917, "map_at_10": 0.94917, "map_at_20": 0.94917, "map_at_50": 0.94917, "map_at_100": 0.94917, "recall_at_1": 0.91, "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": 0.91, "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": 0.91, "mrr_at_3": 0.9466666666666668, "mrr_at_5": 0.9491666666666667, "mrr_at_10": 0.9491666666666667, "mrr_at_20": 0.9491666666666667, "mrr_at_50": 0.9491666666666667, "mrr_at_100": 0.9491666666666667, "naucs_at_1_max": 0.3833903931943138, "naucs_at_1_std": 0.48848428260192905, "naucs_at_1_diff1": 0.8264861500155604, "naucs_at_3_max": 1.0, "naucs_at_3_std": 0.8692810457516356, "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/arxivqa_test_subsampled": {"ndcg_at_1": 0.776, "ndcg_at_3": 0.81376, "ndcg_at_5": 0.83037, "ndcg_at_10": 0.84451, "ndcg_at_20": 0.85313, "ndcg_at_50": 0.85831, "ndcg_at_100": 0.85992, "map_at_1": 0.776, "map_at_3": 0.80467, "map_at_5": 0.81397, "map_at_10": 0.81973, "map_at_20": 0.82211, "map_at_50": 0.82294, "map_at_100": 0.82308, "recall_at_1": 0.776, "recall_at_3": 0.84, "recall_at_5": 0.88, "recall_at_10": 0.924, "recall_at_20": 0.958, "recall_at_50": 0.984, "recall_at_100": 0.994, "precision_at_1": 0.776, "precision_at_3": 0.28, "precision_at_5": 0.176, "precision_at_10": 0.0924, "precision_at_20": 0.0479, "precision_at_50": 0.01968, "precision_at_100": 0.00994, "mrr_at_1": 0.774, "mrr_at_3": 0.8046666666666666, "mrr_at_5": 0.8133666666666667, "mrr_at_10": 0.8186833333333333, "mrr_at_20": 0.8212445641733567, "mrr_at_50": 0.8219611912851504, "mrr_at_100": 0.8221248888102938, "naucs_at_1_max": 0.6541204220072772, "naucs_at_1_std": -0.004310581265656427, "naucs_at_1_diff1": 0.9333299811669199, "naucs_at_3_max": 0.6774423171330395, "naucs_at_3_std": 0.02982326951399226, "naucs_at_3_diff1": 0.9019698085419732, "naucs_at_5_max": 0.7342904867960547, "naucs_at_5_std": 0.12409322303531663, "naucs_at_5_diff1": 0.9104756601972646, "naucs_at_10_max": 0.7714383999213704, "naucs_at_10_std": 0.19174160892426748, "naucs_at_10_diff1": 0.9069978868740466, "naucs_at_20_max": 0.7963629896402987, "naucs_at_20_std": 0.374772131074646, "naucs_at_20_diff1": 0.8955137610599756, "naucs_at_50_max": 0.8293067226890712, "naucs_at_50_std": 0.8605275443510737, "naucs_at_50_diff1": 0.9183006535947711, "naucs_at_100_max": 0.6934329287270289, "naucs_at_100_std": 0.8078120136943184, "naucs_at_100_diff1": 0.9128540305010608}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.49446, "ndcg_at_3": 0.56477, "ndcg_at_5": 0.58452, "ndcg_at_10": 0.59669, "ndcg_at_20": 0.60668, "ndcg_at_50": 0.61757, "ndcg_at_100": 0.62554, "map_at_1": 0.49446, "map_at_3": 0.54767, "map_at_5": 0.55843, "map_at_10": 0.56343, "map_at_20": 0.56612, "map_at_50": 0.56802, "map_at_100": 0.56873, "recall_at_1": 0.49446, "recall_at_3": 0.61419, "recall_at_5": 0.66297, "recall_at_10": 0.70067, "recall_at_20": 0.74058, "recall_at_50": 0.79379, "recall_at_100": 0.84257, "precision_at_1": 0.49446, "precision_at_3": 0.20473, "precision_at_5": 0.13259, "precision_at_10": 0.07007, "precision_at_20": 0.03703, "precision_at_50": 0.01588, "precision_at_100": 0.00843, "mrr_at_1": 0.49889135254988914, "mrr_at_3": 0.5447154471544715, "mrr_at_5": 0.5566888396156688, "mrr_at_10": 0.5629526977087953, "mrr_at_20": 0.5652806848414477, "mrr_at_50": 0.5670115584789515, "mrr_at_100": 0.5677538817333595, "naucs_at_1_max": -0.27864580796328964, "naucs_at_1_std": 0.7722092976730863, "naucs_at_1_diff1": 0.8943248317988693, "naucs_at_3_max": -0.44768791859908297, "naucs_at_3_std": 0.8209416026426787, "naucs_at_3_diff1": 0.8513206720284808, "naucs_at_5_max": -0.5206642942420097, "naucs_at_5_std": 0.8590967813938516, "naucs_at_5_diff1": 0.8553385206717447, "naucs_at_10_max": -0.5861667680971102, "naucs_at_10_std": 0.8921235191636205, "naucs_at_10_diff1": 0.8508472594083637, "naucs_at_20_max": -0.6153314648071393, "naucs_at_20_std": 0.8966962245596599, "naucs_at_20_diff1": 0.8514213312670023, "naucs_at_50_max": -0.7316708344718492, "naucs_at_50_std": 0.8827437458106799, "naucs_at_50_diff1": 0.8348654637400126, "naucs_at_100_max": -0.890172253801331, "naucs_at_100_std": 0.8797216559719966, "naucs_at_100_diff1": 0.8182326755467386}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96524, "ndcg_at_5": 0.96911, "ndcg_at_10": 0.96911, "ndcg_at_20": 0.96911, "ndcg_at_50": 0.96911, "ndcg_at_100": 0.96911, "map_at_1": 0.93, "map_at_3": 0.95667, "map_at_5": 0.95867, "map_at_10": 0.95867, "map_at_20": 0.95867, "map_at_50": 0.95867, "map_at_100": 0.95867, "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_50": 1.0, "recall_at_100": 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_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.94, "mrr_at_3": 0.9616666666666667, "mrr_at_5": 0.9641666666666667, "mrr_at_10": 0.9641666666666667, "mrr_at_20": 0.9641666666666667, "mrr_at_50": 0.9641666666666667, "mrr_at_100": 0.9641666666666667, "naucs_at_1_max": 0.5512204881952787, "naucs_at_1_std": -0.5522875816993494, "naucs_at_1_diff1": 0.9626517273576113, "naucs_at_3_max": -0.5634920634921204, "naucs_at_3_std": -1.7399626517274398, "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_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/infovqa_test_subsampled": {"ndcg_at_1": 0.79757, "ndcg_at_3": 0.84618, "ndcg_at_5": 0.85716, "ndcg_at_10": 0.86704, "ndcg_at_20": 0.86964, "ndcg_at_50": 0.87372, "ndcg_at_100": 0.87532, "map_at_1": 0.79757, "map_at_3": 0.83367, "map_at_5": 0.83984, "map_at_10": 0.84396, "map_at_20": 0.84469, "map_at_50": 0.84538, "map_at_100": 0.8455, "recall_at_1": 0.79757, "recall_at_3": 0.88259, "recall_at_5": 0.90891, "recall_at_10": 0.93927, "recall_at_20": 0.94939, "recall_at_50": 0.96964, "recall_at_100": 0.97976, "precision_at_1": 0.79757, "precision_at_3": 0.2942, "precision_at_5": 0.18178, "precision_at_10": 0.09393, "precision_at_20": 0.04747, "precision_at_50": 0.01939, "precision_at_100": 0.0098, "mrr_at_1": 0.7894736842105263, "mrr_at_3": 0.8306342780026991, "mrr_at_5": 0.8363022941970311, "mrr_at_10": 0.8404167469956944, "mrr_at_20": 0.8411396743317877, "mrr_at_50": 0.8418165179225722, "mrr_at_100": 0.8419436154362733, "naucs_at_1_max": 0.5658752085914066, "naucs_at_1_std": 0.08703668327449693, "naucs_at_1_diff1": 0.8969893821656988, "naucs_at_3_max": 0.5035089171640572, "naucs_at_3_std": 0.10634666680591591, "naucs_at_3_diff1": 0.8617291252020982, "naucs_at_5_max": 0.672890311854327, "naucs_at_5_std": 0.2917197093395984, "naucs_at_5_diff1": 0.8715729540210408, "naucs_at_10_max": 0.7402193471144418, "naucs_at_10_std": 0.3670976593963592, "naucs_at_10_diff1": 0.8958712928076012, "naucs_at_20_max": 0.7849669612599903, "naucs_at_20_std": 0.5713453092645688, "naucs_at_20_diff1": 0.8802696095317121, "naucs_at_50_max": 0.7192418710631517, "naucs_at_50_std": 0.7316569995970472, "naucs_at_50_diff1": 0.8624988164249825, "naucs_at_100_max": 0.6626137244104312, "naucs_at_100_std": 0.8415749940072255, "naucs_at_100_diff1": 0.8476419892262101}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.94, "ndcg_at_3": 0.94631, "ndcg_at_5": 0.95405, "ndcg_at_10": 0.95405, "ndcg_at_20": 0.95684, "ndcg_at_50": 0.95902, "ndcg_at_100": 0.96074, "map_at_1": 0.94, "map_at_3": 0.945, "map_at_5": 0.949, "map_at_10": 0.949, "map_at_20": 0.94991, "map_at_50": 0.95034, "map_at_100": 0.95053, "recall_at_1": 0.94, "recall_at_3": 0.95, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.94, "precision_at_3": 0.31667, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.94, "mrr_at_3": 0.945, "mrr_at_5": 0.9490000000000001, "mrr_at_10": 0.950111111111111, "mrr_at_20": 0.950111111111111, "mrr_at_50": 0.9505873015873015, "mrr_at_100": 0.9507724867724867, "naucs_at_1_max": 0.5278555866791174, "naucs_at_1_std": -0.5602240896358519, "naucs_at_1_diff1": 0.9782135076252712, "naucs_at_3_max": 0.4595704948646117, "naucs_at_3_std": -0.7438842203548082, "naucs_at_3_diff1": 0.973856209150328, "naucs_at_5_max": 0.4352629940865253, "naucs_at_5_std": -0.8445378151260495, "naucs_at_5_diff1": 0.9564270152505424, "naucs_at_10_max": 0.4352629940865253, "naucs_at_10_std": -0.8445378151260495, "naucs_at_10_diff1": 0.9564270152505424, "naucs_at_20_max": 0.9346405228758136, "naucs_at_20_std": -0.3968253968253954, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.35807656395892007, "naucs_at_50_diff1": 1.0, "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": 0.81429, "ndcg_at_3": 0.86688, "ndcg_at_5": 0.87441, "ndcg_at_10": 0.88583, "ndcg_at_20": 0.89213, "ndcg_at_50": 0.89426, "ndcg_at_100": 0.89548, "map_at_1": 0.81429, "map_at_3": 0.85417, "map_at_5": 0.85845, "map_at_10": 0.8631, "map_at_20": 0.86482, "map_at_50": 0.86516, "map_at_100": 0.86528, "recall_at_1": 0.81429, "recall_at_3": 0.90357, "recall_at_5": 0.92143, "recall_at_10": 0.95714, "recall_at_20": 0.98214, "recall_at_50": 0.99286, "recall_at_100": 1.0, "precision_at_1": 0.81429, "precision_at_3": 0.30119, "precision_at_5": 0.18429, "precision_at_10": 0.09571, "precision_at_20": 0.04911, "precision_at_50": 0.01986, "precision_at_100": 0.01, "mrr_at_1": 0.8142857142857143, "mrr_at_3": 0.8535714285714285, "mrr_at_5": 0.8576785714285714, "mrr_at_10": 0.8620280612244897, "mrr_at_20": 0.8640784760874046, "mrr_at_50": 0.8644115436805921, "mrr_at_100": 0.8645378286859094, "naucs_at_1_max": 0.5099174501261181, "naucs_at_1_std": 0.10524153481617399, "naucs_at_1_diff1": 0.8698884048001222, "naucs_at_3_max": 0.5539647957948607, "naucs_at_3_std": 0.17413632119514313, "naucs_at_3_diff1": 0.8326416986547719, "naucs_at_5_max": 0.478800611153553, "naucs_at_5_std": 0.10332314744079385, "naucs_at_5_diff1": 0.8250572956455312, "naucs_at_10_max": 0.6088935574229674, "naucs_at_10_std": 0.23650015561779797, "naucs_at_10_diff1": 0.8465608465608483, "naucs_at_20_max": 0.8216619981325874, "naucs_at_20_std": 0.6112044817927197, "naucs_at_20_diff1": 0.7984126984127048, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.9346405228758071, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.44872, "ndcg_at_3": 0.5037, "ndcg_at_5": 0.51119, "ndcg_at_10": 0.56186, "ndcg_at_20": 0.59295, "ndcg_at_50": 0.62491, "ndcg_at_100": 0.63554, "map_at_1": 0.34359, "map_at_3": 0.43594, "map_at_5": 0.45747, "map_at_10": 0.49017, "map_at_20": 0.50192, "map_at_50": 0.51154, "map_at_100": 0.51383, "recall_at_1": 0.34359, "recall_at_3": 0.50916, "recall_at_5": 0.54217, "recall_at_10": 0.66974, "recall_at_20": 0.76672, "recall_at_50": 0.88184, "recall_at_100": 0.93309, "precision_at_1": 0.46154, "precision_at_3": 0.27564, "precision_at_5": 0.19615, "precision_at_10": 0.13077, "precision_at_20": 0.07885, "precision_at_50": 0.03923, "precision_at_100": 0.02154, "mrr_at_1": 0.46153846153846156, "mrr_at_3": 0.5673076923076923, "mrr_at_5": 0.5807692307692307, "mrr_at_10": 0.5931852869352869, "mrr_at_20": 0.5957493894993895, "mrr_at_50": 0.599353791164136, "mrr_at_100": 0.5996102014205462, "naucs_at_1_max": 0.002194328992717967, "naucs_at_1_std": -0.031840651667529675, "naucs_at_1_diff1": 0.49264228977678737, "naucs_at_3_max": 0.1015332407069215, "naucs_at_3_std": 0.08227931903725726, "naucs_at_3_diff1": 0.23276218831428178, "naucs_at_5_max": 0.04350167135259752, "naucs_at_5_std": 0.07348958132289792, "naucs_at_5_diff1": 0.038716822746462015, "naucs_at_10_max": -0.08985016409859849, "naucs_at_10_std": 0.015107221380773713, "naucs_at_10_diff1": -0.12506839397757577, "naucs_at_20_max": -0.12233651454517988, "naucs_at_20_std": 0.034645213528140144, "naucs_at_20_diff1": -0.14061137918779468, "naucs_at_50_max": -0.14676579665385234, "naucs_at_50_std": -0.016468277680667155, "naucs_at_50_diff1": -0.25633385453548485, "naucs_at_100_max": -0.2049763295760409, "naucs_at_100_std": -0.0530350260858156, "naucs_at_100_diff1": -0.2594154631359254},
|
2 |
+
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
|
3 |
+
"ndcg_at_1": 0.54741,
|
4 |
+
"ndcg_at_3": 0.51063,
|
5 |
+
"ndcg_at_5": 0.49897,
|
6 |
+
"ndcg_at_10": 0.49415,
|
7 |
+
"ndcg_at_20": 0.51343,
|
8 |
+
"ndcg_at_50": 0.59078,
|
9 |
+
"ndcg_at_100": 0.63538,
|
10 |
+
"map_at_1": 0.06112,
|
11 |
+
"map_at_3": 0.1382,
|
12 |
+
"map_at_5": 0.18445,
|
13 |
+
"map_at_10": 0.2524,
|
14 |
+
"map_at_20": 0.30006,
|
15 |
+
"map_at_50": 0.35957,
|
16 |
+
"map_at_100": 0.38851,
|
17 |
+
"recall_at_1": 0.06112,
|
18 |
+
"recall_at_3": 0.18299,
|
19 |
+
"recall_at_5": 0.26472,
|
20 |
+
"recall_at_10": 0.40191,
|
21 |
+
"recall_at_20": 0.5352,
|
22 |
+
"recall_at_50": 0.75781,
|
23 |
+
"recall_at_100": 0.8924,
|
24 |
+
"precision_at_1": 0.54741,
|
25 |
+
"precision_at_3": 0.47989,
|
26 |
+
"precision_at_5": 0.45086,
|
27 |
+
"precision_at_10": 0.37888,
|
28 |
+
"precision_at_20": 0.28362,
|
29 |
+
"precision_at_50": 0.18922,
|
30 |
+
"precision_at_100": 0.12578,
|
31 |
+
"mrr_at_1": 0.5560344827586207,
|
32 |
+
"mrr_at_3": 0.6602011494252873,
|
33 |
+
"mrr_at_5": 0.6793821839080461,
|
34 |
+
"mrr_at_10": 0.6860905856595513,
|
35 |
+
"mrr_at_20": 0.6893415988592205,
|
36 |
+
"mrr_at_50": 0.6899569837403354,
|
37 |
+
"mrr_at_100": 0.6900254019122019,
|
38 |
+
"naucs_at_1_max": 0.19899931717746902,
|
39 |
+
"naucs_at_1_std": 0.1912713809809152,
|
40 |
+
"naucs_at_1_diff1": -0.038035444126148475,
|
41 |
+
"naucs_at_3_max": 0.20495600819240758,
|
42 |
+
"naucs_at_3_std": 0.16790550405572538,
|
43 |
+
"naucs_at_3_diff1": 0.029074570269105135,
|
44 |
+
"naucs_at_5_max": 0.1625330851844803,
|
45 |
+
"naucs_at_5_std": 0.10238997547471022,
|
46 |
+
"naucs_at_5_diff1": -0.0062210568445968855,
|
47 |
+
"naucs_at_10_max": 0.15357323710897905,
|
48 |
+
"naucs_at_10_std": 0.13722417423637584,
|
49 |
+
"naucs_at_10_diff1": -0.03143332026528358,
|
50 |
+
"naucs_at_20_max": 0.07492057455393925,
|
51 |
+
"naucs_at_20_std": 0.13425712594274392,
|
52 |
+
"naucs_at_20_diff1": -0.01417898804015983,
|
53 |
+
"naucs_at_50_max": 0.020626645082431186,
|
54 |
+
"naucs_at_50_std": 0.1387923185354242,
|
55 |
+
"naucs_at_50_diff1": -0.028196311485082164,
|
56 |
+
"naucs_at_100_max": -0.03783089891016362,
|
57 |
+
"naucs_at_100_std": 0.08717161521353252,
|
58 |
+
"naucs_at_100_diff1": -0.0016118299784232586
|
59 |
+
},
|
60 |
+
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
61 |
+
"ndcg_at_1": 0.43056,
|
62 |
+
"ndcg_at_3": 0.51586,
|
63 |
+
"ndcg_at_5": 0.5007,
|
64 |
+
"ndcg_at_10": 0.50244,
|
65 |
+
"ndcg_at_20": 0.53465,
|
66 |
+
"ndcg_at_50": 0.59112,
|
67 |
+
"ndcg_at_100": 0.62064,
|
68 |
+
"map_at_1": 0.18377,
|
69 |
+
"map_at_3": 0.31089,
|
70 |
+
"map_at_5": 0.34121,
|
71 |
+
"map_at_10": 0.37642,
|
72 |
+
"map_at_20": 0.40534,
|
73 |
+
"map_at_50": 0.43068,
|
74 |
+
"map_at_100": 0.43754,
|
75 |
+
"recall_at_1": 0.18377,
|
76 |
+
"recall_at_3": 0.41869,
|
77 |
+
"recall_at_5": 0.48638,
|
78 |
+
"recall_at_10": 0.56114,
|
79 |
+
"recall_at_20": 0.66324,
|
80 |
+
"recall_at_50": 0.81349,
|
81 |
+
"recall_at_100": 0.93626,
|
82 |
+
"precision_at_1": 0.43056,
|
83 |
+
"precision_at_3": 0.375,
|
84 |
+
"precision_at_5": 0.28889,
|
85 |
+
"precision_at_10": 0.20278,
|
86 |
+
"precision_at_20": 0.13681,
|
87 |
+
"precision_at_50": 0.07694,
|
88 |
+
"precision_at_100": 0.04417,
|
89 |
+
"mrr_at_1": 0.4444444444444444,
|
90 |
+
"mrr_at_3": 0.6018518518518519,
|
91 |
+
"mrr_at_5": 0.6081018518518518,
|
92 |
+
"mrr_at_10": 0.6104166666666667,
|
93 |
+
"mrr_at_20": 0.6134023505734032,
|
94 |
+
"mrr_at_50": 0.614429082950942,
|
95 |
+
"mrr_at_100": 0.6154064098676808,
|
96 |
+
"naucs_at_1_max": -0.07365305259701632,
|
97 |
+
"naucs_at_1_std": -0.0442273303903828,
|
98 |
+
"naucs_at_1_diff1": 0.2949540272672445,
|
99 |
+
"naucs_at_3_max": -0.10802492756921314,
|
100 |
+
"naucs_at_3_std": -0.04669947189371184,
|
101 |
+
"naucs_at_3_diff1": -0.0728949627388125,
|
102 |
+
"naucs_at_5_max": -0.2552572158853236,
|
103 |
+
"naucs_at_5_std": -0.1846710716163106,
|
104 |
+
"naucs_at_5_diff1": -0.12002134546511585,
|
105 |
+
"naucs_at_10_max": -0.3201675872693993,
|
106 |
+
"naucs_at_10_std": -0.23986470064093401,
|
107 |
+
"naucs_at_10_diff1": -0.16279676404365048,
|
108 |
+
"naucs_at_20_max": -0.3441481285657308,
|
109 |
+
"naucs_at_20_std": -0.25948207654811956,
|
110 |
+
"naucs_at_20_diff1": -0.19645208167464911,
|
111 |
+
"naucs_at_50_max": -0.43057849108214125,
|
112 |
+
"naucs_at_50_std": -0.3201379636235207,
|
113 |
+
"naucs_at_50_diff1": -0.22760590888322807,
|
114 |
+
"naucs_at_100_max": -0.46285250963434216,
|
115 |
+
"naucs_at_100_std": -0.363188137612312,
|
116 |
+
"naucs_at_100_diff1": -0.23496727359104055
|
117 |
+
},
|
118 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
|
119 |
+
"ndcg_at_1": 0.575,
|
120 |
+
"ndcg_at_3": 0.58726,
|
121 |
+
"ndcg_at_5": 0.59728,
|
122 |
+
"ndcg_at_10": 0.63923,
|
123 |
+
"ndcg_at_20": 0.66624,
|
124 |
+
"ndcg_at_50": 0.68704,
|
125 |
+
"ndcg_at_100": 0.69972,
|
126 |
+
"map_at_1": 0.35444,
|
127 |
+
"map_at_3": 0.47331,
|
128 |
+
"map_at_5": 0.50331,
|
129 |
+
"map_at_10": 0.54381,
|
130 |
+
"map_at_20": 0.55876,
|
131 |
+
"map_at_50": 0.56771,
|
132 |
+
"map_at_100": 0.57022,
|
133 |
+
"recall_at_1": 0.35444,
|
134 |
+
"recall_at_3": 0.54862,
|
135 |
+
"recall_at_5": 0.61134,
|
136 |
+
"recall_at_10": 0.73819,
|
137 |
+
"recall_at_20": 0.81663,
|
138 |
+
"recall_at_50": 0.87245,
|
139 |
+
"recall_at_100": 0.92434,
|
140 |
+
"precision_at_1": 0.575,
|
141 |
+
"precision_at_3": 0.36667,
|
142 |
+
"precision_at_5": 0.2725,
|
143 |
+
"precision_at_10": 0.17813,
|
144 |
+
"precision_at_20": 0.10469,
|
145 |
+
"precision_at_50": 0.05012,
|
146 |
+
"precision_at_100": 0.02738,
|
147 |
+
"mrr_at_1": 0.56875,
|
148 |
+
"mrr_at_3": 0.6708333333333333,
|
149 |
+
"mrr_at_5": 0.6855208333333334,
|
150 |
+
"mrr_at_10": 0.6957242063492063,
|
151 |
+
"mrr_at_20": 0.6976232448107449,
|
152 |
+
"mrr_at_50": 0.6979515276390276,
|
153 |
+
"mrr_at_100": 0.6981114569953856,
|
154 |
+
"naucs_at_1_max": 0.2685071611530002,
|
155 |
+
"naucs_at_1_std": 0.040757242324759406,
|
156 |
+
"naucs_at_1_diff1": 0.39086907897110307,
|
157 |
+
"naucs_at_3_max": 0.0708941966048168,
|
158 |
+
"naucs_at_3_std": -0.07235491512041044,
|
159 |
+
"naucs_at_3_diff1": -0.04516383734701926,
|
160 |
+
"naucs_at_5_max": -3.616204937416473e-6,
|
161 |
+
"naucs_at_5_std": -0.09247359266344345,
|
162 |
+
"naucs_at_5_diff1": -0.20101036765955618,
|
163 |
+
"naucs_at_10_max": -0.11724171373298614,
|
164 |
+
"naucs_at_10_std": -0.11549092319746397,
|
165 |
+
"naucs_at_10_diff1": -0.30608973949972307,
|
166 |
+
"naucs_at_20_max": -0.15891345319651773,
|
167 |
+
"naucs_at_20_std": -0.1128685536499577,
|
168 |
+
"naucs_at_20_diff1": -0.37493429178294696,
|
169 |
+
"naucs_at_50_max": -0.20739052708712324,
|
170 |
+
"naucs_at_50_std": -0.13026360673135243,
|
171 |
+
"naucs_at_50_diff1": -0.40284042096219924,
|
172 |
+
"naucs_at_100_max": -0.22825723213677793,
|
173 |
+
"naucs_at_100_std": -0.11862167475267539,
|
174 |
+
"naucs_at_100_diff1": -0.41577199049091196
|
175 |
+
},
|
176 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
|
177 |
+
"ndcg_at_1": 0.61404,
|
178 |
+
"ndcg_at_3": 0.552,
|
179 |
+
"ndcg_at_5": 0.57021,
|
180 |
+
"ndcg_at_10": 0.59177,
|
181 |
+
"ndcg_at_20": 0.62781,
|
182 |
+
"ndcg_at_50": 0.66213,
|
183 |
+
"ndcg_at_100": 0.67379,
|
184 |
+
"map_at_1": 0.33118,
|
185 |
+
"map_at_3": 0.41808,
|
186 |
+
"map_at_5": 0.45961,
|
187 |
+
"map_at_10": 0.48972,
|
188 |
+
"map_at_20": 0.50896,
|
189 |
+
"map_at_50": 0.5235,
|
190 |
+
"map_at_100": 0.52816,
|
191 |
+
"recall_at_1": 0.33118,
|
192 |
+
"recall_at_3": 0.46982,
|
193 |
+
"recall_at_5": 0.54944,
|
194 |
+
"recall_at_10": 0.65566,
|
195 |
+
"recall_at_20": 0.77366,
|
196 |
+
"recall_at_50": 0.88778,
|
197 |
+
"recall_at_100": 0.92045,
|
198 |
+
"precision_at_1": 0.61404,
|
199 |
+
"precision_at_3": 0.34503,
|
200 |
+
"precision_at_5": 0.27368,
|
201 |
+
"precision_at_10": 0.17193,
|
202 |
+
"precision_at_20": 0.1114,
|
203 |
+
"precision_at_50": 0.05825,
|
204 |
+
"precision_at_100": 0.03298,
|
205 |
+
"mrr_at_1": 0.5964912280701754,
|
206 |
+
"mrr_at_3": 0.6812865497076024,
|
207 |
+
"mrr_at_5": 0.6812865497076024,
|
208 |
+
"mrr_at_10": 0.6871832358674463,
|
209 |
+
"mrr_at_20": 0.6922425022759062,
|
210 |
+
"mrr_at_50": 0.6930890955031604,
|
211 |
+
"mrr_at_100": 0.6930890955031604,
|
212 |
+
"naucs_at_1_max": -0.18309708535761227,
|
213 |
+
"naucs_at_1_std": -0.007381456661982562,
|
214 |
+
"naucs_at_1_diff1": 0.30732508630084004,
|
215 |
+
"naucs_at_3_max": -0.20369312436042705,
|
216 |
+
"naucs_at_3_std": 0.05190902781892078,
|
217 |
+
"naucs_at_3_diff1": -0.016141260839756796,
|
218 |
+
"naucs_at_5_max": -0.2604343236468471,
|
219 |
+
"naucs_at_5_std": -0.024413180213346482,
|
220 |
+
"naucs_at_5_diff1": -0.022892329345085023,
|
221 |
+
"naucs_at_10_max": -0.1848880821409115,
|
222 |
+
"naucs_at_10_std": 0.008525190122667848,
|
223 |
+
"naucs_at_10_diff1": -0.015249832440976916,
|
224 |
+
"naucs_at_20_max": -0.29880658374501545,
|
225 |
+
"naucs_at_20_std": -0.04213299952583688,
|
226 |
+
"naucs_at_20_diff1": -0.048810655476262586,
|
227 |
+
"naucs_at_50_max": -0.34562636189863627,
|
228 |
+
"naucs_at_50_std": -0.10582674487072245,
|
229 |
+
"naucs_at_50_diff1": -0.1306813668575179,
|
230 |
+
"naucs_at_100_max": -0.34623793556332916,
|
231 |
+
"naucs_at_100_std": -0.07974452650276295,
|
232 |
+
"naucs_at_100_diff1": -0.14583553240737473
|
233 |
+
},
|
234 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
|
235 |
+
"ndcg_at_1": 0.55263,
|
236 |
+
"ndcg_at_3": 0.53271,
|
237 |
+
"ndcg_at_5": 0.55689,
|
238 |
+
"ndcg_at_10": 0.58626,
|
239 |
+
"ndcg_at_20": 0.61796,
|
240 |
+
"ndcg_at_50": 0.65316,
|
241 |
+
"ndcg_at_100": 0.66702,
|
242 |
+
"map_at_1": 0.28677,
|
243 |
+
"map_at_3": 0.39445,
|
244 |
+
"map_at_5": 0.43962,
|
245 |
+
"map_at_10": 0.47552,
|
246 |
+
"map_at_20": 0.49671,
|
247 |
+
"map_at_50": 0.51072,
|
248 |
+
"map_at_100": 0.5162,
|
249 |
+
"recall_at_1": 0.28677,
|
250 |
+
"recall_at_3": 0.46525,
|
251 |
+
"recall_at_5": 0.56098,
|
252 |
+
"recall_at_10": 0.67457,
|
253 |
+
"recall_at_20": 0.78279,
|
254 |
+
"recall_at_50": 0.90087,
|
255 |
+
"recall_at_100": 0.93904,
|
256 |
+
"precision_at_1": 0.55263,
|
257 |
+
"precision_at_3": 0.34795,
|
258 |
+
"precision_at_5": 0.27632,
|
259 |
+
"precision_at_10": 0.18333,
|
260 |
+
"precision_at_20": 0.11491,
|
261 |
+
"precision_at_50": 0.06044,
|
262 |
+
"precision_at_100": 0.035,
|
263 |
+
"mrr_at_1": 0.5394736842105263,
|
264 |
+
"mrr_at_3": 0.6418128654970761,
|
265 |
+
"mrr_at_5": 0.6503654970760234,
|
266 |
+
"mrr_at_10": 0.65812447786132,
|
267 |
+
"mrr_at_20": 0.6613348635142671,
|
268 |
+
"mrr_at_50": 0.6632523470183257,
|
269 |
+
"mrr_at_100": 0.6632523470183257,
|
270 |
+
"naucs_at_1_max": 0.026074740927519928,
|
271 |
+
"naucs_at_1_std": 0.0665267906629989,
|
272 |
+
"naucs_at_1_diff1": 0.26475189282642253,
|
273 |
+
"naucs_at_3_max": -0.11699329721348749,
|
274 |
+
"naucs_at_3_std": 0.034724428785861,
|
275 |
+
"naucs_at_3_diff1": -0.06500823338336245,
|
276 |
+
"naucs_at_5_max": -0.15525742665500714,
|
277 |
+
"naucs_at_5_std": -0.0007029574302984752,
|
278 |
+
"naucs_at_5_diff1": -0.11428313538875555,
|
279 |
+
"naucs_at_10_max": -0.16443948785535192,
|
280 |
+
"naucs_at_10_std": -0.023414974850073055,
|
281 |
+
"naucs_at_10_diff1": -0.1421086474718392,
|
282 |
+
"naucs_at_20_max": -0.197823753688015,
|
283 |
+
"naucs_at_20_std": -0.021674091781515255,
|
284 |
+
"naucs_at_20_diff1": -0.18113094982693073,
|
285 |
+
"naucs_at_50_max": -0.25739967642020234,
|
286 |
+
"naucs_at_50_std": -0.06035516399907118,
|
287 |
+
"naucs_at_50_diff1": -0.23372161884057194,
|
288 |
+
"naucs_at_100_max": -0.27625472729524525,
|
289 |
+
"naucs_at_100_std": -0.05802308794039868,
|
290 |
+
"naucs_at_100_diff1": -0.2352303429668158
|
291 |
+
},
|
292 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
|
293 |
+
"ndcg_at_1": 0.525,
|
294 |
+
"ndcg_at_3": 0.54716,
|
295 |
+
"ndcg_at_5": 0.56518,
|
296 |
+
"ndcg_at_10": 0.60281,
|
297 |
+
"ndcg_at_20": 0.63098,
|
298 |
+
"ndcg_at_50": 0.6531,
|
299 |
+
"ndcg_at_100": 0.66545,
|
300 |
+
"map_at_1": 0.31729,
|
301 |
+
"map_at_3": 0.43631,
|
302 |
+
"map_at_5": 0.46986,
|
303 |
+
"map_at_10": 0.50577,
|
304 |
+
"map_at_20": 0.5214,
|
305 |
+
"map_at_50": 0.52972,
|
306 |
+
"map_at_100": 0.53236,
|
307 |
+
"recall_at_1": 0.31729,
|
308 |
+
"recall_at_3": 0.51777,
|
309 |
+
"recall_at_5": 0.59622,
|
310 |
+
"recall_at_10": 0.71217,
|
311 |
+
"recall_at_20": 0.79369,
|
312 |
+
"recall_at_50": 0.86035,
|
313 |
+
"recall_at_100": 0.9077,
|
314 |
+
"precision_at_1": 0.525,
|
315 |
+
"precision_at_3": 0.34479,
|
316 |
+
"precision_at_5": 0.26125,
|
317 |
+
"precision_at_10": 0.17047,
|
318 |
+
"precision_at_20": 0.10156,
|
319 |
+
"precision_at_50": 0.04809,
|
320 |
+
"precision_at_100": 0.02655,
|
321 |
+
"mrr_at_1": 0.521875,
|
322 |
+
"mrr_at_3": 0.6229166666666667,
|
323 |
+
"mrr_at_5": 0.6413541666666667,
|
324 |
+
"mrr_at_10": 0.6526822916666666,
|
325 |
+
"mrr_at_20": 0.654819594877463,
|
326 |
+
"mrr_at_50": 0.6554222117851556,
|
327 |
+
"mrr_at_100": 0.6555914689034035,
|
328 |
+
"naucs_at_1_max": 0.2906325846921682,
|
329 |
+
"naucs_at_1_std": 0.06423059173418094,
|
330 |
+
"naucs_at_1_diff1": 0.448169845827778,
|
331 |
+
"naucs_at_3_max": 0.07976033275315568,
|
332 |
+
"naucs_at_3_std": -0.03694347010556673,
|
333 |
+
"naucs_at_3_diff1": -0.00570199473253546,
|
334 |
+
"naucs_at_5_max": 0.014659645432582174,
|
335 |
+
"naucs_at_5_std": -0.08162828155050585,
|
336 |
+
"naucs_at_5_diff1": -0.14232800244174196,
|
337 |
+
"naucs_at_10_max": -0.0842571134499816,
|
338 |
+
"naucs_at_10_std": -0.13986852153125942,
|
339 |
+
"naucs_at_10_diff1": -0.2526166207377402,
|
340 |
+
"naucs_at_20_max": -0.14121549988298185,
|
341 |
+
"naucs_at_20_std": -0.13657737700427194,
|
342 |
+
"naucs_at_20_diff1": -0.30194444174817464,
|
343 |
+
"naucs_at_50_max": -0.18022843383725712,
|
344 |
+
"naucs_at_50_std": -0.1368265102548377,
|
345 |
+
"naucs_at_50_diff1": -0.3498376513961813,
|
346 |
+
"naucs_at_100_max": -0.20683430675792094,
|
347 |
+
"naucs_at_100_std": -0.13875444462530698,
|
348 |
+
"naucs_at_100_diff1": -0.36859626748542823
|
349 |
+
},
|
350 |
+
"vidore/synthetic_axa_filtered_v1.0": {
|
351 |
+
"ndcg_at_1": 0.5,
|
352 |
+
"ndcg_at_3": 0.62618,
|
353 |
+
"ndcg_at_5": 0.59839,
|
354 |
+
"ndcg_at_10": 0.58705,
|
355 |
+
"ndcg_at_20": 0.61603,
|
356 |
+
"ndcg_at_50": 0.66597,
|
357 |
+
"ndcg_at_100": 0.68287,
|
358 |
+
"map_at_1": 0.17661,
|
359 |
+
"map_at_3": 0.36502,
|
360 |
+
"map_at_5": 0.39879,
|
361 |
+
"map_at_10": 0.43806,
|
362 |
+
"map_at_20": 0.46907,
|
363 |
+
"map_at_50": 0.49276,
|
364 |
+
"map_at_100": 0.4981,
|
365 |
+
"recall_at_1": 0.17661,
|
366 |
+
"recall_at_3": 0.54673,
|
367 |
+
"recall_at_5": 0.59602,
|
368 |
+
"recall_at_10": 0.68965,
|
369 |
+
"recall_at_20": 0.76947,
|
370 |
+
"recall_at_50": 0.91353,
|
371 |
+
"recall_at_100": 0.96521,
|
372 |
+
"precision_at_1": 0.5,
|
373 |
+
"precision_at_3": 0.46296,
|
374 |
+
"precision_at_5": 0.35556,
|
375 |
+
"precision_at_10": 0.22778,
|
376 |
+
"precision_at_20": 0.15278,
|
377 |
+
"precision_at_50": 0.08,
|
378 |
+
"precision_at_100": 0.04444,
|
379 |
+
"mrr_at_1": 0.5,
|
380 |
+
"mrr_at_3": 0.6944444444444444,
|
381 |
+
"mrr_at_5": 0.6944444444444444,
|
382 |
+
"mrr_at_10": 0.6944444444444444,
|
383 |
+
"mrr_at_20": 0.6944444444444444,
|
384 |
+
"mrr_at_50": 0.6969696969696969,
|
385 |
+
"mrr_at_100": 0.6969696969696969,
|
386 |
+
"naucs_at_1_max": -0.2649286915597099,
|
387 |
+
"naucs_at_1_std": -0.2940555637425178,
|
388 |
+
"naucs_at_1_diff1": 0.3662687803063795,
|
389 |
+
"naucs_at_3_max": -0.49658019607010634,
|
390 |
+
"naucs_at_3_std": -0.3772337900485017,
|
391 |
+
"naucs_at_3_diff1": -0.1627833746782874,
|
392 |
+
"naucs_at_5_max": -0.5986742297090961,
|
393 |
+
"naucs_at_5_std": -0.4537347487754755,
|
394 |
+
"naucs_at_5_diff1": -0.25484184762587836,
|
395 |
+
"naucs_at_10_max": -0.7032286711767408,
|
396 |
+
"naucs_at_10_std": -0.5402873044780693,
|
397 |
+
"naucs_at_10_diff1": -0.250898327094186,
|
398 |
+
"naucs_at_20_max": -0.637724179407209,
|
399 |
+
"naucs_at_20_std": -0.5189671897426067,
|
400 |
+
"naucs_at_20_diff1": -0.27658015939088765,
|
401 |
+
"naucs_at_50_max": -0.6187318235256102,
|
402 |
+
"naucs_at_50_std": -0.5310219511420982,
|
403 |
+
"naucs_at_50_diff1": -0.27707941800085223,
|
404 |
+
"naucs_at_100_max": -0.6202004090535382,
|
405 |
+
"naucs_at_100_std": -0.5432756751449638,
|
406 |
+
"naucs_at_100_diff1": -0.2715983846055494
|
407 |
+
},
|
408 |
+
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
|
409 |
+
"ndcg_at_1": 0.55172,
|
410 |
+
"ndcg_at_3": 0.54048,
|
411 |
+
"ndcg_at_5": 0.51595,
|
412 |
+
"ndcg_at_10": 0.51341,
|
413 |
+
"ndcg_at_20": 0.54792,
|
414 |
+
"ndcg_at_50": 0.61345,
|
415 |
+
"ndcg_at_100": 0.65309,
|
416 |
+
"map_at_1": 0.06341,
|
417 |
+
"map_at_3": 0.14907,
|
418 |
+
"map_at_5": 0.19483,
|
419 |
+
"map_at_10": 0.26656,
|
420 |
+
"map_at_20": 0.32533,
|
421 |
+
"map_at_50": 0.38317,
|
422 |
+
"map_at_100": 0.41122,
|
423 |
+
"recall_at_1": 0.06341,
|
424 |
+
"recall_at_3": 0.20022,
|
425 |
+
"recall_at_5": 0.27082,
|
426 |
+
"recall_at_10": 0.40671,
|
427 |
+
"recall_at_20": 0.57946,
|
428 |
+
"recall_at_50": 0.78205,
|
429 |
+
"recall_at_100": 0.89891,
|
430 |
+
"precision_at_1": 0.55172,
|
431 |
+
"precision_at_3": 0.51724,
|
432 |
+
"precision_at_5": 0.46897,
|
433 |
+
"precision_at_10": 0.39828,
|
434 |
+
"precision_at_20": 0.30776,
|
435 |
+
"precision_at_50": 0.1931,
|
436 |
+
"precision_at_100": 0.1269,
|
437 |
+
"mrr_at_1": 0.603448275862069,
|
438 |
+
"mrr_at_3": 0.6925287356321839,
|
439 |
+
"mrr_at_5": 0.7089080459770115,
|
440 |
+
"mrr_at_10": 0.7132868089764641,
|
441 |
+
"mrr_at_20": 0.7183845847638951,
|
442 |
+
"mrr_at_50": 0.71904771473737,
|
443 |
+
"mrr_at_100": 0.71904771473737,
|
444 |
+
"naucs_at_1_max": 0.4262157733451073,
|
445 |
+
"naucs_at_1_std": 0.32984538171821315,
|
446 |
+
"naucs_at_1_diff1": 0.12315457044803446,
|
447 |
+
"naucs_at_3_max": 0.07836128415322025,
|
448 |
+
"naucs_at_3_std": 0.0649036893047738,
|
449 |
+
"naucs_at_3_diff1": -0.06209838897565292,
|
450 |
+
"naucs_at_5_max": 0.1284664968747896,
|
451 |
+
"naucs_at_5_std": 0.07008745558362922,
|
452 |
+
"naucs_at_5_diff1": -0.10371576299512358,
|
453 |
+
"naucs_at_10_max": 0.17696666641677838,
|
454 |
+
"naucs_at_10_std": 0.18241519517317692,
|
455 |
+
"naucs_at_10_diff1": -0.13811311830073486,
|
456 |
+
"naucs_at_20_max": 0.10291535353674224,
|
457 |
+
"naucs_at_20_std": 0.1918823805461267,
|
458 |
+
"naucs_at_20_diff1": -0.06857922449160693,
|
459 |
+
"naucs_at_50_max": 0.046333954531615734,
|
460 |
+
"naucs_at_50_std": 0.22257516542310005,
|
461 |
+
"naucs_at_50_diff1": -0.09956425708477333,
|
462 |
+
"naucs_at_100_max": -0.02185631024396941,
|
463 |
+
"naucs_at_100_std": 0.17833736053437418,
|
464 |
+
"naucs_at_100_diff1": -0.06588665309807952
|
465 |
+
}, "./data_dir/eval_vidore/tatdqa_test": {"ndcg_at_1": 0.57108, "ndcg_at_3": 0.67493, "ndcg_at_5": 0.70361, "ndcg_at_10": 0.72693, "ndcg_at_20": 0.73559, "ndcg_at_50": 0.74195, "ndcg_at_100": 0.74529, "map_at_1": 0.57108, "map_at_3": 0.64895, "map_at_5": 0.6648, "map_at_10": 0.67439, "map_at_20": 0.6768, "map_at_50": 0.67786, "map_at_100": 0.67815, "recall_at_1": 0.57108, "recall_at_3": 0.7503, "recall_at_5": 0.82017, "recall_at_10": 0.89247, "recall_at_20": 0.92649, "recall_at_50": 0.95808, "recall_at_100": 0.97874, "precision_at_1": 0.57108, "precision_at_3": 0.2501, "precision_at_5": 0.16403, "precision_at_10": 0.08925, "precision_at_20": 0.04632, "precision_at_50": 0.01916, "precision_at_100": 0.00979, "mrr_at_1": 0.56865127582017, "mrr_at_3": 0.6471243418388012, "mrr_at_5": 0.6632239773187526, "mrr_at_10": 0.6727636984319852, "mrr_at_20": 0.6753542309195802, "mrr_at_50": 0.6765612284057695, "mrr_at_100": 0.6767635994564822, "naucs_at_1_max": 0.19627696906414918, "naucs_at_1_std": 0.25490113312887763, "naucs_at_1_diff1": 0.7311472112111653, "naucs_at_3_max": 0.12505762179060695, "naucs_at_3_std": 0.3250883135485268, "naucs_at_3_diff1": 0.6368932102920861, "naucs_at_5_max": 0.12681693174662004, "naucs_at_5_std": 0.36553579145484827, "naucs_at_5_diff1": 0.5963185435608184, "naucs_at_10_max": 0.2443283094718615, "naucs_at_10_std": 0.5378975291557723, "naucs_at_10_diff1": 0.6056682957261833, "naucs_at_20_max": 0.2941297289999579, "naucs_at_20_std": 0.5490669907768836, "naucs_at_20_diff1": 0.5965035030640417, "naucs_at_50_max": 0.21733999338436122, "naucs_at_50_std": 0.5631005588549655, "naucs_at_50_diff1": 0.6097410948123246, "naucs_at_100_max": 0.21831800388731984, "naucs_at_100_std": 0.710384903173119, "naucs_at_100_diff1": 0.6734222845071824}, "./data_dir/eval_vidore/shiftproject_test": {"ndcg_at_1": 0.63, "ndcg_at_3": 0.74071, "ndcg_at_5": 0.77385, "ndcg_at_10": 0.78346, "ndcg_at_20": 0.78886, "ndcg_at_50": 0.79529, "ndcg_at_100": 0.79852, "map_at_1": 0.63, "map_at_3": 0.71333, "map_at_5": 0.73183, "map_at_10": 0.73575, "map_at_20": 0.73742, "map_at_50": 0.73865, "map_at_100": 0.73894, "recall_at_1": 0.63, "recall_at_3": 0.82, "recall_at_5": 0.9, "recall_at_10": 0.93, "recall_at_20": 0.95, "recall_at_50": 0.98, "recall_at_100": 1.0, "precision_at_1": 0.63, "precision_at_3": 0.27333, "precision_at_5": 0.18, "precision_at_10": 0.093, "precision_at_20": 0.0475, "precision_at_50": 0.0196, "precision_at_100": 0.01, "mrr_at_1": 0.63, "mrr_at_3": 0.7183333333333333, "mrr_at_5": 0.7348333333333333, "mrr_at_10": 0.7408611111111111, "mrr_at_20": 0.741361111111111, "mrr_at_50": 0.7421598822324629, "mrr_at_100": 0.7424503305755428, "naucs_at_1_max": -0.0974004606778548, "naucs_at_1_std": -0.25468904244817375, "naucs_at_1_diff1": 0.6640185524687, "naucs_at_3_max": -0.3256691265557873, "naucs_at_3_std": -0.5354389249917381, "naucs_at_3_diff1": 0.624628263024562, "naucs_at_5_max": -0.22777777777777553, "naucs_at_5_std": -0.5987861811391184, "naucs_at_5_diff1": 0.46909430438842176, "naucs_at_10_max": -0.18354008269974378, "naucs_at_10_std": -0.4598506069094287, "naucs_at_10_diff1": 0.47258903561424775, "naucs_at_20_max": -0.1884220354808507, "naucs_at_20_std": -0.3007469654528384, "naucs_at_20_diff1": 0.4926237161531324, "naucs_at_50_max": 0.5401493930905731, "naucs_at_50_std": -0.22035480859009582, "naucs_at_50_diff1": 0.19140989729225052, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN}, "./data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.97, "ndcg_at_3": 0.97, "ndcg_at_5": 0.97431, "ndcg_at_10": 0.9812, "ndcg_at_20": 0.9812, "ndcg_at_50": 0.9812, "ndcg_at_100": 0.9812, "map_at_1": 0.97, "map_at_3": 0.97, "map_at_5": 0.9725, "map_at_10": 0.9756, "map_at_20": 0.9756, "map_at_50": 0.9756, "map_at_100": 0.9756, "recall_at_1": 0.97, "recall_at_3": 0.97, "recall_at_5": 0.98, "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": 0.32333, "precision_at_5": 0.196, "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": 0.9733333333333333, "mrr_at_5": 0.9733333333333333, "mrr_at_10": 0.9764285714285714, "mrr_at_20": 0.9764285714285714, "mrr_at_50": 0.9764285714285714, "mrr_at_100": 0.9764285714285714, "naucs_at_1_max": 0.5659819483348937, "naucs_at_1_std": -0.7791783380018684, "naucs_at_1_diff1": 0.9564270152505465, "naucs_at_3_max": 0.5659819483348902, "naucs_at_3_std": -0.7791783380018689, "naucs_at_3_diff1": 0.9564270152505466, "naucs_at_5_max": 0.9346405228758136, "naucs_at_5_std": -0.5929038281979465, "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/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.95786, "ndcg_at_5": 0.96216, "ndcg_at_10": 0.96216, "ndcg_at_20": 0.96216, "ndcg_at_50": 0.96216, "ndcg_at_100": 0.96216, "map_at_1": 0.91, "map_at_3": 0.94667, "map_at_5": 0.94917, "map_at_10": 0.94917, "map_at_20": 0.94917, "map_at_50": 0.94917, "map_at_100": 0.94917, "recall_at_1": 0.91, "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": 0.91, "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": 0.91, "mrr_at_3": 0.9466666666666668, "mrr_at_5": 0.9491666666666667, "mrr_at_10": 0.9491666666666667, "mrr_at_20": 0.9491666666666667, "mrr_at_50": 0.9491666666666667, "mrr_at_100": 0.9491666666666667, "naucs_at_1_max": 0.3833903931943138, "naucs_at_1_std": 0.48848428260192905, "naucs_at_1_diff1": 0.8264861500155604, "naucs_at_3_max": 1.0, "naucs_at_3_std": 0.8692810457516356, "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/arxivqa_test_subsampled": {"ndcg_at_1": 0.776, "ndcg_at_3": 0.81376, "ndcg_at_5": 0.83037, "ndcg_at_10": 0.84451, "ndcg_at_20": 0.85313, "ndcg_at_50": 0.85831, "ndcg_at_100": 0.85992, "map_at_1": 0.776, "map_at_3": 0.80467, "map_at_5": 0.81397, "map_at_10": 0.81973, "map_at_20": 0.82211, "map_at_50": 0.82294, "map_at_100": 0.82308, "recall_at_1": 0.776, "recall_at_3": 0.84, "recall_at_5": 0.88, "recall_at_10": 0.924, "recall_at_20": 0.958, "recall_at_50": 0.984, "recall_at_100": 0.994, "precision_at_1": 0.776, "precision_at_3": 0.28, "precision_at_5": 0.176, "precision_at_10": 0.0924, "precision_at_20": 0.0479, "precision_at_50": 0.01968, "precision_at_100": 0.00994, "mrr_at_1": 0.774, "mrr_at_3": 0.8046666666666666, "mrr_at_5": 0.8133666666666667, "mrr_at_10": 0.8186833333333333, "mrr_at_20": 0.8212445641733567, "mrr_at_50": 0.8219611912851504, "mrr_at_100": 0.8221248888102938, "naucs_at_1_max": 0.6541204220072772, "naucs_at_1_std": -0.004310581265656427, "naucs_at_1_diff1": 0.9333299811669199, "naucs_at_3_max": 0.6774423171330395, "naucs_at_3_std": 0.02982326951399226, "naucs_at_3_diff1": 0.9019698085419732, "naucs_at_5_max": 0.7342904867960547, "naucs_at_5_std": 0.12409322303531663, "naucs_at_5_diff1": 0.9104756601972646, "naucs_at_10_max": 0.7714383999213704, "naucs_at_10_std": 0.19174160892426748, "naucs_at_10_diff1": 0.9069978868740466, "naucs_at_20_max": 0.7963629896402987, "naucs_at_20_std": 0.374772131074646, "naucs_at_20_diff1": 0.8955137610599756, "naucs_at_50_max": 0.8293067226890712, "naucs_at_50_std": 0.8605275443510737, "naucs_at_50_diff1": 0.9183006535947711, "naucs_at_100_max": 0.6934329287270289, "naucs_at_100_std": 0.8078120136943184, "naucs_at_100_diff1": 0.9128540305010608}, "./data_dir/eval_vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.49446, "ndcg_at_3": 0.56477, "ndcg_at_5": 0.58452, "ndcg_at_10": 0.59669, "ndcg_at_20": 0.60668, "ndcg_at_50": 0.61757, "ndcg_at_100": 0.62554, "map_at_1": 0.49446, "map_at_3": 0.54767, "map_at_5": 0.55843, "map_at_10": 0.56343, "map_at_20": 0.56612, "map_at_50": 0.56802, "map_at_100": 0.56873, "recall_at_1": 0.49446, "recall_at_3": 0.61419, "recall_at_5": 0.66297, "recall_at_10": 0.70067, "recall_at_20": 0.74058, "recall_at_50": 0.79379, "recall_at_100": 0.84257, "precision_at_1": 0.49446, "precision_at_3": 0.20473, "precision_at_5": 0.13259, "precision_at_10": 0.07007, "precision_at_20": 0.03703, "precision_at_50": 0.01588, "precision_at_100": 0.00843, "mrr_at_1": 0.49889135254988914, "mrr_at_3": 0.5447154471544715, "mrr_at_5": 0.5566888396156688, "mrr_at_10": 0.5629526977087953, "mrr_at_20": 0.5652806848414477, "mrr_at_50": 0.5670115584789515, "mrr_at_100": 0.5677538817333595, "naucs_at_1_max": -0.27864580796328964, "naucs_at_1_std": 0.7722092976730863, "naucs_at_1_diff1": 0.8943248317988693, "naucs_at_3_max": -0.44768791859908297, "naucs_at_3_std": 0.8209416026426787, "naucs_at_3_diff1": 0.8513206720284808, "naucs_at_5_max": -0.5206642942420097, "naucs_at_5_std": 0.8590967813938516, "naucs_at_5_diff1": 0.8553385206717447, "naucs_at_10_max": -0.5861667680971102, "naucs_at_10_std": 0.8921235191636205, "naucs_at_10_diff1": 0.8508472594083637, "naucs_at_20_max": -0.6153314648071393, "naucs_at_20_std": 0.8966962245596599, "naucs_at_20_diff1": 0.8514213312670023, "naucs_at_50_max": -0.7316708344718492, "naucs_at_50_std": 0.8827437458106799, "naucs_at_50_diff1": 0.8348654637400126, "naucs_at_100_max": -0.890172253801331, "naucs_at_100_std": 0.8797216559719966, "naucs_at_100_diff1": 0.8182326755467386}, "./data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96524, "ndcg_at_5": 0.96911, "ndcg_at_10": 0.96911, "ndcg_at_20": 0.96911, "ndcg_at_50": 0.96911, "ndcg_at_100": 0.96911, "map_at_1": 0.93, "map_at_3": 0.95667, "map_at_5": 0.95867, "map_at_10": 0.95867, "map_at_20": 0.95867, "map_at_50": 0.95867, "map_at_100": 0.95867, "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_50": 1.0, "recall_at_100": 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_50": 0.02, "precision_at_100": 0.01, "mrr_at_1": 0.94, "mrr_at_3": 0.9616666666666667, "mrr_at_5": 0.9641666666666667, "mrr_at_10": 0.9641666666666667, "mrr_at_20": 0.9641666666666667, "mrr_at_50": 0.9641666666666667, "mrr_at_100": 0.9641666666666667, "naucs_at_1_max": 0.5512204881952787, "naucs_at_1_std": -0.5522875816993494, "naucs_at_1_diff1": 0.9626517273576113, "naucs_at_3_max": -0.5634920634921204, "naucs_at_3_std": -1.7399626517274398, "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_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/infovqa_test_subsampled": {"ndcg_at_1": 0.79757, "ndcg_at_3": 0.84618, "ndcg_at_5": 0.85716, "ndcg_at_10": 0.86704, "ndcg_at_20": 0.86964, "ndcg_at_50": 0.87372, "ndcg_at_100": 0.87532, "map_at_1": 0.79757, "map_at_3": 0.83367, "map_at_5": 0.83984, "map_at_10": 0.84396, "map_at_20": 0.84469, "map_at_50": 0.84538, "map_at_100": 0.8455, "recall_at_1": 0.79757, "recall_at_3": 0.88259, "recall_at_5": 0.90891, "recall_at_10": 0.93927, "recall_at_20": 0.94939, "recall_at_50": 0.96964, "recall_at_100": 0.97976, "precision_at_1": 0.79757, "precision_at_3": 0.2942, "precision_at_5": 0.18178, "precision_at_10": 0.09393, "precision_at_20": 0.04747, "precision_at_50": 0.01939, "precision_at_100": 0.0098, "mrr_at_1": 0.7894736842105263, "mrr_at_3": 0.8306342780026991, "mrr_at_5": 0.8363022941970311, "mrr_at_10": 0.8404167469956944, "mrr_at_20": 0.8411396743317877, "mrr_at_50": 0.8418165179225722, "mrr_at_100": 0.8419436154362733, "naucs_at_1_max": 0.5658752085914066, "naucs_at_1_std": 0.08703668327449693, "naucs_at_1_diff1": 0.8969893821656988, "naucs_at_3_max": 0.5035089171640572, "naucs_at_3_std": 0.10634666680591591, "naucs_at_3_diff1": 0.8617291252020982, "naucs_at_5_max": 0.672890311854327, "naucs_at_5_std": 0.2917197093395984, "naucs_at_5_diff1": 0.8715729540210408, "naucs_at_10_max": 0.7402193471144418, "naucs_at_10_std": 0.3670976593963592, "naucs_at_10_diff1": 0.8958712928076012, "naucs_at_20_max": 0.7849669612599903, "naucs_at_20_std": 0.5713453092645688, "naucs_at_20_diff1": 0.8802696095317121, "naucs_at_50_max": 0.7192418710631517, "naucs_at_50_std": 0.7316569995970472, "naucs_at_50_diff1": 0.8624988164249825, "naucs_at_100_max": 0.6626137244104312, "naucs_at_100_std": 0.8415749940072255, "naucs_at_100_diff1": 0.8476419892262101}, "./data_dir/eval_vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.94, "ndcg_at_3": 0.94631, "ndcg_at_5": 0.95405, "ndcg_at_10": 0.95405, "ndcg_at_20": 0.95684, "ndcg_at_50": 0.95902, "ndcg_at_100": 0.96074, "map_at_1": 0.94, "map_at_3": 0.945, "map_at_5": 0.949, "map_at_10": 0.949, "map_at_20": 0.94991, "map_at_50": 0.95034, "map_at_100": 0.95053, "recall_at_1": 0.94, "recall_at_3": 0.95, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_50": 0.99, "recall_at_100": 1.0, "precision_at_1": 0.94, "precision_at_3": 0.31667, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_50": 0.0198, "precision_at_100": 0.01, "mrr_at_1": 0.94, "mrr_at_3": 0.945, "mrr_at_5": 0.9490000000000001, "mrr_at_10": 0.950111111111111, "mrr_at_20": 0.950111111111111, "mrr_at_50": 0.9505873015873015, "mrr_at_100": 0.9507724867724867, "naucs_at_1_max": 0.5278555866791174, "naucs_at_1_std": -0.5602240896358519, "naucs_at_1_diff1": 0.9782135076252712, "naucs_at_3_max": 0.4595704948646117, "naucs_at_3_std": -0.7438842203548082, "naucs_at_3_diff1": 0.973856209150328, "naucs_at_5_max": 0.4352629940865253, "naucs_at_5_std": -0.8445378151260495, "naucs_at_5_diff1": 0.9564270152505424, "naucs_at_10_max": 0.4352629940865253, "naucs_at_10_std": -0.8445378151260495, "naucs_at_10_diff1": 0.9564270152505424, "naucs_at_20_max": 0.9346405228758136, "naucs_at_20_std": -0.3968253968253954, "naucs_at_20_diff1": 1.0, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.35807656395892007, "naucs_at_50_diff1": 1.0, "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": 0.81429, "ndcg_at_3": 0.86688, "ndcg_at_5": 0.87441, "ndcg_at_10": 0.88583, "ndcg_at_20": 0.89213, "ndcg_at_50": 0.89426, "ndcg_at_100": 0.89548, "map_at_1": 0.81429, "map_at_3": 0.85417, "map_at_5": 0.85845, "map_at_10": 0.8631, "map_at_20": 0.86482, "map_at_50": 0.86516, "map_at_100": 0.86528, "recall_at_1": 0.81429, "recall_at_3": 0.90357, "recall_at_5": 0.92143, "recall_at_10": 0.95714, "recall_at_20": 0.98214, "recall_at_50": 0.99286, "recall_at_100": 1.0, "precision_at_1": 0.81429, "precision_at_3": 0.30119, "precision_at_5": 0.18429, "precision_at_10": 0.09571, "precision_at_20": 0.04911, "precision_at_50": 0.01986, "precision_at_100": 0.01, "mrr_at_1": 0.8142857142857143, "mrr_at_3": 0.8535714285714285, "mrr_at_5": 0.8576785714285714, "mrr_at_10": 0.8620280612244897, "mrr_at_20": 0.8640784760874046, "mrr_at_50": 0.8644115436805921, "mrr_at_100": 0.8645378286859094, "naucs_at_1_max": 0.5099174501261181, "naucs_at_1_std": 0.10524153481617399, "naucs_at_1_diff1": 0.8698884048001222, "naucs_at_3_max": 0.5539647957948607, "naucs_at_3_std": 0.17413632119514313, "naucs_at_3_diff1": 0.8326416986547719, "naucs_at_5_max": 0.478800611153553, "naucs_at_5_std": 0.10332314744079385, "naucs_at_5_diff1": 0.8250572956455312, "naucs_at_10_max": 0.6088935574229674, "naucs_at_10_std": 0.23650015561779797, "naucs_at_10_diff1": 0.8465608465608483, "naucs_at_20_max": 0.8216619981325874, "naucs_at_20_std": 0.6112044817927197, "naucs_at_20_diff1": 0.7984126984127048, "naucs_at_50_max": 1.0, "naucs_at_50_std": 0.9346405228758071, "naucs_at_50_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0}}
|