baseline-results / bm25_captioning_metrics.json
HugSib's picture
Upload 7 files
9294e27 verified
raw
history blame contribute delete
No virus
16.9 kB
{"vidore/arxivqa_test_subsampled_captioning": {"ndcg_at_1": 0.35471, "ndcg_at_3": 0.38749, "ndcg_at_5": 0.40137, "ndcg_at_10": 0.4189, "ndcg_at_20": 0.43205, "ndcg_at_100": 0.46057, "ndcg_at_1000": 0.49627, "map_at_1": 0.35471, "map_at_3": 0.37943, "map_at_5": 0.38704, "map_at_10": 0.3943, "map_at_20": 0.3979, "map_at_100": 0.40141, "map_at_1000": 0.40256, "recall_at_1": 0.35471, "recall_at_3": 0.41082, "recall_at_5": 0.44489, "recall_at_10": 0.499, "recall_at_20": 0.5511, "recall_at_100": 0.71142, "recall_at_1000": 1.0, "precision_at_1": 0.35471, "precision_at_3": 0.13694, "precision_at_5": 0.08898, "precision_at_10": 0.0499, "precision_at_20": 0.02756, "precision_at_100": 0.00711, "precision_at_1000": 0.001, "mrr_at_1": 0.35470941883767537, "mrr_at_3": 0.3794255177020709, "mrr_at_5": 0.3870407481629926, "mrr_at_10": 0.3943013010147279, "mrr_at_20": 0.3979044097731162, "mrr_at_100": 0.4014087954137622, "mrr_at_1000": 0.40254583657876286, "naucs_at_1_max": 0.7107863708672527, "naucs_at_1_std": 0.16655143065456648, "naucs_at_1_diff1": 0.7503884209574972, "naucs_at_3_max": 0.6794486344308436, "naucs_at_3_std": 0.1764800646544904, "naucs_at_3_diff1": 0.6837898829455666, "naucs_at_5_max": 0.6580063709536177, "naucs_at_5_std": 0.16768918724166829, "naucs_at_5_diff1": 0.6522196919726458, "naucs_at_10_max": 0.6378766547711558, "naucs_at_10_std": 0.18109213120693538, "naucs_at_10_diff1": 0.631013418241438, "naucs_at_20_max": 0.6381653259037495, "naucs_at_20_std": 0.19860689307593032, "naucs_at_20_diff1": 0.6102557881436013, "naucs_at_100_max": 0.5732518889409701, "naucs_at_100_std": 0.209246465034422, "naucs_at_100_diff1": 0.5348625585944835, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/docvqa_test_subsampled_captioning": {"ndcg_at_1": 0.30222, "ndcg_at_3": 0.36569, "ndcg_at_5": 0.38395, "ndcg_at_10": 0.40359, "ndcg_at_20": 0.41697, "ndcg_at_100": 0.442, "ndcg_at_1000": 0.47831, "map_at_1": 0.30222, "map_at_3": 0.35, "map_at_5": 0.36011, "map_at_10": 0.36834, "map_at_20": 0.37196, "map_at_100": 0.37508, "map_at_1000": 0.37628, "recall_at_1": 0.30222, "recall_at_3": 0.41111, "recall_at_5": 0.45556, "recall_at_10": 0.51556, "recall_at_20": 0.56889, "recall_at_100": 0.70889, "recall_at_1000": 1.0, "precision_at_1": 0.30222, "precision_at_3": 0.13704, "precision_at_5": 0.09111, "precision_at_10": 0.05156, "precision_at_20": 0.02844, "precision_at_100": 0.00709, "precision_at_1000": 0.001, "mrr_at_1": 0.3, "mrr_at_3": 0.34814814814814815, "mrr_at_5": 0.3588148148148148, "mrr_at_10": 0.3673932980599646, "mrr_at_20": 0.37102598888899196, "mrr_at_100": 0.37425679774339693, "mrr_at_1000": 0.37531452957225825, "naucs_at_1_max": 0.6616048612527444, "naucs_at_1_std": 0.2205289551665806, "naucs_at_1_diff1": 0.7441813731959258, "naucs_at_3_max": 0.6435727720426708, "naucs_at_3_std": 0.1627733348648221, "naucs_at_3_diff1": 0.6397076770664332, "naucs_at_5_max": 0.6257882997798737, "naucs_at_5_std": 0.144137498724434, "naucs_at_5_diff1": 0.6070994358353864, "naucs_at_10_max": 0.5809102287908141, "naucs_at_10_std": 0.12136383877528874, "naucs_at_10_diff1": 0.5642233027235856, "naucs_at_20_max": 0.5599239364480743, "naucs_at_20_std": 0.1133022029125838, "naucs_at_20_diff1": 0.5288550970224367, "naucs_at_100_max": 0.5072226988551234, "naucs_at_100_std": 0.13089935839282152, "naucs_at_100_diff1": 0.42179822418896035, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/infovqa_test_subsampled_captioning": {"ndcg_at_1": 0.61538, "ndcg_at_3": 0.68773, "ndcg_at_5": 0.70018, "ndcg_at_10": 0.71349, "ndcg_at_20": 0.72201, "ndcg_at_100": 0.73266, "ndcg_at_1000": 0.74469, "map_at_1": 0.61538, "map_at_3": 0.67004, "map_at_5": 0.67692, "map_at_10": 0.68216, "map_at_20": 0.68441, "map_at_100": 0.68591, "map_at_1000": 0.6863, "recall_at_1": 0.61538, "recall_at_3": 0.73887, "recall_at_5": 0.76923, "recall_at_10": 0.81174, "recall_at_20": 0.84615, "recall_at_100": 0.90283, "recall_at_1000": 1.0, "precision_at_1": 0.61538, "precision_at_3": 0.24629, "precision_at_5": 0.15385, "precision_at_10": 0.08117, "precision_at_20": 0.04231, "precision_at_100": 0.00903, "precision_at_1000": 0.001, "mrr_at_1": 0.6153846153846154, "mrr_at_3": 0.6700404858299595, "mrr_at_5": 0.6769230769230766, "mrr_at_10": 0.6821581196581193, "mrr_at_20": 0.6842787541891178, "mrr_at_100": 0.6858747194100033, "mrr_at_1000": 0.6862609365628476, "naucs_at_1_max": 0.6840497390171273, "naucs_at_1_std": 0.21155323018597844, "naucs_at_1_diff1": 0.7836381260278086, "naucs_at_3_max": 0.724026374122518, "naucs_at_3_std": 0.27326902460319447, "naucs_at_3_diff1": 0.7205456295244483, "naucs_at_5_max": 0.7075731905388908, "naucs_at_5_std": 0.26688459757132, "naucs_at_5_diff1": 0.6976903420775469, "naucs_at_10_max": 0.7210728251773157, "naucs_at_10_std": 0.3132624306451927, "naucs_at_10_diff1": 0.6811003410078096, "naucs_at_20_max": 0.7182175348372994, "naucs_at_20_std": 0.3083798496825381, "naucs_at_20_diff1": 0.6723449775571294, "naucs_at_100_max": 0.7378499042261256, "naucs_at_100_std": 0.4954902049241885, "naucs_at_100_diff1": 0.6260224704707891, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/tabfquad_test_subsampled_captioning": {"ndcg_at_1": 0.24286, "ndcg_at_3": 0.31658, "ndcg_at_5": 0.35362, "ndcg_at_10": 0.39585, "ndcg_at_20": 0.43105, "ndcg_at_100": 0.48189, "ndcg_at_1000": 0.48189, "map_at_1": 0.24286, "map_at_3": 0.29881, "map_at_5": 0.31952, "map_at_10": 0.33665, "map_at_20": 0.3463, "map_at_100": 0.35342, "map_at_1000": 0.35342, "recall_at_1": 0.24286, "recall_at_3": 0.36786, "recall_at_5": 0.45714, "recall_at_10": 0.58929, "recall_at_20": 0.72857, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.24286, "precision_at_3": 0.12262, "precision_at_5": 0.09143, "precision_at_10": 0.05893, "precision_at_20": 0.03643, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.25, "mrr_at_3": 0.30416666666666664, "mrr_at_5": 0.3248809523809524, "mrr_at_10": 0.34113378684807266, "mrr_at_20": 0.3508819688929432, "mrr_at_100": 0.3581819063179925, "mrr_at_1000": 0.3581819063179925, "naucs_at_1_max": 0.27482492177355844, "naucs_at_1_std": 0.07912045807701315, "naucs_at_1_diff1": 0.45217544009025307, "naucs_at_3_max": 0.20629222085797924, "naucs_at_3_std": 0.07778675169583728, "naucs_at_3_diff1": 0.336048851312552, "naucs_at_5_max": 0.12657527567324275, "naucs_at_5_std": 0.01278973820418573, "naucs_at_5_diff1": 0.2805115895281671, "naucs_at_10_max": 0.11068520409499127, "naucs_at_10_std": 0.06472390228575903, "naucs_at_10_diff1": 0.19567983661927568, "naucs_at_20_max": 0.24785392724324057, "naucs_at_20_std": 0.1697564521991996, "naucs_at_20_diff1": 0.23868243715571894, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/tatdqa_test_captioning": {"ndcg_at_1": 0.49028, "ndcg_at_3": 0.58599, "ndcg_at_5": 0.61467, "ndcg_at_10": 0.63784, "ndcg_at_20": 0.65461, "ndcg_at_100": 0.67307, "ndcg_at_1000": 0.67841, "map_at_1": 0.49028, "map_at_3": 0.56258, "map_at_5": 0.57843, "map_at_10": 0.5881, "map_at_20": 0.5928, "map_at_100": 0.59526, "map_at_1000": 0.59551, "recall_at_1": 0.49028, "recall_at_3": 0.65371, "recall_at_5": 0.72357, "recall_at_10": 0.79465, "recall_at_20": 0.86027, "recall_at_100": 0.96112, "recall_at_1000": 1.0, "precision_at_1": 0.49028, "precision_at_3": 0.2179, "precision_at_5": 0.14471, "precision_at_10": 0.07947, "precision_at_20": 0.04301, "precision_at_100": 0.00961, "precision_at_1000": 0.001, "mrr_at_1": 0.4890643985419198, "mrr_at_3": 0.5619684082624553, "mrr_at_5": 0.5779769137302566, "mrr_at_10": 0.5874701054986604, "mrr_at_20": 0.5922265163570909, "mrr_at_100": 0.5946852788997554, "mrr_at_1000": 0.5949451741278895, "naucs_at_1_max": 0.5238035470534966, "naucs_at_1_std": 0.1834833029363977, "naucs_at_1_diff1": 0.6997115756316219, "naucs_at_3_max": 0.5315457833886871, "naucs_at_3_std": 0.18945427873202372, "naucs_at_3_diff1": 0.6128413103749237, "naucs_at_5_max": 0.5296304471226658, "naucs_at_5_std": 0.20013045106033062, "naucs_at_5_diff1": 0.5880328958364259, "naucs_at_10_max": 0.5439029514824874, "naucs_at_10_std": 0.271158717803679, "naucs_at_10_diff1": 0.5541216665749958, "naucs_at_20_max": 0.6263794377288422, "naucs_at_20_std": 0.4468636941163992, "naucs_at_20_diff1": 0.5317148547048963, "naucs_at_100_max": 0.5849500955036473, "naucs_at_100_std": 0.5125470547270657, "naucs_at_100_diff1": 0.48470033540288254, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/shiftproject_test_captioning": {"ndcg_at_1": 0.47, "ndcg_at_3": 0.56309, "ndcg_at_5": 0.60871, "ndcg_at_10": 0.63182, "ndcg_at_20": 0.64221, "ndcg_at_100": 0.66105, "ndcg_at_1000": 0.66735, "map_at_1": 0.47, "map_at_3": 0.54, "map_at_5": 0.5655, "map_at_10": 0.5753, "map_at_20": 0.57829, "map_at_100": 0.58099, "map_at_1000": 0.58122, "recall_at_1": 0.47, "recall_at_3": 0.63, "recall_at_5": 0.74, "recall_at_10": 0.81, "recall_at_20": 0.85, "recall_at_100": 0.95, "recall_at_1000": 1.0, "precision_at_1": 0.47, "precision_at_3": 0.21, "precision_at_5": 0.148, "precision_at_10": 0.081, "precision_at_20": 0.0425, "precision_at_100": 0.0095, "precision_at_1000": 0.001, "mrr_at_1": 0.47, "mrr_at_3": 0.54, "mrr_at_5": 0.5655000000000001, "mrr_at_10": 0.5753015873015874, "mrr_at_20": 0.5782851037851039, "mrr_at_100": 0.5809916716002134, "mrr_at_1000": 0.5812205865887138, "naucs_at_1_max": 0.16575904218146348, "naucs_at_1_std": -0.07741399543770343, "naucs_at_1_diff1": 0.5687706852674745, "naucs_at_3_max": 0.1379996552750752, "naucs_at_3_std": -0.09724376753004503, "naucs_at_3_diff1": 0.581817327128285, "naucs_at_5_max": 0.1552856737358583, "naucs_at_5_std": -0.10824784072016491, "naucs_at_5_diff1": 0.5830866550423749, "naucs_at_10_max": 0.3803237466603805, "naucs_at_10_std": 0.21064487401121126, "naucs_at_10_diff1": 0.5777673005395781, "naucs_at_20_max": 0.3638138626749107, "naucs_at_20_std": 0.11122681418808977, "naucs_at_20_diff1": 0.6284738041002277, "naucs_at_100_max": 0.1654528478057925, "naucs_at_100_std": 0.13183940242763956, "naucs_at_100_diff1": 0.7899159663865595, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_artificial_intelligence_test_captioning": {"ndcg_at_1": 0.79, "ndcg_at_3": 0.87571, "ndcg_at_5": 0.88002, "ndcg_at_10": 0.88714, "ndcg_at_20": 0.89243, "ndcg_at_100": 0.89243, "ndcg_at_1000": 0.89489, "map_at_1": 0.79, "map_at_3": 0.85667, "map_at_5": 0.85917, "map_at_10": 0.8625, "map_at_20": 0.86408, "map_at_100": 0.86408, "map_at_1000": 0.86415, "recall_at_1": 0.79, "recall_at_3": 0.93, "recall_at_5": 0.94, "recall_at_10": 0.96, "recall_at_20": 0.98, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.79, "precision_at_3": 0.31, "precision_at_5": 0.188, "precision_at_10": 0.096, "precision_at_20": 0.049, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.79, "mrr_at_3": 0.8566666666666667, "mrr_at_5": 0.8591666666666667, "mrr_at_10": 0.8625, "mrr_at_20": 0.8640757575757577, "mrr_at_100": 0.8640757575757577, "mrr_at_1000": 0.8641583749397475, "naucs_at_1_max": 0.6288744078678428, "naucs_at_1_std": 0.10743742034770468, "naucs_at_1_diff1": 0.8903743958448547, "naucs_at_3_max": 0.7953181272509017, "naucs_at_3_std": -0.00847005468854118, "naucs_at_3_diff1": 0.9176337201547277, "naucs_at_5_max": 0.7612044817927189, "naucs_at_5_std": 0.08403361344537601, "naucs_at_5_diff1": 0.9039060068471841, "naucs_at_10_max": 0.967320261437907, "naucs_at_10_std": 0.3244631185807679, "naucs_at_10_diff1": 0.967320261437907, "naucs_at_20_max": 1.0, "naucs_at_20_std": 0.4960317460317504, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 0.4960317460317565, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_energy_test_captioning": {"ndcg_at_1": 0.76, "ndcg_at_3": 0.83417, "ndcg_at_5": 0.84709, "ndcg_at_10": 0.85731, "ndcg_at_20": 0.86226, "ndcg_at_100": 0.86597, "ndcg_at_1000": 0.86701, "map_at_1": 0.76, "map_at_3": 0.815, "map_at_5": 0.8225, "map_at_10": 0.82702, "map_at_20": 0.82832, "map_at_100": 0.82883, "map_at_1000": 0.82884, "recall_at_1": 0.76, "recall_at_3": 0.89, "recall_at_5": 0.92, "recall_at_10": 0.95, "recall_at_20": 0.97, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.76, "precision_at_3": 0.29667, "precision_at_5": 0.184, "precision_at_10": 0.095, "precision_at_20": 0.0485, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.77, "mrr_at_3": 0.825, "mrr_at_5": 0.8325, "mrr_at_10": 0.8355952380952381, "mrr_at_20": 0.8368869047619047, "mrr_at_100": 0.8373978937728939, "mrr_at_1000": 0.8374193530003616, "naucs_at_1_max": 0.7507787488102445, "naucs_at_1_std": 0.1935407112572463, "naucs_at_1_diff1": 0.932183957774509, "naucs_at_3_max": 0.7816338802508357, "naucs_at_3_std": 0.2358474357873024, "naucs_at_3_diff1": 0.8857486470234515, "naucs_at_5_max": 0.8129668534080287, "naucs_at_5_std": 0.3503734827264242, "naucs_at_5_diff1": 0.895833333333333, "naucs_at_10_max": 0.8846872082166187, "naucs_at_10_std": 0.6840336134453832, "naucs_at_10_diff1": 0.88888888888889, "naucs_at_20_max": 0.9564270152505424, "naucs_at_20_std": 0.8638344226579531, "naucs_at_20_diff1": 0.9074074074074053, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_government_reports_test_captioning": {"ndcg_at_1": 0.75, "ndcg_at_3": 0.80547, "ndcg_at_5": 0.82657, "ndcg_at_10": 0.8363, "ndcg_at_20": 0.83865, "ndcg_at_100": 0.84253, "ndcg_at_1000": 0.84901, "map_at_1": 0.75, "map_at_3": 0.79333, "map_at_5": 0.80533, "map_at_10": 0.80936, "map_at_20": 0.80992, "map_at_100": 0.81052, "map_at_1000": 0.81078, "recall_at_1": 0.75, "recall_at_3": 0.84, "recall_at_5": 0.89, "recall_at_10": 0.92, "recall_at_20": 0.93, "recall_at_100": 0.95, "recall_at_1000": 1.0, "precision_at_1": 0.75, "precision_at_3": 0.28, "precision_at_5": 0.178, "precision_at_10": 0.092, "precision_at_20": 0.0465, "precision_at_100": 0.0095, "precision_at_1000": 0.001, "mrr_at_1": 0.75, "mrr_at_3": 0.7933333333333334, "mrr_at_5": 0.8053333333333333, "mrr_at_10": 0.8093611111111112, "mrr_at_20": 0.8099166666666667, "mrr_at_100": 0.8105151515151516, "mrr_at_1000": 0.8107936655759888, "naucs_at_1_max": 0.6349764521193086, "naucs_at_1_std": 0.13356357927786458, "naucs_at_1_diff1": 0.7447828362114077, "naucs_at_3_max": 0.8274729995090826, "naucs_at_3_std": 0.26687530682375954, "naucs_at_3_diff1": 0.8640770741286196, "naucs_at_5_max": 0.8973455888669359, "naucs_at_5_std": 0.5830684649085125, "naucs_at_5_diff1": 0.7976977922858863, "naucs_at_10_max": 0.876867413632119, "naucs_at_10_std": 0.579948646125118, "naucs_at_10_diff1": 0.7598622782446334, "naucs_at_20_max": 0.9229691876750716, "naucs_at_20_std": 0.6452581032412973, "naucs_at_20_diff1": 0.7652394291049759, "naucs_at_100_max": 0.8921568627451013, "naucs_at_100_std": 0.5850606909430469, "naucs_at_100_diff1": 0.7268907563025232, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_healthcare_industry_test_captioning": {"ndcg_at_1": 0.81, "ndcg_at_3": 0.87547, "ndcg_at_5": 0.89182, "ndcg_at_10": 0.89831, "ndcg_at_20": 0.90357, "ndcg_at_100": 0.90357, "ndcg_at_1000": 0.90357, "map_at_1": 0.81, "map_at_3": 0.86, "map_at_5": 0.869, "map_at_10": 0.87168, "map_at_20": 0.87322, "map_at_100": 0.87322, "map_at_1000": 0.87322, "recall_at_1": 0.81, "recall_at_3": 0.92, "recall_at_5": 0.96, "recall_at_10": 0.98, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.81, "precision_at_3": 0.30667, "precision_at_5": 0.192, "precision_at_10": 0.098, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.81, "mrr_at_3": 0.8599999999999999, "mrr_at_5": 0.8689999999999999, "mrr_at_10": 0.8716785714285714, "mrr_at_20": 0.873217032967033, "mrr_at_100": 0.873217032967033, "mrr_at_1000": 0.873217032967033, "naucs_at_1_max": 0.5821939336790821, "naucs_at_1_std": -0.10846560846560842, "naucs_at_1_diff1": 0.7768610194352775, "naucs_at_3_max": 0.7225140056022409, "naucs_at_3_std": 0.18294817927170998, "naucs_at_3_diff1": 0.7117180205415513, "naucs_at_5_max": 0.625933706816059, "naucs_at_5_std": -0.3085901027077449, "naucs_at_5_diff1": 0.8068394024276381, "naucs_at_10_max": 0.6381886087768404, "naucs_at_10_std": -0.5929038281979465, "naucs_at_10_diff1": 0.6790382819794609, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}