Upload results_tsystems-colqwen2.5-3b-multilingual-v1.0_vidore_benchmark_collection.json
Browse files
results_tsystems-colqwen2.5-3b-multilingual-v1.0_vidore_benchmark_collection.json
ADDED
@@ -0,0 +1,589 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"timestamp": "2025-03-09T16:34:55.435464",
|
4 |
+
"vidore_benchmark_version": "0.1.dev293+g9358cf6"
|
5 |
+
},
|
6 |
+
"metrics": {
|
7 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {"ndcg_at_1": 0.625, "ndcg_at_3": 0.63378, "ndcg_at_5": 0.65347, "ndcg_at_10": 0.6786, "ndcg_at_20": 0.71203, "ndcg_at_50": 0.73102, "ndcg_at_100": 0.74123, "map_at_1": 0.39121, "map_at_3": 0.5227, "map_at_5": 0.56225, "map_at_10": 0.59469, "map_at_20": 0.61309, "map_at_50": 0.62037, "map_at_100": 0.62289, "recall_at_1": 0.39121, "recall_at_3": 0.59737, "recall_at_5": 0.68129, "recall_at_10": 0.75444, "recall_at_20": 0.84735, "recall_at_50": 0.90199, "recall_at_100": 0.93641, "precision_at_1": 0.625, "precision_at_3": 0.38542, "precision_at_5": 0.29, "precision_at_10": 0.1825, "precision_at_20": 0.11063, "precision_at_50": 0.05125, "precision_at_100": 0.02812, "mrr_at_1": 0.6, "mrr_at_3": 0.7093749999999999, "mrr_at_5": 0.72, "mrr_at_10": 0.7268204365079365, "mrr_at_20": 0.7292081176262679, "mrr_at_50": 0.7294236348676472, "mrr_at_100": 0.7295438271753395, "naucs_at_1_max": 0.25742286046962914, "naucs_at_1_std": -0.14400349311080918, "naucs_at_1_diff1": 0.42325829613817234, "naucs_at_3_max": -0.02048224143318386, "naucs_at_3_std": -0.04757316946151454, "naucs_at_3_diff1": -0.10976460785334881, "naucs_at_5_max": -0.06722396249807405, "naucs_at_5_std": -0.024300690323006423, "naucs_at_5_diff1": -0.20257789059003908, "naucs_at_10_max": -0.12362188498167358, "naucs_at_10_std": -0.010092683908130212, "naucs_at_10_diff1": -0.2593652943167933, "naucs_at_20_max": -0.17010775572774514, "naucs_at_20_std": 0.01843266871971254, "naucs_at_20_diff1": -0.30267122927905377, "naucs_at_50_max": -0.2100729793775826, "naucs_at_50_std": 0.09677241700523359, "naucs_at_50_diff1": -0.3257432472833357, "naucs_at_100_max": -0.249160863302171, "naucs_at_100_std": 0.1262607846915956, "naucs_at_100_diff1": -0.3596440757157095}, "vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {"ndcg_at_1": 0.56897, "ndcg_at_3": 0.55714, "ndcg_at_5": 0.54782, "ndcg_at_10": 0.56373, "ndcg_at_20": 0.57742, "ndcg_at_50": 0.65441, "ndcg_at_100": 0.68555, "map_at_1": 0.07314, "map_at_3": 0.17119, "map_at_5": 0.23415, "map_at_10": 0.31416, "map_at_20": 0.36504, "map_at_50": 0.42965, "map_at_100": 0.4549, "recall_at_1": 0.07314, "recall_at_3": 0.20505, "recall_at_5": 0.30316, "recall_at_10": 0.4773, "recall_at_20": 0.59656, "recall_at_50": 0.81741, "recall_at_100": 0.91015, "precision_at_1": 0.56897, "precision_at_3": 0.52874, "precision_at_5": 0.49655, "precision_at_10": 0.42414, "precision_at_20": 0.30776, "precision_at_50": 0.19793, "precision_at_100": 0.12621, "mrr_at_1": 0.5689655172413793, "mrr_at_3": 0.6954022988505748, "mrr_at_5": 0.7160919540229886, "mrr_at_10": 0.7247126436781609, "mrr_at_20": 0.7270114942528735, "mrr_at_50": 0.7270114942528735, "mrr_at_100": 0.7270114942528735, "naucs_at_1_max": 0.21067669634700478, "naucs_at_1_std": 0.1973913874534294, "naucs_at_1_diff1": 0.07471804040416491, "naucs_at_3_max": 0.25293486951628225, "naucs_at_3_std": 0.16322512894107372, "naucs_at_3_diff1": 0.08261338662774292, "naucs_at_5_max": 0.11797873815270753, "naucs_at_5_std": 0.12735237839765626, "naucs_at_5_diff1": -0.07293175765432203, "naucs_at_10_max": 0.1297569898852053, "naucs_at_10_std": 0.16373258397253945, "naucs_at_10_diff1": -0.14160027188301702, "naucs_at_20_max": 0.12527454625310325, "naucs_at_20_std": 0.16482436842599318, "naucs_at_20_diff1": -0.08778057388499196, "naucs_at_50_max": 0.08683499944417812, "naucs_at_50_std": 0.12275733623461196, "naucs_at_50_diff1": -0.002301806368489772, "naucs_at_100_max": 0.0011120669499529632, "naucs_at_100_std": 0.054821704719591476, "naucs_at_100_diff1": -0.009725835440763952}, "vidore/synthetic_rse_restaurant_filtered_v1.0": {"ndcg_at_1": 0.42105, "ndcg_at_3": 0.44906, "ndcg_at_5": 0.51661, "ndcg_at_10": 0.58374, "ndcg_at_20": 0.61856, "ndcg_at_50": 0.64511, "ndcg_at_100": 0.65848, "map_at_1": 0.21798, "map_at_3": 0.33277, "map_at_5": 0.39992, "map_at_10": 0.457, "map_at_20": 0.47874, "map_at_50": 0.49282, "map_at_100": 0.49821, "recall_at_1": 0.21798, "recall_at_3": 0.42325, "recall_at_5": 0.58956, "recall_at_10": 0.75917, "recall_at_20": 0.86602, "recall_at_50": 0.93285, "recall_at_100": 0.98026, "precision_at_1": 0.42105, "precision_at_3": 0.30994, "precision_at_5": 0.27719, "precision_at_10": 0.20702, "precision_at_20": 0.12895, "precision_at_50": 0.06947, "precision_at_100": 0.0386, "mrr_at_1": 0.3684210526315789, "mrr_at_3": 0.5263157894736842, "mrr_at_5": 0.5517543859649122, "mrr_at_10": 0.5667362851573378, "mrr_at_20": 0.571009789430842, "mrr_at_50": 0.571009789430842, "mrr_at_100": 0.571009789430842, "naucs_at_1_max": -0.08150044082579858, "naucs_at_1_std": -0.03923680144624444, "naucs_at_1_diff1": 0.30751934172500794, "naucs_at_3_max": -0.03769302754359695, "naucs_at_3_std": 0.04797783592287287, "naucs_at_3_diff1": 0.16557925905582654, "naucs_at_5_max": -0.09946781385204509, "naucs_at_5_std": 0.03991758007715041, "naucs_at_5_diff1": 0.1466426068147725, "naucs_at_10_max": -0.23814028940918253, "naucs_at_10_std": -0.08419025453995246, "naucs_at_10_diff1": 0.0262882685010371, "naucs_at_20_max": -0.3529381371421357, "naucs_at_20_std": -0.19372687870613367, "naucs_at_20_diff1": -0.11623873880779917, "naucs_at_50_max": -0.3677332592832498, "naucs_at_50_std": -0.2258078729275452, "naucs_at_50_diff1": -0.23025855390363398, "naucs_at_100_max": -0.3691287090976769, "naucs_at_100_std": -0.21870171092074447, "naucs_at_100_diff1": -0.280256891874517}, "vidore/synthetic_axa_filtered_v1.0": {"ndcg_at_1": 0.77778, "ndcg_at_3": 0.70073, "ndcg_at_5": 0.69272, "ndcg_at_10": 0.72099, "ndcg_at_20": 0.74666, "ndcg_at_50": 0.78266, "ndcg_at_100": 0.80204, "map_at_1": 0.42233, "map_at_3": 0.48129, "map_at_5": 0.53468, "map_at_10": 0.60332, "map_at_20": 0.63606, "map_at_50": 0.6598, "map_at_100": 0.6635, "recall_at_1": 0.42233, "recall_at_3": 0.49384, "recall_at_5": 0.56767, "recall_at_10": 0.72369, "recall_at_20": 0.82221, "recall_at_50": 0.9004, "recall_at_100": 0.98955, "precision_at_1": 0.77778, "precision_at_3": 0.44444, "precision_at_5": 0.37778, "precision_at_10": 0.28889, "precision_at_20": 0.175, "precision_at_50": 0.08778, "precision_at_100": 0.04667, "mrr_at_1": 0.7222222222222222, "mrr_at_3": 0.8055555555555556, "mrr_at_5": 0.8055555555555556, "mrr_at_10": 0.8117283950617283, "mrr_at_20": 0.8117283950617283, "mrr_at_50": 0.8117283950617283, "mrr_at_100": 0.8127204585537918, "naucs_at_1_max": 0.032908823460004816, "naucs_at_1_std": 0.1208523759704863, "naucs_at_1_diff1": 0.4103770245502531, "naucs_at_3_max": -0.5791247248908119, "naucs_at_3_std": -0.30939312876418795, "naucs_at_3_diff1": -0.11892142096286706, "naucs_at_5_max": -0.5656227555698552, "naucs_at_5_std": -0.3144734850512628, "naucs_at_5_diff1": -0.11074261204589309, "naucs_at_10_max": -0.7315123238409165, "naucs_at_10_std": -0.29227628600844874, "naucs_at_10_diff1": -0.24501059333410422, "naucs_at_20_max": -0.7422260882284083, "naucs_at_20_std": -0.309352965967354, "naucs_at_20_diff1": -0.28168147686205885, "naucs_at_50_max": -0.6957529396254553, "naucs_at_50_std": -0.2118189031711075, "naucs_at_50_diff1": -0.19680255262954957, "naucs_at_100_max": -0.6847144194483713, "naucs_at_100_std": -0.2295503118683743, "naucs_at_100_diff1": -0.21530026683670947}, "vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {"ndcg_at_1": 0.4693, "ndcg_at_3": 0.47581, "ndcg_at_5": 0.53334, "ndcg_at_10": 0.60221, "ndcg_at_20": 0.63978, "ndcg_at_50": 0.66714, "ndcg_at_100": 0.67944, "map_at_1": 0.25877, "map_at_3": 0.36425, "map_at_5": 0.42918, "map_at_10": 0.48488, "map_at_20": 0.50717, "map_at_50": 0.52147, "map_at_100": 0.52715, "recall_at_1": 0.25877, "recall_at_3": 0.44371, "recall_at_5": 0.58474, "recall_at_10": 0.76245, "recall_at_20": 0.87253, "recall_at_50": 0.94497, "recall_at_100": 0.983, "precision_at_1": 0.4693, "precision_at_3": 0.31579, "precision_at_5": 0.27632, "precision_at_10": 0.20351, "precision_at_20": 0.12939, "precision_at_50": 0.06895, "precision_at_100": 0.03851, "mrr_at_1": 0.4517543859649123, "mrr_at_3": 0.5679824561403509, "mrr_at_5": 0.5914473684210527, "mrr_at_10": 0.6053379977722083, "mrr_at_20": 0.610436247667896, "mrr_at_50": 0.6105487083066724, "mrr_at_100": 0.610593010982554, "naucs_at_1_max": -0.0032763618982571546, "naucs_at_1_std": -0.04265362728852897, "naucs_at_1_diff1": 0.33787367107833005, "naucs_at_3_max": 0.06352930121600564, "naucs_at_3_std": 0.1206847845021258, "naucs_at_3_diff1": 0.22341748914306014, "naucs_at_5_max": 0.012060453628726792, "naucs_at_5_std": 0.07793057942781008, "naucs_at_5_diff1": 0.14002578592705445, "naucs_at_10_max": -0.07291427224405066, "naucs_at_10_std": 0.02725885332872106, "naucs_at_10_diff1": 0.039108418446936195, "naucs_at_20_max": -0.19200355565225224, "naucs_at_20_std": -0.0632407019801024, "naucs_at_20_diff1": -0.09163716416624872, "naucs_at_50_max": -0.2174588126867704, "naucs_at_50_std": -0.04761369806986984, "naucs_at_50_diff1": -0.20893523167133235, "naucs_at_100_max": -0.20472823218617445, "naucs_at_100_std": -0.01263906721329091, "naucs_at_100_diff1": -0.2470752658763323}, "vidore/synthetic_axa_filtered_v1.0_multilingual": {"ndcg_at_1": 0.63889, "ndcg_at_3": 0.59807, "ndcg_at_5": 0.59952, "ndcg_at_10": 0.61184, "ndcg_at_20": 0.65129, "ndcg_at_50": 0.70277, "ndcg_at_100": 0.72594, "map_at_1": 0.35152, "map_at_3": 0.41736, "map_at_5": 0.46326, "map_at_10": 0.51129, "map_at_20": 0.54607, "map_at_50": 0.57039, "map_at_100": 0.57609, "recall_at_1": 0.35152, "recall_at_3": 0.4472, "recall_at_5": 0.51546, "recall_at_10": 0.61331, "recall_at_20": 0.73582, "recall_at_50": 0.8751, "recall_at_100": 0.97216, "precision_at_1": 0.63889, "precision_at_3": 0.37963, "precision_at_5": 0.32778, "precision_at_10": 0.23611, "precision_at_20": 0.15694, "precision_at_50": 0.08389, "precision_at_100": 0.04611, "mrr_at_1": 0.5833333333333334, "mrr_at_3": 0.675925925925926, "mrr_at_5": 0.6863425925925927, "mrr_at_10": 0.6898699294532629, "mrr_at_20": 0.6931268577101911, "mrr_at_50": 0.6945504688213023, "mrr_at_100": 0.695467245281557, "naucs_at_1_max": 0.20559304441249548, "naucs_at_1_std": 0.33225812365052354, "naucs_at_1_diff1": 0.2494425783944826, "naucs_at_3_max": -0.1666348687765573, "naucs_at_3_std": -0.0005992816457949559, "naucs_at_3_diff1": -0.040196705405881335, "naucs_at_5_max": -0.25852583704596965, "naucs_at_5_std": -0.06197198551556286, "naucs_at_5_diff1": -0.09839193676342861, "naucs_at_10_max": -0.3236637978584169, "naucs_at_10_std": -0.017938292208914665, "naucs_at_10_diff1": -0.1897280855200544, "naucs_at_20_max": -0.40675605630454054, "naucs_at_20_std": -0.038948273071241074, "naucs_at_20_diff1": -0.21300773810654475, "naucs_at_50_max": -0.46071423380584564, "naucs_at_50_std": 0.003316964198679821, "naucs_at_50_diff1": -0.20742631158862873, "naucs_at_100_max": -0.48302121533638276, "naucs_at_100_std": -0.02257339920307775, "naucs_at_100_diff1": -0.23986195237093472}, "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {"ndcg_at_1": 0.58125, "ndcg_at_3": 0.59964, "ndcg_at_5": 0.61653, "ndcg_at_10": 0.64715, "ndcg_at_20": 0.67697, "ndcg_at_50": 0.70023, "ndcg_at_100": 0.7099, "map_at_1": 0.35556, "map_at_3": 0.48638, "map_at_5": 0.52353, "map_at_10": 0.5578, "map_at_20": 0.57476, "map_at_50": 0.58377, "map_at_100": 0.586, "recall_at_1": 0.35556, "recall_at_3": 0.56694, "recall_at_5": 0.6449, "recall_at_10": 0.73752, "recall_at_20": 0.81979, "recall_at_50": 0.88964, "recall_at_100": 0.92446, "precision_at_1": 0.58125, "precision_at_3": 0.37031, "precision_at_5": 0.27812, "precision_at_10": 0.17672, "precision_at_20": 0.10656, "precision_at_50": 0.05047, "precision_at_100": 0.02733, "mrr_at_1": 0.575, "mrr_at_3": 0.686458333333333, "mrr_at_5": 0.6988802083333328, "mrr_at_10": 0.7047377232142853, "mrr_at_20": 0.7069792573321496, "mrr_at_50": 0.7077243980518698, "mrr_at_100": 0.7078665562263524, "naucs_at_1_max": 0.204649483693431, "naucs_at_1_std": -0.07471914194116777, "naucs_at_1_diff1": 0.4235121561361923, "naucs_at_3_max": 0.10838604356014085, "naucs_at_3_std": -0.032223603946613624, "naucs_at_3_diff1": -0.0726850998935557, "naucs_at_5_max": 0.04868975397578592, "naucs_at_5_std": -0.026692316497247126, "naucs_at_5_diff1": -0.15723044600427544, "naucs_at_10_max": -0.014634672838583301, "naucs_at_10_std": -0.006914667371736347, "naucs_at_10_diff1": -0.2215599418061795, "naucs_at_20_max": -0.04321858791097813, "naucs_at_20_std": 0.03973908730406033, "naucs_at_20_diff1": -0.269405568696458, "naucs_at_50_max": -0.07787569567795065, "naucs_at_50_std": 0.08739793863557406, "naucs_at_50_diff1": -0.3044991611826985, "naucs_at_100_max": -0.10062921874859215, "naucs_at_100_std": 0.10740913637879311, "naucs_at_100_diff1": -0.3265063129151157}, "vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {"ndcg_at_1": 0.55603, "ndcg_at_3": 0.52794, "ndcg_at_5": 0.51211, "ndcg_at_10": 0.51968, "ndcg_at_20": 0.5468, "ndcg_at_50": 0.62812, "ndcg_at_100": 0.66252, "map_at_1": 0.06779, "map_at_3": 0.1579, "map_at_5": 0.20922, "map_at_10": 0.27847, "map_at_20": 0.33219, "map_at_50": 0.39606, "map_at_100": 0.42247, "recall_at_1": 0.06779, "recall_at_3": 0.2032, "recall_at_5": 0.28548, "recall_at_10": 0.43255, "recall_at_20": 0.57784, "recall_at_50": 0.80506, "recall_at_100": 0.90457, "precision_at_1": 0.55603, "precision_at_3": 0.49713, "precision_at_5": 0.45776, "precision_at_10": 0.39267, "precision_at_20": 0.29569, "precision_at_50": 0.19517, "precision_at_100": 0.12608, "mrr_at_1": 0.5560344827586207, "mrr_at_3": 0.6709770114942529, "mrr_at_5": 0.6908045977011494, "mrr_at_10": 0.7021004378762999, "mrr_at_20": 0.7044611434317317, "mrr_at_50": 0.7044611434317317, "mrr_at_100": 0.7044611434317317, "naucs_at_1_max": 0.12252594015795006, "naucs_at_1_std": 0.04032712959341147, "naucs_at_1_diff1": 0.299521257932423, "naucs_at_3_max": 0.1783194723097986, "naucs_at_3_std": 0.15795436980522737, "naucs_at_3_diff1": 0.13549315425520392, "naucs_at_5_max": 0.10720091449477931, "naucs_at_5_std": 0.11536706854130578, "naucs_at_5_diff1": 0.08426069339757927, "naucs_at_10_max": 0.07660682975236519, "naucs_at_10_std": 0.12758098060267584, "naucs_at_10_diff1": 0.02885931849244283, "naucs_at_20_max": 0.06173573896223077, "naucs_at_20_std": 0.1526676740300435, "naucs_at_20_diff1": 0.03721907205932031, "naucs_at_50_max": 0.035005108372197405, "naucs_at_50_std": 0.12278272118441529, "naucs_at_50_diff1": 0.023815094990020436, "naucs_at_100_max": 0.008104727507858567, "naucs_at_100_std": 0.09112073056582873, "naucs_at_100_diff1": 0.007004628382597912}, "vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.70513, "ndcg_at_3": 0.69207, "ndcg_at_5": 0.72093, "ndcg_at_10": 0.75477, "ndcg_at_20": 0.77073, "ndcg_at_50": 0.78593, "ndcg_at_100": 0.79155, "map_at_1": 0.49505, "map_at_3": 0.61455, "map_at_5": 0.66109, "map_at_10": 0.68841, "map_at_20": 0.69563, "map_at_50": 0.70138, "map_at_100": 0.70277, "recall_at_1": 0.49505, "recall_at_3": 0.66525, "recall_at_5": 0.77518, "recall_at_10": 0.84474, "recall_at_20": 0.89384, "recall_at_50": 0.95199, "recall_at_100": 0.97445, "precision_at_1": 0.73077, "precision_at_3": 0.38462, "precision_at_5": 0.28077, "precision_at_10": 0.175, "precision_at_20": 0.09712, "precision_at_50": 0.04308, "precision_at_100": 0.02269, "mrr_at_1": 0.6730769230769231, "mrr_at_3": 0.75, "mrr_at_5": 0.7663461538461538, "mrr_at_10": 0.7718406593406594, "mrr_at_20": 0.774720132808368, "mrr_at_50": 0.7752398833281186, "mrr_at_100": 0.7752398833281186, "naucs_at_1_max": 0.07450432208098738, "naucs_at_1_std": -0.1221585160396508, "naucs_at_1_diff1": 0.2418043211076284, "naucs_at_3_max": -0.13514324775574957, "naucs_at_3_std": -0.10634205434873391, "naucs_at_3_diff1": -0.2613333286838361, "naucs_at_5_max": -0.04946008996206912, "naucs_at_5_std": 0.037880149042777284, "naucs_at_5_diff1": -0.3511884965069251, "naucs_at_10_max": -0.09883516423910808, "naucs_at_10_std": 0.013232412769527718, "naucs_at_10_diff1": -0.3544207353216777, "naucs_at_20_max": -0.09016517756196715, "naucs_at_20_std": 0.015026938617059471, "naucs_at_20_diff1": -0.35536152309208796, "naucs_at_50_max": -0.16240739881229074, "naucs_at_50_std": -0.01665504021287616, "naucs_at_50_diff1": -0.3752326957547292, "naucs_at_100_max": -0.15927213243146954, "naucs_at_100_std": -0.02200053653311622, "naucs_at_100_diff1": -0.38431093213885725},
|
8 |
+
"vidore/arxivqa_test_subsampled": {
|
9 |
+
"ndcg_at_1": 0.896,
|
10 |
+
"ndcg_at_3": 0.9285,
|
11 |
+
"ndcg_at_5": 0.93409,
|
12 |
+
"ndcg_at_10": 0.93887,
|
13 |
+
"ndcg_at_20": 0.94191,
|
14 |
+
"ndcg_at_50": 0.94277,
|
15 |
+
"ndcg_at_100": 0.94346,
|
16 |
+
"map_at_1": 0.896,
|
17 |
+
"map_at_3": 0.921,
|
18 |
+
"map_at_5": 0.924,
|
19 |
+
"map_at_10": 0.92612,
|
20 |
+
"map_at_20": 0.92696,
|
21 |
+
"map_at_50": 0.92712,
|
22 |
+
"map_at_100": 0.92719,
|
23 |
+
"recall_at_1": 0.896,
|
24 |
+
"recall_at_3": 0.95,
|
25 |
+
"recall_at_5": 0.964,
|
26 |
+
"recall_at_10": 0.978,
|
27 |
+
"recall_at_20": 0.99,
|
28 |
+
"recall_at_50": 0.994,
|
29 |
+
"recall_at_100": 0.998,
|
30 |
+
"precision_at_1": 0.896,
|
31 |
+
"precision_at_3": 0.31667,
|
32 |
+
"precision_at_5": 0.1928,
|
33 |
+
"precision_at_10": 0.0978,
|
34 |
+
"precision_at_20": 0.0495,
|
35 |
+
"precision_at_50": 0.01988,
|
36 |
+
"precision_at_100": 0.00998,
|
37 |
+
"mrr_at_1": 0.896,
|
38 |
+
"mrr_at_3": 0.9213333333333332,
|
39 |
+
"mrr_at_5": 0.9240333333333333,
|
40 |
+
"mrr_at_10": 0.9264857142857141,
|
41 |
+
"mrr_at_20": 0.9274158230658229,
|
42 |
+
"mrr_at_50": 0.9274847885830643,
|
43 |
+
"mrr_at_100": 0.9275602871585629,
|
44 |
+
"naucs_at_1_max": 0.8456651988738907,
|
45 |
+
"naucs_at_1_std": -0.12317729011766297,
|
46 |
+
"naucs_at_1_diff1": 0.9409423951490659,
|
47 |
+
"naucs_at_3_max": 0.8706816059757188,
|
48 |
+
"naucs_at_3_std": 0.006965452847808854,
|
49 |
+
"naucs_at_3_diff1": 0.9522875816993475,
|
50 |
+
"naucs_at_5_max": 0.9080558149185568,
|
51 |
+
"naucs_at_5_std": -0.04549227098247105,
|
52 |
+
"naucs_at_5_diff1": 0.9555192447349298,
|
53 |
+
"naucs_at_10_max": 0.8866819455054739,
|
54 |
+
"naucs_at_10_std": -0.08407605466429298,
|
55 |
+
"naucs_at_10_diff1": 0.9762329174093952,
|
56 |
+
"naucs_at_20_max": 0.9477124183006524,
|
57 |
+
"naucs_at_20_std": 0.25144724556488873,
|
58 |
+
"naucs_at_20_diff1": 1.0,
|
59 |
+
"naucs_at_50_max": 0.9564270152505304,
|
60 |
+
"naucs_at_50_std": 0.4352629940865033,
|
61 |
+
"naucs_at_50_diff1": 1.0,
|
62 |
+
"naucs_at_100_max": 1.0,
|
63 |
+
"naucs_at_100_std": 1.0,
|
64 |
+
"naucs_at_100_diff1": 1.0
|
65 |
+
},
|
66 |
+
"vidore/docvqa_test_subsampled": {
|
67 |
+
"ndcg_at_1": 0.54324,
|
68 |
+
"ndcg_at_3": 0.60994,
|
69 |
+
"ndcg_at_5": 0.6398,
|
70 |
+
"ndcg_at_10": 0.66199,
|
71 |
+
"ndcg_at_20": 0.67267,
|
72 |
+
"ndcg_at_50": 0.68225,
|
73 |
+
"ndcg_at_100": 0.68945,
|
74 |
+
"map_at_1": 0.54324,
|
75 |
+
"map_at_3": 0.59387,
|
76 |
+
"map_at_5": 0.61027,
|
77 |
+
"map_at_10": 0.61899,
|
78 |
+
"map_at_20": 0.62193,
|
79 |
+
"map_at_50": 0.62343,
|
80 |
+
"map_at_100": 0.62407,
|
81 |
+
"recall_at_1": 0.54324,
|
82 |
+
"recall_at_3": 0.65632,
|
83 |
+
"recall_at_5": 0.72949,
|
84 |
+
"recall_at_10": 0.80044,
|
85 |
+
"recall_at_20": 0.84257,
|
86 |
+
"recall_at_50": 0.89135,
|
87 |
+
"recall_at_100": 0.9357,
|
88 |
+
"precision_at_1": 0.54324,
|
89 |
+
"precision_at_3": 0.21877,
|
90 |
+
"precision_at_5": 0.1459,
|
91 |
+
"precision_at_10": 0.08004,
|
92 |
+
"precision_at_20": 0.04213,
|
93 |
+
"precision_at_50": 0.01783,
|
94 |
+
"precision_at_100": 0.00936,
|
95 |
+
"mrr_at_1": 0.5432372505543237,
|
96 |
+
"mrr_at_3": 0.5946045824094608,
|
97 |
+
"mrr_at_5": 0.6103473762010347,
|
98 |
+
"mrr_at_10": 0.6190493788054763,
|
99 |
+
"mrr_at_20": 0.6220782499013536,
|
100 |
+
"mrr_at_50": 0.623690385474884,
|
101 |
+
"mrr_at_100": 0.624317545713404,
|
102 |
+
"naucs_at_1_max": 0.5195120835206619,
|
103 |
+
"naucs_at_1_std": -0.31481029514111575,
|
104 |
+
"naucs_at_1_diff1": 0.8886195631998732,
|
105 |
+
"naucs_at_3_max": 0.4894265436758743,
|
106 |
+
"naucs_at_3_std": -0.35348286092835673,
|
107 |
+
"naucs_at_3_diff1": 0.825360351363726,
|
108 |
+
"naucs_at_5_max": 0.49365870598559275,
|
109 |
+
"naucs_at_5_std": -0.3667256163548182,
|
110 |
+
"naucs_at_5_diff1": 0.8190874936930554,
|
111 |
+
"naucs_at_10_max": 0.49415281281253026,
|
112 |
+
"naucs_at_10_std": -0.1787227124233066,
|
113 |
+
"naucs_at_10_diff1": 0.760124698410118,
|
114 |
+
"naucs_at_20_max": 0.4624420442016527,
|
115 |
+
"naucs_at_20_std": -0.14955421166412503,
|
116 |
+
"naucs_at_20_diff1": 0.7582711922759812,
|
117 |
+
"naucs_at_50_max": 0.46372165402671495,
|
118 |
+
"naucs_at_50_std": -0.009043079292315782,
|
119 |
+
"naucs_at_50_diff1": 0.7459081960812681,
|
120 |
+
"naucs_at_100_max": 0.41099442703800165,
|
121 |
+
"naucs_at_100_std": 0.4785954026968201,
|
122 |
+
"naucs_at_100_diff1": 0.7044383203056372
|
123 |
+
},
|
124 |
+
"vidore/infovqa_test_subsampled": {
|
125 |
+
"ndcg_at_1": 0.89676,
|
126 |
+
"ndcg_at_3": 0.92534,
|
127 |
+
"ndcg_at_5": 0.93031,
|
128 |
+
"ndcg_at_10": 0.935,
|
129 |
+
"ndcg_at_20": 0.93663,
|
130 |
+
"ndcg_at_50": 0.93904,
|
131 |
+
"ndcg_at_100": 0.94001,
|
132 |
+
"map_at_1": 0.89676,
|
133 |
+
"map_at_3": 0.91903,
|
134 |
+
"map_at_5": 0.92176,
|
135 |
+
"map_at_10": 0.92376,
|
136 |
+
"map_at_20": 0.92426,
|
137 |
+
"map_at_50": 0.92465,
|
138 |
+
"map_at_100": 0.92473,
|
139 |
+
"recall_at_1": 0.89676,
|
140 |
+
"recall_at_3": 0.94332,
|
141 |
+
"recall_at_5": 0.95547,
|
142 |
+
"recall_at_10": 0.96964,
|
143 |
+
"recall_at_20": 0.97571,
|
144 |
+
"recall_at_50": 0.98785,
|
145 |
+
"recall_at_100": 0.99393,
|
146 |
+
"precision_at_1": 0.89676,
|
147 |
+
"precision_at_3": 0.31444,
|
148 |
+
"precision_at_5": 0.19109,
|
149 |
+
"precision_at_10": 0.09696,
|
150 |
+
"precision_at_20": 0.04879,
|
151 |
+
"precision_at_50": 0.01976,
|
152 |
+
"precision_at_100": 0.00994,
|
153 |
+
"mrr_at_1": 0.8967611336032388,
|
154 |
+
"mrr_at_3": 0.9183535762483129,
|
155 |
+
"mrr_at_5": 0.9206815114709849,
|
156 |
+
"mrr_at_10": 0.9232191054559475,
|
157 |
+
"mrr_at_20": 0.9235380847222951,
|
158 |
+
"mrr_at_50": 0.9239302146072342,
|
159 |
+
"mrr_at_100": 0.9240125185515768,
|
160 |
+
"naucs_at_1_max": 0.7062394427119798,
|
161 |
+
"naucs_at_1_std": -0.2812879238976883,
|
162 |
+
"naucs_at_1_diff1": 0.9410064894465787,
|
163 |
+
"naucs_at_3_max": 0.7564908149226892,
|
164 |
+
"naucs_at_3_std": -0.3059756682732854,
|
165 |
+
"naucs_at_3_diff1": 0.9422566807977654,
|
166 |
+
"naucs_at_5_max": 0.84758972902799,
|
167 |
+
"naucs_at_5_std": -0.0929285302133143,
|
168 |
+
"naucs_at_5_diff1": 0.9450692388254637,
|
169 |
+
"naucs_at_10_max": 0.8860131032188592,
|
170 |
+
"naucs_at_10_std": 0.24420167069765694,
|
171 |
+
"naucs_at_10_diff1": 0.9368484108193146,
|
172 |
+
"naucs_at_20_max": 0.8806609405034168,
|
173 |
+
"naucs_at_20_std": 0.28312028971462133,
|
174 |
+
"naucs_at_20_diff1": 0.9428274225349419,
|
175 |
+
"naucs_at_50_max": 0.78308879001761,
|
176 |
+
"naucs_at_50_std": 0.08727770914673263,
|
177 |
+
"naucs_at_50_diff1": 0.9537108770403242,
|
178 |
+
"naucs_at_100_max": 0.6097113980568468,
|
179 |
+
"naucs_at_100_std": -0.06311386037266957,
|
180 |
+
"naucs_at_100_diff1": 0.9074217540806789
|
181 |
+
},
|
182 |
+
"vidore/tabfquad_test_subsampled": {
|
183 |
+
"ndcg_at_1": 0.90714,
|
184 |
+
"ndcg_at_3": 0.94809,
|
185 |
+
"ndcg_at_5": 0.95085,
|
186 |
+
"ndcg_at_10": 0.95556,
|
187 |
+
"ndcg_at_20": 0.95556,
|
188 |
+
"ndcg_at_50": 0.95633,
|
189 |
+
"ndcg_at_100": 0.95633,
|
190 |
+
"map_at_1": 0.90714,
|
191 |
+
"map_at_3": 0.93869,
|
192 |
+
"map_at_5": 0.94012,
|
193 |
+
"map_at_10": 0.94212,
|
194 |
+
"map_at_20": 0.94212,
|
195 |
+
"map_at_50": 0.94227,
|
196 |
+
"map_at_100": 0.94227,
|
197 |
+
"recall_at_1": 0.90714,
|
198 |
+
"recall_at_3": 0.975,
|
199 |
+
"recall_at_5": 0.98214,
|
200 |
+
"recall_at_10": 0.99643,
|
201 |
+
"recall_at_20": 0.99643,
|
202 |
+
"recall_at_50": 1.0,
|
203 |
+
"recall_at_100": 1.0,
|
204 |
+
"precision_at_1": 0.90714,
|
205 |
+
"precision_at_3": 0.325,
|
206 |
+
"precision_at_5": 0.19643,
|
207 |
+
"precision_at_10": 0.09964,
|
208 |
+
"precision_at_20": 0.04982,
|
209 |
+
"precision_at_50": 0.02,
|
210 |
+
"precision_at_100": 0.01,
|
211 |
+
"mrr_at_1": 0.9071428571428571,
|
212 |
+
"mrr_at_3": 0.9386904761904761,
|
213 |
+
"mrr_at_5": 0.9401190476190476,
|
214 |
+
"mrr_at_10": 0.9421173469387754,
|
215 |
+
"mrr_at_20": 0.9421173469387754,
|
216 |
+
"mrr_at_50": 0.9422602040816326,
|
217 |
+
"mrr_at_100": 0.9422602040816326,
|
218 |
+
"naucs_at_1_max": 0.47509516627163817,
|
219 |
+
"naucs_at_1_std": 0.09654887596064192,
|
220 |
+
"naucs_at_1_diff1": 0.9256625727213957,
|
221 |
+
"naucs_at_3_max": 0.7953181272509063,
|
222 |
+
"naucs_at_3_std": 0.6569294384420459,
|
223 |
+
"naucs_at_3_diff1": 0.9626517273576122,
|
224 |
+
"naucs_at_5_max": 0.9477124183006519,
|
225 |
+
"naucs_at_5_std": 0.8585434173669502,
|
226 |
+
"naucs_at_5_diff1": 0.9477124183006519,
|
227 |
+
"naucs_at_10_max": 1.0,
|
228 |
+
"naucs_at_10_std": 1.0,
|
229 |
+
"naucs_at_10_diff1": 0.8692810457516478,
|
230 |
+
"naucs_at_20_max": 1.0,
|
231 |
+
"naucs_at_20_std": 1.0,
|
232 |
+
"naucs_at_20_diff1": 0.8692810457516478,
|
233 |
+
"naucs_at_50_max": 1.0,
|
234 |
+
"naucs_at_50_std": 1.0,
|
235 |
+
"naucs_at_50_diff1": 1.0,
|
236 |
+
"naucs_at_100_max": 1.0,
|
237 |
+
"naucs_at_100_std": 1.0,
|
238 |
+
"naucs_at_100_diff1": 1.0
|
239 |
+
},
|
240 |
+
"vidore/tatdqa_test": {
|
241 |
+
"ndcg_at_1": 0.68165,
|
242 |
+
"ndcg_at_3": 0.78589,
|
243 |
+
"ndcg_at_5": 0.80738,
|
244 |
+
"ndcg_at_10": 0.81887,
|
245 |
+
"ndcg_at_20": 0.82338,
|
246 |
+
"ndcg_at_50": 0.82868,
|
247 |
+
"ndcg_at_100": 0.82966,
|
248 |
+
"map_at_1": 0.68165,
|
249 |
+
"map_at_3": 0.76094,
|
250 |
+
"map_at_5": 0.77284,
|
251 |
+
"map_at_10": 0.77775,
|
252 |
+
"map_at_20": 0.77902,
|
253 |
+
"map_at_50": 0.77992,
|
254 |
+
"map_at_100": 0.78,
|
255 |
+
"recall_at_1": 0.68165,
|
256 |
+
"recall_at_3": 0.85784,
|
257 |
+
"recall_at_5": 0.91009,
|
258 |
+
"recall_at_10": 0.94471,
|
259 |
+
"recall_at_20": 0.96233,
|
260 |
+
"recall_at_50": 0.98846,
|
261 |
+
"recall_at_100": 0.99453,
|
262 |
+
"precision_at_1": 0.68165,
|
263 |
+
"precision_at_3": 0.28595,
|
264 |
+
"precision_at_5": 0.18202,
|
265 |
+
"precision_at_10": 0.09447,
|
266 |
+
"precision_at_20": 0.04812,
|
267 |
+
"precision_at_50": 0.01977,
|
268 |
+
"precision_at_100": 0.00995,
|
269 |
+
"mrr_at_1": 0.6822600243013366,
|
270 |
+
"mrr_at_3": 0.7609356014580796,
|
271 |
+
"mrr_at_5": 0.7725394896719318,
|
272 |
+
"mrr_at_10": 0.7775212636695014,
|
273 |
+
"mrr_at_20": 0.7787535437042965,
|
274 |
+
"mrr_at_50": 0.7796543784238207,
|
275 |
+
"mrr_at_100": 0.7797401545799822,
|
276 |
+
"naucs_at_1_max": 0.16062026715795888,
|
277 |
+
"naucs_at_1_std": -0.3264360293606425,
|
278 |
+
"naucs_at_1_diff1": 0.8234210928574244,
|
279 |
+
"naucs_at_3_max": 0.2735402374223285,
|
280 |
+
"naucs_at_3_std": -0.2518265754222236,
|
281 |
+
"naucs_at_3_diff1": 0.7126512468213168,
|
282 |
+
"naucs_at_5_max": 0.3207976518601587,
|
283 |
+
"naucs_at_5_std": -0.09980902320534159,
|
284 |
+
"naucs_at_5_diff1": 0.654620096904173,
|
285 |
+
"naucs_at_10_max": 0.4248907897527349,
|
286 |
+
"naucs_at_10_std": 0.05751189029665147,
|
287 |
+
"naucs_at_10_diff1": 0.6072701680557849,
|
288 |
+
"naucs_at_20_max": 0.5189102534669143,
|
289 |
+
"naucs_at_20_std": 0.17852289719761627,
|
290 |
+
"naucs_at_20_diff1": 0.5826792796971454,
|
291 |
+
"naucs_at_50_max": 0.6766878761446519,
|
292 |
+
"naucs_at_50_std": 0.4444418209829138,
|
293 |
+
"naucs_at_50_diff1": 0.5707904926948768,
|
294 |
+
"naucs_at_100_max": 0.5171029913955458,
|
295 |
+
"naucs_at_100_std": 0.4414823767216705,
|
296 |
+
"naucs_at_100_diff1": 0.48651595702377487
|
297 |
+
},
|
298 |
+
"vidore/shiftproject_test": {
|
299 |
+
"ndcg_at_1": 0.79,
|
300 |
+
"ndcg_at_3": 0.88309,
|
301 |
+
"ndcg_at_5": 0.88309,
|
302 |
+
"ndcg_at_10": 0.88666,
|
303 |
+
"ndcg_at_20": 0.89172,
|
304 |
+
"ndcg_at_50": 0.89372,
|
305 |
+
"ndcg_at_100": 0.89546,
|
306 |
+
"map_at_1": 0.79,
|
307 |
+
"map_at_3": 0.86,
|
308 |
+
"map_at_5": 0.86,
|
309 |
+
"map_at_10": 0.86167,
|
310 |
+
"map_at_20": 0.86308,
|
311 |
+
"map_at_50": 0.8634,
|
312 |
+
"map_at_100": 0.86359,
|
313 |
+
"recall_at_1": 0.79,
|
314 |
+
"recall_at_3": 0.95,
|
315 |
+
"recall_at_5": 0.95,
|
316 |
+
"recall_at_10": 0.96,
|
317 |
+
"recall_at_20": 0.98,
|
318 |
+
"recall_at_50": 0.99,
|
319 |
+
"recall_at_100": 1.0,
|
320 |
+
"precision_at_1": 0.79,
|
321 |
+
"precision_at_3": 0.31667,
|
322 |
+
"precision_at_5": 0.19,
|
323 |
+
"precision_at_10": 0.096,
|
324 |
+
"precision_at_20": 0.049,
|
325 |
+
"precision_at_50": 0.0198,
|
326 |
+
"precision_at_100": 0.01,
|
327 |
+
"mrr_at_1": 0.79,
|
328 |
+
"mrr_at_3": 0.8633333333333333,
|
329 |
+
"mrr_at_5": 0.8633333333333333,
|
330 |
+
"mrr_at_10": 0.865,
|
331 |
+
"mrr_at_20": 0.8664354066985647,
|
332 |
+
"mrr_at_50": 0.8667579873437259,
|
333 |
+
"mrr_at_100": 0.8669466665890089,
|
334 |
+
"naucs_at_1_max": 0.039218986702575266,
|
335 |
+
"naucs_at_1_std": -0.30031019308918766,
|
336 |
+
"naucs_at_1_diff1": 0.8456248346839152,
|
337 |
+
"naucs_at_3_max": 0.5220354808590087,
|
338 |
+
"naucs_at_3_std": -0.057609710550887504,
|
339 |
+
"naucs_at_3_diff1": 0.8160597572362241,
|
340 |
+
"naucs_at_5_max": 0.5220354808590145,
|
341 |
+
"naucs_at_5_std": -0.05760971055088009,
|
342 |
+
"naucs_at_5_diff1": 0.8160597572362281,
|
343 |
+
"naucs_at_10_max": 0.4352240896358576,
|
344 |
+
"naucs_at_10_std": -0.10270774976656832,
|
345 |
+
"naucs_at_10_diff1": 0.9305555555555542,
|
346 |
+
"naucs_at_20_max": 0.1914098972922579,
|
347 |
+
"naucs_at_20_std": -0.3968253968253954,
|
348 |
+
"naucs_at_20_diff1": 0.861111111111116,
|
349 |
+
"naucs_at_50_max": 0.554154995331464,
|
350 |
+
"naucs_at_50_std": 0.35807656395892007,
|
351 |
+
"naucs_at_50_diff1": 1.0,
|
352 |
+
"naucs_at_100_max": null,
|
353 |
+
"naucs_at_100_std": null,
|
354 |
+
"naucs_at_100_diff1": null
|
355 |
+
},
|
356 |
+
"vidore/syntheticDocQA_artificial_intelligence_test": {
|
357 |
+
"ndcg_at_1": 1.0,
|
358 |
+
"ndcg_at_3": 1.0,
|
359 |
+
"ndcg_at_5": 1.0,
|
360 |
+
"ndcg_at_10": 1.0,
|
361 |
+
"ndcg_at_20": 1.0,
|
362 |
+
"ndcg_at_50": 1.0,
|
363 |
+
"ndcg_at_100": 1.0,
|
364 |
+
"map_at_1": 1.0,
|
365 |
+
"map_at_3": 1.0,
|
366 |
+
"map_at_5": 1.0,
|
367 |
+
"map_at_10": 1.0,
|
368 |
+
"map_at_20": 1.0,
|
369 |
+
"map_at_50": 1.0,
|
370 |
+
"map_at_100": 1.0,
|
371 |
+
"recall_at_1": 1.0,
|
372 |
+
"recall_at_3": 1.0,
|
373 |
+
"recall_at_5": 1.0,
|
374 |
+
"recall_at_10": 1.0,
|
375 |
+
"recall_at_20": 1.0,
|
376 |
+
"recall_at_50": 1.0,
|
377 |
+
"recall_at_100": 1.0,
|
378 |
+
"precision_at_1": 1.0,
|
379 |
+
"precision_at_3": 0.33333,
|
380 |
+
"precision_at_5": 0.2,
|
381 |
+
"precision_at_10": 0.1,
|
382 |
+
"precision_at_20": 0.05,
|
383 |
+
"precision_at_50": 0.02,
|
384 |
+
"precision_at_100": 0.01,
|
385 |
+
"mrr_at_1": 1.0,
|
386 |
+
"mrr_at_3": 1.0,
|
387 |
+
"mrr_at_5": 1.0,
|
388 |
+
"mrr_at_10": 1.0,
|
389 |
+
"mrr_at_20": 1.0,
|
390 |
+
"mrr_at_50": 1.0,
|
391 |
+
"mrr_at_100": 1.0,
|
392 |
+
"naucs_at_1_max": null,
|
393 |
+
"naucs_at_1_std": null,
|
394 |
+
"naucs_at_1_diff1": null,
|
395 |
+
"naucs_at_3_max": 1.0,
|
396 |
+
"naucs_at_3_std": 1.0,
|
397 |
+
"naucs_at_3_diff1": 1.0,
|
398 |
+
"naucs_at_5_max": 1.0,
|
399 |
+
"naucs_at_5_std": 1.0,
|
400 |
+
"naucs_at_5_diff1": 1.0,
|
401 |
+
"naucs_at_10_max": 1.0,
|
402 |
+
"naucs_at_10_std": 1.0,
|
403 |
+
"naucs_at_10_diff1": 1.0,
|
404 |
+
"naucs_at_20_max": 1.0,
|
405 |
+
"naucs_at_20_std": 1.0,
|
406 |
+
"naucs_at_20_diff1": 1.0,
|
407 |
+
"naucs_at_50_max": null,
|
408 |
+
"naucs_at_50_std": null,
|
409 |
+
"naucs_at_50_diff1": null,
|
410 |
+
"naucs_at_100_max": null,
|
411 |
+
"naucs_at_100_std": null,
|
412 |
+
"naucs_at_100_diff1": null
|
413 |
+
},
|
414 |
+
"vidore/syntheticDocQA_energy_test": {
|
415 |
+
"ndcg_at_1": 0.94,
|
416 |
+
"ndcg_at_3": 0.95893,
|
417 |
+
"ndcg_at_5": 0.95893,
|
418 |
+
"ndcg_at_10": 0.96208,
|
419 |
+
"ndcg_at_20": 0.96718,
|
420 |
+
"ndcg_at_50": 0.96718,
|
421 |
+
"ndcg_at_100": 0.96718,
|
422 |
+
"map_at_1": 0.94,
|
423 |
+
"map_at_3": 0.955,
|
424 |
+
"map_at_5": 0.955,
|
425 |
+
"map_at_10": 0.95625,
|
426 |
+
"map_at_20": 0.95767,
|
427 |
+
"map_at_50": 0.95767,
|
428 |
+
"map_at_100": 0.95767,
|
429 |
+
"recall_at_1": 0.94,
|
430 |
+
"recall_at_3": 0.97,
|
431 |
+
"recall_at_5": 0.97,
|
432 |
+
"recall_at_10": 0.98,
|
433 |
+
"recall_at_20": 1.0,
|
434 |
+
"recall_at_50": 1.0,
|
435 |
+
"recall_at_100": 1.0,
|
436 |
+
"precision_at_1": 0.94,
|
437 |
+
"precision_at_3": 0.32333,
|
438 |
+
"precision_at_5": 0.194,
|
439 |
+
"precision_at_10": 0.098,
|
440 |
+
"precision_at_20": 0.05,
|
441 |
+
"precision_at_50": 0.02,
|
442 |
+
"precision_at_100": 0.01,
|
443 |
+
"mrr_at_1": 0.94,
|
444 |
+
"mrr_at_3": 0.955,
|
445 |
+
"mrr_at_5": 0.955,
|
446 |
+
"mrr_at_10": 0.9566666666666667,
|
447 |
+
"mrr_at_20": 0.9582142857142857,
|
448 |
+
"mrr_at_50": 0.9582142857142857,
|
449 |
+
"mrr_at_100": 0.9582142857142857,
|
450 |
+
"naucs_at_1_max": 0.49004046062869583,
|
451 |
+
"naucs_at_1_std": -0.6582633053221264,
|
452 |
+
"naucs_at_1_diff1": 1.0,
|
453 |
+
"naucs_at_3_max": 0.7424525365701778,
|
454 |
+
"naucs_at_3_std": -1.040616246498596,
|
455 |
+
"naucs_at_3_diff1": 1.0,
|
456 |
+
"naucs_at_5_max": 0.742452536570183,
|
457 |
+
"naucs_at_5_std": -1.040616246498598,
|
458 |
+
"naucs_at_5_diff1": 1.0,
|
459 |
+
"naucs_at_10_max": 0.9346405228758136,
|
460 |
+
"naucs_at_10_std": -0.690943043884218,
|
461 |
+
"naucs_at_10_diff1": 1.0,
|
462 |
+
"naucs_at_20_max": 1.0,
|
463 |
+
"naucs_at_20_std": 1.0,
|
464 |
+
"naucs_at_20_diff1": 1.0,
|
465 |
+
"naucs_at_50_max": null,
|
466 |
+
"naucs_at_50_std": null,
|
467 |
+
"naucs_at_50_diff1": null,
|
468 |
+
"naucs_at_100_max": null,
|
469 |
+
"naucs_at_100_std": null,
|
470 |
+
"naucs_at_100_diff1": null
|
471 |
+
},
|
472 |
+
"vidore/syntheticDocQA_government_reports_test": {
|
473 |
+
"ndcg_at_1": 0.92,
|
474 |
+
"ndcg_at_3": 0.95655,
|
475 |
+
"ndcg_at_5": 0.96085,
|
476 |
+
"ndcg_at_10": 0.96419,
|
477 |
+
"ndcg_at_20": 0.96419,
|
478 |
+
"ndcg_at_50": 0.96419,
|
479 |
+
"ndcg_at_100": 0.96419,
|
480 |
+
"map_at_1": 0.92,
|
481 |
+
"map_at_3": 0.94833,
|
482 |
+
"map_at_5": 0.95083,
|
483 |
+
"map_at_10": 0.95226,
|
484 |
+
"map_at_20": 0.95226,
|
485 |
+
"map_at_50": 0.95226,
|
486 |
+
"map_at_100": 0.95226,
|
487 |
+
"recall_at_1": 0.92,
|
488 |
+
"recall_at_3": 0.98,
|
489 |
+
"recall_at_5": 0.99,
|
490 |
+
"recall_at_10": 1.0,
|
491 |
+
"recall_at_20": 1.0,
|
492 |
+
"recall_at_50": 1.0,
|
493 |
+
"recall_at_100": 1.0,
|
494 |
+
"precision_at_1": 0.92,
|
495 |
+
"precision_at_3": 0.32667,
|
496 |
+
"precision_at_5": 0.198,
|
497 |
+
"precision_at_10": 0.1,
|
498 |
+
"precision_at_20": 0.05,
|
499 |
+
"precision_at_50": 0.02,
|
500 |
+
"precision_at_100": 0.01,
|
501 |
+
"mrr_at_1": 0.93,
|
502 |
+
"mrr_at_3": 0.9533333333333333,
|
503 |
+
"mrr_at_5": 0.9558333333333333,
|
504 |
+
"mrr_at_10": 0.9574999999999999,
|
505 |
+
"mrr_at_20": 0.9574999999999999,
|
506 |
+
"mrr_at_50": 0.9574999999999999,
|
507 |
+
"mrr_at_100": 0.9574999999999999,
|
508 |
+
"naucs_at_1_max": 0.6289682539682547,
|
509 |
+
"naucs_at_1_std": 0.44461951447245585,
|
510 |
+
"naucs_at_1_diff1": 0.9509803921568633,
|
511 |
+
"naucs_at_3_max": 1.0,
|
512 |
+
"naucs_at_3_std": 0.3384687208216551,
|
513 |
+
"naucs_at_3_diff1": 0.9346405228758099,
|
514 |
+
"naucs_at_5_max": 1.0,
|
515 |
+
"naucs_at_5_std": 0.5541549953314738,
|
516 |
+
"naucs_at_5_diff1": 0.8692810457516413,
|
517 |
+
"naucs_at_10_max": 1.0,
|
518 |
+
"naucs_at_10_std": 1.0,
|
519 |
+
"naucs_at_10_diff1": 1.0,
|
520 |
+
"naucs_at_20_max": 1.0,
|
521 |
+
"naucs_at_20_std": 1.0,
|
522 |
+
"naucs_at_20_diff1": 1.0,
|
523 |
+
"naucs_at_50_max": null,
|
524 |
+
"naucs_at_50_std": null,
|
525 |
+
"naucs_at_50_diff1": null,
|
526 |
+
"naucs_at_100_max": null,
|
527 |
+
"naucs_at_100_std": null,
|
528 |
+
"naucs_at_100_diff1": null
|
529 |
+
},
|
530 |
+
"vidore/syntheticDocQA_healthcare_industry_test": {
|
531 |
+
"ndcg_at_1": 0.94,
|
532 |
+
"ndcg_at_3": 0.97655,
|
533 |
+
"ndcg_at_5": 0.97655,
|
534 |
+
"ndcg_at_10": 0.97655,
|
535 |
+
"ndcg_at_20": 0.97655,
|
536 |
+
"ndcg_at_50": 0.97655,
|
537 |
+
"ndcg_at_100": 0.97655,
|
538 |
+
"map_at_1": 0.94,
|
539 |
+
"map_at_3": 0.96833,
|
540 |
+
"map_at_5": 0.96833,
|
541 |
+
"map_at_10": 0.96833,
|
542 |
+
"map_at_20": 0.96833,
|
543 |
+
"map_at_50": 0.96833,
|
544 |
+
"map_at_100": 0.96833,
|
545 |
+
"recall_at_1": 0.94,
|
546 |
+
"recall_at_3": 1.0,
|
547 |
+
"recall_at_5": 1.0,
|
548 |
+
"recall_at_10": 1.0,
|
549 |
+
"recall_at_20": 1.0,
|
550 |
+
"recall_at_50": 1.0,
|
551 |
+
"recall_at_100": 1.0,
|
552 |
+
"precision_at_1": 0.94,
|
553 |
+
"precision_at_3": 0.33333,
|
554 |
+
"precision_at_5": 0.2,
|
555 |
+
"precision_at_10": 0.1,
|
556 |
+
"precision_at_20": 0.05,
|
557 |
+
"precision_at_50": 0.02,
|
558 |
+
"precision_at_100": 0.01,
|
559 |
+
"mrr_at_1": 0.95,
|
560 |
+
"mrr_at_3": 0.9733333333333333,
|
561 |
+
"mrr_at_5": 0.9733333333333333,
|
562 |
+
"mrr_at_10": 0.9733333333333333,
|
563 |
+
"mrr_at_20": 0.9733333333333333,
|
564 |
+
"mrr_at_50": 0.9733333333333333,
|
565 |
+
"mrr_at_100": 0.9733333333333333,
|
566 |
+
"naucs_at_1_max": 0.5662931839402436,
|
567 |
+
"naucs_at_1_std": 0.18837535014005719,
|
568 |
+
"naucs_at_1_diff1": 0.9782135076252712,
|
569 |
+
"naucs_at_3_max": 1.0,
|
570 |
+
"naucs_at_3_std": 1.0,
|
571 |
+
"naucs_at_3_diff1": 1.0,
|
572 |
+
"naucs_at_5_max": 1.0,
|
573 |
+
"naucs_at_5_std": 1.0,
|
574 |
+
"naucs_at_5_diff1": 1.0,
|
575 |
+
"naucs_at_10_max": 1.0,
|
576 |
+
"naucs_at_10_std": 1.0,
|
577 |
+
"naucs_at_10_diff1": 1.0,
|
578 |
+
"naucs_at_20_max": 1.0,
|
579 |
+
"naucs_at_20_std": 1.0,
|
580 |
+
"naucs_at_20_diff1": 1.0,
|
581 |
+
"naucs_at_50_max": null,
|
582 |
+
"naucs_at_50_std": null,
|
583 |
+
"naucs_at_50_diff1": null,
|
584 |
+
"naucs_at_100_max": null,
|
585 |
+
"naucs_at_100_std": null,
|
586 |
+
"naucs_at_100_diff1": null
|
587 |
+
}
|
588 |
+
}
|
589 |
+
}
|