vidore
baseline-results / MrLight_dse-qwen2-2b-mrl-v1_metrics.json
QuentinJG's picture
Rename dse-qwen2-2b-mrl-v1_metrics.json to MrLight_dse-qwen2-2b-mrl-v1_metrics.json
244c2c1 verified
{"vidore/restaurant_esg_reports_beir":{"ndcg_at_1": 0.57692, "ndcg_at_3": 0.59121, "ndcg_at_5": 0.61353, "ndcg_at_10": 0.65611, "ndcg_at_20": 0.67738, "ndcg_at_50": 0.70659, "ndcg_at_100": 0.71134, "map_at_1": 0.43878, "map_at_3": 0.52393, "map_at_5": 0.55415, "map_at_10": 0.58352, "map_at_20": 0.59072, "map_at_50": 0.60006, "map_at_100": 0.60096, "recall_at_1": 0.43878, "recall_at_3": 0.58109, "recall_at_5": 0.64986, "recall_at_10": 0.76109, "recall_at_20": 0.82711, "recall_at_50": 0.92671, "recall_at_100": 0.94143, "precision_at_1": 0.57692, "precision_at_3": 0.30128, "precision_at_5": 0.22692, "precision_at_10": 0.14231, "precision_at_20": 0.08077, "precision_at_50": 0.04077, "precision_at_100": 0.02135, "mrr_at_1": 0.5769230769230769, "mrr_at_3": 0.6506410256410255, "mrr_at_5": 0.6689102564102564, "mrr_at_10": 0.6795329670329671, "mrr_at_20": 0.6852704987320373, "mrr_at_50": 0.6859573119188506, "mrr_at_100": 0.6859573119188506, "naucs_at_1_max": 0.5418911562542305, "naucs_at_1_std": 0.20055570120391908, "naucs_at_1_diff1": 0.5816182952833016, "naucs_at_3_max": 0.444887791729428, "naucs_at_3_std": 0.1878188817808082, "naucs_at_3_diff1": 0.24516714877709772, "naucs_at_5_max": 0.3576917143634376, "naucs_at_5_std": 0.3146793359298167, "naucs_at_5_diff1": 0.20231297302416876, "naucs_at_10_max": 0.30325232725570483, "naucs_at_10_std": 0.3104236154641994, "naucs_at_10_diff1": 0.15267960599125216, "naucs_at_20_max": 0.19027080117548262, "naucs_at_20_std": 0.25917580943335483, "naucs_at_20_diff1": 0.06740470085735437, "naucs_at_50_max": 0.03163322201193101, "naucs_at_50_std": 0.34919542888628285, "naucs_at_50_diff1": -0.13916843076016824, "naucs_at_100_max": -0.004174504355160278, "naucs_at_100_std": 0.3102330681956664, "naucs_at_100_diff1": -0.18342881515692896},
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.61638,
"ndcg_at_3": 0.56152,
"ndcg_at_5": 0.52766,
"ndcg_at_10": 0.50386,
"ndcg_at_20": 0.52905,
"ndcg_at_50": 0.59924,
"ndcg_at_100": 0.64499,
"map_at_1": 0.10966,
"map_at_3": 0.18025,
"map_at_5": 0.22059,
"map_at_10": 0.27303,
"map_at_20": 0.32152,
"map_at_50": 0.3761,
"map_at_100": 0.40404,
"recall_at_1": 0.10966,
"recall_at_3": 0.20523,
"recall_at_5": 0.26844,
"recall_at_10": 0.37487,
"recall_at_20": 0.51741,
"recall_at_50": 0.72401,
"recall_at_100": 0.86775,
"precision_at_1": 0.61638,
"precision_at_3": 0.50431,
"precision_at_5": 0.44655,
"precision_at_10": 0.35474,
"precision_at_20": 0.27328,
"precision_at_50": 0.18155,
"precision_at_100": 0.12065,
"mrr_at_1": 0.6163793103448276,
"mrr_at_3": 0.6925287356321839,
"mrr_at_5": 0.7102011494252874,
"mrr_at_10": 0.718962096332786,
"mrr_at_20": 0.7231871887024284,
"mrr_at_50": 0.7237159734553511,
"mrr_at_100": 0.7238004900205979,
"naucs_at_1_max": 0.34596784523504825,
"naucs_at_1_std": 0.05278856703331606,
"naucs_at_1_diff1": 0.3297587418314042,
"naucs_at_3_max": 0.5029144517937729,
"naucs_at_3_std": 0.2231019571062493,
"naucs_at_3_diff1": 0.20335115211304228,
"naucs_at_5_max": 0.5149206605759316,
"naucs_at_5_std": 0.26662174197070115,
"naucs_at_5_diff1": 0.14828813095199359,
"naucs_at_10_max": 0.4599324966715773,
"naucs_at_10_std": 0.2348731572168293,
"naucs_at_10_diff1": 0.09878469326052801,
"naucs_at_20_max": 0.3859484304972611,
"naucs_at_20_std": 0.23758331403387306,
"naucs_at_20_diff1": 0.03544769259787339,
"naucs_at_50_max": 0.3632517104190556,
"naucs_at_50_std": 0.2066927285873065,
"naucs_at_50_diff1": 0.006182684176672445,
"naucs_at_100_max": 0.3370599065344064,
"naucs_at_100_std": 0.1567879208284283,
"naucs_at_100_diff1": 0.002693165667338441
},
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.61111,
"ndcg_at_3": 0.58312,
"ndcg_at_5": 0.563,
"ndcg_at_10": 0.57366,
"ndcg_at_20": 0.61559,
"ndcg_at_50": 0.66698,
"ndcg_at_100": 0.69592,
"map_at_1": 0.29719,
"map_at_3": 0.37804,
"map_at_5": 0.40831,
"map_at_10": 0.45203,
"map_at_20": 0.48429,
"map_at_50": 0.50936,
"map_at_100": 0.51691,
"recall_at_1": 0.29719,
"recall_at_3": 0.43714,
"recall_at_5": 0.49859,
"recall_at_10": 0.60156,
"recall_at_20": 0.72609,
"recall_at_50": 0.86156,
"recall_at_100": 0.97535,
"precision_at_1": 0.61111,
"precision_at_3": 0.37963,
"precision_at_5": 0.29722,
"precision_at_10": 0.21528,
"precision_at_20": 0.14444,
"precision_at_50": 0.07889,
"precision_at_100": 0.04514,
"mrr_at_1": 0.625,
"mrr_at_3": 0.712962962962963,
"mrr_at_5": 0.7192129629629629,
"mrr_at_10": 0.723070987654321,
"mrr_at_20": 0.7278509299342633,
"mrr_at_50": 0.7284822430655764,
"mrr_at_100": 0.7293405298500758,
"naucs_at_1_max": 0.3848227484508222,
"naucs_at_1_std": -0.08000983619708767,
"naucs_at_1_diff1": 0.4657532875224316,
"naucs_at_3_max": 0.4586578479025003,
"naucs_at_3_std": 0.050520010863521786,
"naucs_at_3_diff1": 0.11894751048792912,
"naucs_at_5_max": 0.45814613208898153,
"naucs_at_5_std": 0.10036578017452273,
"naucs_at_5_diff1": 0.14226787478918548,
"naucs_at_10_max": 0.38933024700440644,
"naucs_at_10_std": 0.10908977639879786,
"naucs_at_10_diff1": 0.04126701611233207,
"naucs_at_20_max": 0.299286271613387,
"naucs_at_20_std": -0.04991115678400207,
"naucs_at_20_diff1": 0.023390444264937076,
"naucs_at_50_max": 0.29091680058769365,
"naucs_at_50_std": -0.09648752688031435,
"naucs_at_50_diff1": 0.005065536209402169,
"naucs_at_100_max": 0.27102010346173067,
"naucs_at_100_std": -0.09908878557247906,
"naucs_at_100_diff1": -0.034603469977902104
},
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
"ndcg_at_1": 0.59375,
"ndcg_at_3": 0.57457,
"ndcg_at_5": 0.59151,
"ndcg_at_10": 0.6304,
"ndcg_at_20": 0.66535,
"ndcg_at_50": 0.68685,
"ndcg_at_100": 0.69723,
"map_at_1": 0.36595,
"map_at_3": 0.46498,
"map_at_5": 0.50465,
"map_at_10": 0.54205,
"map_at_20": 0.55994,
"map_at_50": 0.56681,
"map_at_100": 0.56942,
"recall_at_1": 0.36595,
"recall_at_3": 0.52556,
"recall_at_5": 0.60479,
"recall_at_10": 0.71809,
"recall_at_20": 0.82006,
"recall_at_50": 0.88973,
"recall_at_100": 0.92353,
"precision_at_1": 0.59375,
"precision_at_3": 0.34792,
"precision_at_5": 0.2625,
"precision_at_10": 0.17125,
"precision_at_20": 0.105,
"precision_at_50": 0.04913,
"precision_at_100": 0.02706,
"mrr_at_1": 0.59375,
"mrr_at_3": 0.6770833333333333,
"mrr_at_5": 0.6845833333333333,
"mrr_at_10": 0.6923263888888889,
"mrr_at_20": 0.6966747366195896,
"mrr_at_50": 0.6977952203025732,
"mrr_at_100": 0.6977952203025732,
"naucs_at_1_max": 0.18948192493667948,
"naucs_at_1_std": -0.1857333640340778,
"naucs_at_1_diff1": 0.45310614782408476,
"naucs_at_3_max": 0.20793268621537397,
"naucs_at_3_std": 0.024502623108701212,
"naucs_at_3_diff1": -0.04161999138302425,
"naucs_at_5_max": 0.2595318634742594,
"naucs_at_5_std": 0.13124423827730436,
"naucs_at_5_diff1": -0.16963613458649673,
"naucs_at_10_max": 0.19737029268683812,
"naucs_at_10_std": 0.1127686152397857,
"naucs_at_10_diff1": -0.24609539671907257,
"naucs_at_20_max": 0.20107423764283505,
"naucs_at_20_std": 0.16350088306328306,
"naucs_at_20_diff1": -0.28002571180725316,
"naucs_at_50_max": 0.23619326963608264,
"naucs_at_50_std": 0.23592454685963232,
"naucs_at_50_diff1": -0.27406210481944604,
"naucs_at_100_max": 0.19490992689979728,
"naucs_at_100_std": 0.2159703887302359,
"naucs_at_100_diff1": -0.28808424783423425
},
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
"ndcg_at_1": 0.49123,
"ndcg_at_3": 0.52491,
"ndcg_at_5": 0.549,
"ndcg_at_10": 0.58069,
"ndcg_at_20": 0.62666,
"ndcg_at_50": 0.65351,
"ndcg_at_100": 0.66649,
"map_at_1": 0.27646,
"map_at_3": 0.39956,
"map_at_5": 0.43527,
"map_at_10": 0.46871,
"map_at_20": 0.49556,
"map_at_50": 0.50966,
"map_at_100": 0.51539,
"recall_at_1": 0.27646,
"recall_at_3": 0.47318,
"recall_at_5": 0.56021,
"recall_at_10": 0.67579,
"recall_at_20": 0.82222,
"recall_at_50": 0.89893,
"recall_at_100": 0.93567,
"precision_at_1": 0.49123,
"precision_at_3": 0.35673,
"precision_at_5": 0.27368,
"precision_at_10": 0.17544,
"precision_at_20": 0.11754,
"precision_at_50": 0.0607,
"precision_at_100": 0.03456,
"mrr_at_1": 0.45614035087719296,
"mrr_at_3": 0.5994152046783625,
"mrr_at_5": 0.62046783625731,
"mrr_at_10": 0.6268727373990532,
"mrr_at_20": 0.6315203386797814,
"mrr_at_50": 0.6315203386797814,
"mrr_at_100": 0.6315203386797814,
"naucs_at_1_max": 0.19051853845052494,
"naucs_at_1_std": 0.20355537207330812,
"naucs_at_1_diff1": -0.12302962095615802,
"naucs_at_3_max": 0.11577027220994451,
"naucs_at_3_std": 0.32989496542423047,
"naucs_at_3_diff1": -0.22744550186158394,
"naucs_at_5_max": 0.10743436129871246,
"naucs_at_5_std": 0.28731569705920795,
"naucs_at_5_diff1": -0.09799672764249866,
"naucs_at_10_max": -0.008835157538298827,
"naucs_at_10_std": 0.2455763435011526,
"naucs_at_10_diff1": -0.2055482467738796,
"naucs_at_20_max": 0.129319916224517,
"naucs_at_20_std": 0.34091567304281567,
"naucs_at_20_diff1": -0.13530127176926188,
"naucs_at_50_max": 0.17896877858786578,
"naucs_at_50_std": 0.3724755518204154,
"naucs_at_50_diff1": -0.16068264007399716,
"naucs_at_100_max": 0.1693644107812463,
"naucs_at_100_std": 0.37366292441647775,
"naucs_at_100_diff1": -0.19419560850304593
},
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
"ndcg_at_1": 0.47368,
"ndcg_at_3": 0.51876,
"ndcg_at_5": 0.55691,
"ndcg_at_10": 0.59054,
"ndcg_at_20": 0.62588,
"ndcg_at_50": 0.65188,
"ndcg_at_100": 0.66391,
"map_at_1": 0.25148,
"map_at_3": 0.38514,
"map_at_5": 0.43451,
"map_at_10": 0.46917,
"map_at_20": 0.49205,
"map_at_50": 0.50569,
"map_at_100": 0.51086,
"recall_at_1": 0.25148,
"recall_at_3": 0.47811,
"recall_at_5": 0.59638,
"recall_at_10": 0.71584,
"recall_at_20": 0.82752,
"recall_at_50": 0.90175,
"recall_at_100": 0.93555,
"precision_at_1": 0.47368,
"precision_at_3": 0.35234,
"precision_at_5": 0.28509,
"precision_at_10": 0.18465,
"precision_at_20": 0.11886,
"precision_at_50": 0.06123,
"precision_at_100": 0.03465,
"mrr_at_1": 0.47368421052631576,
"mrr_at_3": 0.6103801169590642,
"mrr_at_5": 0.6290204678362573,
"mrr_at_10": 0.6387444305207463,
"mrr_at_20": 0.6420700254194837,
"mrr_at_50": 0.6420700254194837,
"mrr_at_100": 0.6420700254194837,
"naucs_at_1_max": 0.021998290116773362,
"naucs_at_1_std": 0.20593892977264253,
"naucs_at_1_diff1": 0.04000630293480376,
"naucs_at_3_max": 0.16679520410206775,
"naucs_at_3_std": 0.2539255582748061,
"naucs_at_3_diff1": -0.1767759420056167,
"naucs_at_5_max": 0.18315159247533566,
"naucs_at_5_std": 0.19488231192523825,
"naucs_at_5_diff1": -0.09643606839804793,
"naucs_at_10_max": 0.11810099613857135,
"naucs_at_10_std": 0.19033260478147687,
"naucs_at_10_diff1": -0.16700233316285062,
"naucs_at_20_max": 0.22873578018421611,
"naucs_at_20_std": 0.2438357252829489,
"naucs_at_20_diff1": -0.12648824798942035,
"naucs_at_50_max": 0.29001817165730326,
"naucs_at_50_std": 0.30893614625589927,
"naucs_at_50_diff1": -0.15292878304478627,
"naucs_at_100_max": 0.295925982612213,
"naucs_at_100_std": 0.3439602802965318,
"naucs_at_100_diff1": -0.17862936586575465
},
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
"ndcg_at_1": 0.525,
"ndcg_at_3": 0.5325,
"ndcg_at_5": 0.55128,
"ndcg_at_10": 0.58866,
"ndcg_at_20": 0.62065,
"ndcg_at_50": 0.64723,
"ndcg_at_100": 0.65984,
"map_at_1": 0.3272,
"map_at_3": 0.42922,
"map_at_5": 0.4658,
"map_at_10": 0.49963,
"map_at_20": 0.5162,
"map_at_50": 0.52517,
"map_at_100": 0.5279,
"recall_at_1": 0.3272,
"recall_at_3": 0.49467,
"recall_at_5": 0.57378,
"recall_at_10": 0.68508,
"recall_at_20": 0.7775,
"recall_at_50": 0.86325,
"recall_at_100": 0.9108,
"precision_at_1": 0.525,
"precision_at_3": 0.32344,
"precision_at_5": 0.24781,
"precision_at_10": 0.16094,
"precision_at_20": 0.09875,
"precision_at_50": 0.04778,
"precision_at_100": 0.02647,
"mrr_at_1": 0.5296875,
"mrr_at_3": 0.61875,
"mrr_at_5": 0.631640625,
"mrr_at_10": 0.6416387648809524,
"mrr_at_20": 0.6464613335500284,
"mrr_at_50": 0.6478930503388797,
"mrr_at_100": 0.6479903319648815,
"naucs_at_1_max": 0.24778441527364697,
"naucs_at_1_std": -0.09729984958807641,
"naucs_at_1_diff1": 0.44067488804567034,
"naucs_at_3_max": 0.20943872715376793,
"naucs_at_3_std": -0.037746347965928524,
"naucs_at_3_diff1": 0.0466041739279314,
"naucs_at_5_max": 0.2001981257448891,
"naucs_at_5_std": 0.017847556855142162,
"naucs_at_5_diff1": -0.0495566981568709,
"naucs_at_10_max": 0.17331840747590824,
"naucs_at_10_std": 0.02726002662524363,
"naucs_at_10_diff1": -0.1258892790207611,
"naucs_at_20_max": 0.1754294886712855,
"naucs_at_20_std": 0.08596120348505716,
"naucs_at_20_diff1": -0.1873758078086679,
"naucs_at_50_max": 0.1887338703884953,
"naucs_at_50_std": 0.11705093889461508,
"naucs_at_50_diff1": -0.2122540480338123,
"naucs_at_100_max": 0.1568646905430392,
"naucs_at_100_std": 0.11574463637472221,
"naucs_at_100_diff1": -0.2397209331916511
},
"vidore/synthetic_axa_filtered_v1.0": {
"ndcg_at_1": 0.66667,
"ndcg_at_3": 0.68921,
"ndcg_at_5": 0.65541,
"ndcg_at_10": 0.67064,
"ndcg_at_20": 0.6892,
"ndcg_at_50": 0.74325,
"ndcg_at_100": 0.77033,
"map_at_1": 0.35099,
"map_at_3": 0.46331,
"map_at_5": 0.48943,
"map_at_10": 0.54347,
"map_at_20": 0.56799,
"map_at_50": 0.59849,
"map_at_100": 0.60632,
"recall_at_1": 0.35099,
"recall_at_3": 0.53798,
"recall_at_5": 0.5886,
"recall_at_10": 0.69355,
"recall_at_20": 0.75202,
"recall_at_50": 0.88548,
"recall_at_100": 0.99383,
"precision_at_1": 0.66667,
"precision_at_3": 0.44444,
"precision_at_5": 0.33333,
"precision_at_10": 0.25,
"precision_at_20": 0.15278,
"precision_at_50": 0.08444,
"precision_at_100": 0.04722,
"mrr_at_1": 0.7777777777777778,
"mrr_at_3": 0.8611111111111112,
"mrr_at_5": 0.8611111111111112,
"mrr_at_10": 0.8611111111111112,
"mrr_at_20": 0.8611111111111112,
"mrr_at_50": 0.8611111111111112,
"mrr_at_100": 0.8619929453262787,
"naucs_at_1_max": 0.4262448193676405,
"naucs_at_1_std": -0.7210395313068694,
"naucs_at_1_diff1": 0.48290890305613315,
"naucs_at_3_max": 0.2403382205448024,
"naucs_at_3_std": -0.26145924022609357,
"naucs_at_3_diff1": -0.281601100934536,
"naucs_at_5_max": 0.3431606151598846,
"naucs_at_5_std": -0.1758864067082082,
"naucs_at_5_diff1": -0.22109598304086536,
"naucs_at_10_max": 0.20395082823892463,
"naucs_at_10_std": 0.008923787088265448,
"naucs_at_10_diff1": -0.24131406720472492,
"naucs_at_20_max": 0.22154256455925808,
"naucs_at_20_std": -0.1379449851488306,
"naucs_at_20_diff1": -0.18566905572363052,
"naucs_at_50_max": 0.2350275712297213,
"naucs_at_50_std": -0.23479928995686508,
"naucs_at_50_diff1": -0.05729811655635159,
"naucs_at_100_max": 0.29761317883636684,
"naucs_at_100_std": -0.22647856705470173,
"naucs_at_100_diff1": -0.05321553752172787
},
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
"ndcg_at_1": 0.68966,
"ndcg_at_3": 0.65481,
"ndcg_at_5": 0.61545,
"ndcg_at_10": 0.58132,
"ndcg_at_20": 0.58431,
"ndcg_at_50": 0.64411,
"ndcg_at_100": 0.68704,
"map_at_1": 0.10859,
"map_at_3": 0.20301,
"map_at_5": 0.26051,
"map_at_10": 0.32196,
"map_at_20": 0.3692,
"map_at_50": 0.42135,
"map_at_100": 0.4502,
"recall_at_1": 0.10859,
"recall_at_3": 0.23833,
"recall_at_5": 0.31715,
"recall_at_10": 0.44498,
"recall_at_20": 0.56044,
"recall_at_50": 0.74643,
"recall_at_100": 0.88265,
"precision_at_1": 0.68966,
"precision_at_3": 0.60345,
"precision_at_5": 0.53448,
"precision_at_10": 0.41379,
"precision_at_20": 0.2931,
"precision_at_50": 0.18724,
"precision_at_100": 0.12379,
"mrr_at_1": 0.6896551724137931,
"mrr_at_3": 0.7701149425287356,
"mrr_at_5": 0.782183908045977,
"mrr_at_10": 0.7891283524904215,
"mrr_at_20": 0.7918451758969001,
"mrr_at_50": 0.7918451758969001,
"mrr_at_100": 0.7918451758969001,
"naucs_at_1_max": 0.3245006997523202,
"naucs_at_1_std": -0.06482007482463782,
"naucs_at_1_diff1": 0.3078527258382627,
"naucs_at_3_max": 0.525076097209777,
"naucs_at_3_std": 0.2467588492065337,
"naucs_at_3_diff1": 0.20861089363774643,
"naucs_at_5_max": 0.5094414808154117,
"naucs_at_5_std": 0.31493109273776154,
"naucs_at_5_diff1": 0.13697802644327908,
"naucs_at_10_max": 0.3893182946127188,
"naucs_at_10_std": 0.17799947164356045,
"naucs_at_10_diff1": 0.0839404364515122,
"naucs_at_20_max": 0.33715384913150076,
"naucs_at_20_std": 0.23677079050318373,
"naucs_at_20_diff1": -0.004414568467661759,
"naucs_at_50_max": 0.29927692739083983,
"naucs_at_50_std": 0.20505150041100245,
"naucs_at_50_diff1": -0.0542579517041488,
"naucs_at_100_max": 0.22924912758168547,
"naucs_at_100_std": 0.11415171678422828,
"naucs_at_100_diff1": -0.03736088904371261
}, "vidore/arxivqa_test_subsampled": {"ndcg_at_1": 0.794, "ndcg_at_3": 0.84612, "ndcg_at_5": 0.85584, "ndcg_at_10": 0.86884, "ndcg_at_20": 0.87552, "ndcg_at_100": 0.88006, "ndcg_at_1000": 0.88061, "map_at_1": 0.794, "map_at_3": 0.83367, "map_at_5": 0.83897, "map_at_10": 0.84437, "map_at_20": 0.84626, "map_at_100": 0.84692, "map_at_1000": 0.84695, "recall_at_1": 0.794, "recall_at_3": 0.882, "recall_at_5": 0.906, "recall_at_10": 0.946, "recall_at_20": 0.972, "recall_at_100": 0.996, "recall_at_1000": 1.0, "precision_at_1": 0.794, "precision_at_3": 0.294, "precision_at_5": 0.1812, "precision_at_10": 0.0946, "precision_at_20": 0.0486, "precision_at_100": 0.00996, "precision_at_1000": 0.001, "mrr_at_1": 0.794, "mrr_at_3": 0.8333333333333334, "mrr_at_5": 0.8385333333333332, "mrr_at_10": 0.8440206349206347, "mrr_at_20": 0.8457624946948473, "mrr_at_100": 0.8464318523346234, "mrr_at_1000": 0.8464586755347477, "naucs_at_1_max": 0.0264204919913496, "naucs_at_1_std": -0.4432218159450506, "naucs_at_1_diff1": 0.8754399753955507, "naucs_at_3_max": -0.08298212469117683, "naucs_at_3_std": -0.5738264787094874, "naucs_at_3_diff1": 0.8379192300860663, "naucs_at_5_max": -0.07192522399030574, "naucs_at_5_std": -0.5486421518962216, "naucs_at_5_diff1": 0.8177285098436528, "naucs_at_10_max": -0.30577169139260696, "naucs_at_10_std": -0.7531728740879055, "naucs_at_10_diff1": 0.8244112459798737, "naucs_at_20_max": -0.2807456315859826, "naucs_at_20_std": -0.4205348806189298, "naucs_at_20_diff1": 0.882953181272511, "naucs_at_100_max": -1.7399626517274025, "naucs_at_100_std": 0.34897292250231704, "naucs_at_100_diff1": 0.8611111111111168, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/docvqa_test_subsampled": {"ndcg_at_1": 0.48337, "ndcg_at_3": 0.55403, "ndcg_at_5": 0.5713, "ndcg_at_10": 0.60081, "ndcg_at_20": 0.61311, "ndcg_at_100": 0.63676, "ndcg_at_1000": 0.64891, "map_at_1": 0.48337, "map_at_3": 0.53769, "map_at_5": 0.54723, "map_at_10": 0.55947, "map_at_20": 0.56283, "map_at_100": 0.56619, "map_at_1000": 0.56674, "recall_at_1": 0.48337, "recall_at_3": 0.60089, "recall_at_5": 0.64302, "recall_at_10": 0.73392, "recall_at_20": 0.78271, "recall_at_100": 0.90909, "recall_at_1000": 1.0, "precision_at_1": 0.48337, "precision_at_3": 0.2003, "precision_at_5": 0.1286, "precision_at_10": 0.07339, "precision_at_20": 0.03914, "precision_at_100": 0.00909, "precision_at_1000": 0.001, "mrr_at_1": 0.4878048780487805, "mrr_at_3": 0.5395417590539542, "mrr_at_5": 0.5487435328898742, "mrr_at_10": 0.5610539189807481, "mrr_at_20": 0.5648169761114504, "mrr_at_100": 0.5681408169734422, "mrr_at_1000": 0.5686621426973844, "naucs_at_1_max": -0.5212133012346877, "naucs_at_1_std": -0.09288577096523737, "naucs_at_1_diff1": 0.7503022682010474, "naucs_at_3_max": -0.6565880303875717, "naucs_at_3_std": -0.07460405832901369, "naucs_at_3_diff1": 0.6561082577501688, "naucs_at_5_max": -0.5943855392066872, "naucs_at_5_std": -0.05220343159264611, "naucs_at_5_diff1": 0.6238399743739096, "naucs_at_10_max": -0.6195908132701516, "naucs_at_10_std": 0.13900687126802166, "naucs_at_10_diff1": 0.558265195499329, "naucs_at_20_max": -0.6615869284465803, "naucs_at_20_std": 0.1387067044872028, "naucs_at_20_diff1": 0.5554270724438797, "naucs_at_100_max": -0.7684732285094673, "naucs_at_100_std": 0.45832384986805724, "naucs_at_100_diff1": 0.4903408194281384, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/infovqa_test_subsampled": {"ndcg_at_1": 0.81377, "ndcg_at_3": 0.86726, "ndcg_at_5": 0.88059, "ndcg_at_10": 0.89071, "ndcg_at_20": 0.89184, "ndcg_at_100": 0.89493, "ndcg_at_1000": 0.89651, "map_at_1": 0.81377, "map_at_3": 0.85425, "map_at_5": 0.86164, "map_at_10": 0.866, "map_at_20": 0.86637, "map_at_100": 0.86683, "map_at_1000": 0.86689, "recall_at_1": 0.81377, "recall_at_3": 0.90486, "recall_at_5": 0.93725, "recall_at_10": 0.96761, "recall_at_20": 0.97166, "recall_at_100": 0.98785, "recall_at_1000": 1.0, "precision_at_1": 0.81377, "precision_at_3": 0.30162, "precision_at_5": 0.18745, "precision_at_10": 0.09676, "precision_at_20": 0.04858, "precision_at_100": 0.00988, "precision_at_1000": 0.001, "mrr_at_1": 0.8137651821862348, "mrr_at_3": 0.8542510121457486, "mrr_at_5": 0.8617408906882587, "mrr_at_10": 0.866114002956108, "mrr_at_20": 0.8665832705306387, "mrr_at_100": 0.8669491238036686, "mrr_at_1000": 0.8670130381350266, "naucs_at_1_max": 0.08332768086513993, "naucs_at_1_std": -0.16693401490742565, "naucs_at_1_diff1": 0.9069340613475471, "naucs_at_3_max": 0.0011369168562785203, "naucs_at_3_std": -0.14976111225508304, "naucs_at_3_diff1": 0.8389370588773137, "naucs_at_5_max": -0.0749515972070914, "naucs_at_5_std": -0.08214044161222527, "naucs_at_5_diff1": 0.8372514892403252, "naucs_at_10_max": -0.1502345681826907, "naucs_at_10_std": 0.5637465376812698, "naucs_at_10_diff1": 0.7969878779414252, "naucs_at_20_max": -0.20287146290299748, "naucs_at_20_std": 0.6550388680835327, "naucs_at_20_diff1": 0.7878243417729163, "naucs_at_100_max": -0.6623458938523301, "naucs_at_100_std": 0.7639533363794858, "naucs_at_100_diff1": 0.8604151369738356, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/tabfquad_test_subsampled": {"ndcg_at_1": 0.875, "ndcg_at_3": 0.92487, "ndcg_at_5": 0.93087, "ndcg_at_10": 0.93426, "ndcg_at_20": 0.93601, "ndcg_at_100": 0.93739, "ndcg_at_1000": 0.93739, "map_at_1": 0.875, "map_at_3": 0.9125, "map_at_5": 0.91589, "map_at_10": 0.91725, "map_at_20": 0.91769, "map_at_100": 0.91791, "map_at_1000": 0.91791, "recall_at_1": 0.875, "recall_at_3": 0.96071, "recall_at_5": 0.975, "recall_at_10": 0.98571, "recall_at_20": 0.99286, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.875, "precision_at_3": 0.32024, "precision_at_5": 0.195, "precision_at_10": 0.09857, "precision_at_20": 0.04964, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.8678571428571429, "mrr_at_3": 0.9101190476190477, "mrr_at_5": 0.9135119047619048, "mrr_at_10": 0.9148653628117914, "mrr_at_20": 0.9153266723356009, "mrr_at_100": 0.9155495426855899, "mrr_at_1000": 0.9155495426855899, "naucs_at_1_max": 0.6341186138885083, "naucs_at_1_std": -0.33273524174770575, "naucs_at_1_diff1": 0.8733735104780164, "naucs_at_3_max": 0.7835922247686966, "naucs_at_3_std": -0.27565571683218926, "naucs_at_3_diff1": 0.8767082590612036, "naucs_at_5_max": 0.8832866479925309, "naucs_at_5_std": -0.041149793250630305, "naucs_at_5_diff1": 0.885620915032675, "naucs_at_10_max": 0.8978758169934754, "naucs_at_10_std": 0.022175536881420224, "naucs_at_10_diff1": 0.8692810457516408, "naucs_at_20_max": 0.8611111111111035, "naucs_at_20_std": 0.41433239962653884, "naucs_at_20_diff1": 0.8692810457516309, "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": {"ndcg_at_1": 0.54192, "ndcg_at_3": 0.65843, "ndcg_at_5": 0.69378, "ndcg_at_10": 0.71916, "ndcg_at_20": 0.73058, "ndcg_at_100": 0.73824, "ndcg_at_1000": 0.73959, "map_at_1": 0.54192, "map_at_3": 0.63001, "map_at_5": 0.64967, "map_at_10": 0.66004, "map_at_20": 0.6632, "map_at_100": 0.66435, "map_at_1000": 0.66442, "recall_at_1": 0.54192, "recall_at_3": 0.74058, "recall_at_5": 0.82625, "recall_at_10": 0.90522, "recall_at_20": 0.95018, "recall_at_100": 0.99028, "recall_at_1000": 1.0, "precision_at_1": 0.54192, "precision_at_3": 0.24686, "precision_at_5": 0.16525, "precision_at_10": 0.09052, "precision_at_20": 0.04751, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.540097205346294, "mrr_at_3": 0.6291008505467812, "mrr_at_5": 0.6485722964763079, "mrr_at_10": 0.6587733128893529, "mrr_at_20": 0.6620815452578555, "mrr_at_100": 0.6632579676072735, "mrr_at_1000": 0.6633336632341336, "naucs_at_1_max": -0.058378738250013384, "naucs_at_1_std": -0.22221425489777502, "naucs_at_1_diff1": 0.7291748780182709, "naucs_at_3_max": -0.07682812054313384, "naucs_at_3_std": -0.24718525281474638, "naucs_at_3_diff1": 0.6115470895642744, "naucs_at_5_max": -0.07888770379939952, "naucs_at_5_std": -0.19457655229648088, "naucs_at_5_diff1": 0.5914062739597068, "naucs_at_10_max": 0.0029404715257986057, "naucs_at_10_std": -0.05548744311414097, "naucs_at_10_diff1": 0.5356727090689206, "naucs_at_20_max": -0.004305759775130589, "naucs_at_20_std": 0.2822864075893588, "naucs_at_20_diff1": 0.5157529604916903, "naucs_at_100_max": -0.04774510029921774, "naucs_at_100_std": 0.8056862206490103, "naucs_at_100_diff1": 0.5126658383723813, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/shiftproject_test": {"ndcg_at_1": 0.68, "ndcg_at_3": 0.79595, "ndcg_at_5": 0.8196, "ndcg_at_10": 0.83596, "ndcg_at_20": 0.83866, "ndcg_at_100": 0.84072, "ndcg_at_1000": 0.84072, "map_at_1": 0.68, "map_at_3": 0.77, "map_at_5": 0.7825, "map_at_10": 0.78935, "map_at_20": 0.79018, "map_at_100": 0.79054, "map_at_1000": 0.79054, "recall_at_1": 0.68, "recall_at_3": 0.87, "recall_at_5": 0.93, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.68, "precision_at_3": 0.29, "precision_at_5": 0.186, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.7, "mrr_at_3": 0.775, "mrr_at_5": 0.7915000000000001, "mrr_at_10": 0.7985238095238096, "mrr_at_20": 0.799357142857143, "mrr_at_100": 0.7997142857142859, "mrr_at_1000": 0.7997142857142859, "naucs_at_1_max": 0.2058945477161214, "naucs_at_1_std": -0.3255476470181746, "naucs_at_1_diff1": 0.6658489392578257, "naucs_at_3_max": 0.26312671258238784, "naucs_at_3_std": -0.1116418573650315, "naucs_at_3_diff1": 0.5204769310523577, "naucs_at_5_max": 0.26463918900894084, "naucs_at_5_std": 0.08563425370148234, "naucs_at_5_diff1": 0.3650126717353644, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": 0.12278244631185727, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": 0.12278244631185926, "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}, "vidore/syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.94, "ndcg_at_3": 0.97024, "ndcg_at_5": 0.97454, "ndcg_at_10": 0.97454, "ndcg_at_20": 0.97454, "ndcg_at_100": 0.97454, "ndcg_at_1000": 0.97454, "map_at_1": 0.94, "map_at_3": 0.96333, "map_at_5": 0.96583, "map_at_10": 0.96583, "map_at_20": 0.96583, "map_at_100": 0.96583, "map_at_1000": 0.96583, "recall_at_1": 0.94, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.94, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.9633333333333333, "mrr_at_5": 0.9658333333333333, "mrr_at_10": 0.9658333333333333, "mrr_at_20": 0.9658333333333333, "mrr_at_100": 0.9658333333333333, "mrr_at_1000": 0.9658333333333333, "naucs_at_1_max": 0.28003423591658866, "naucs_at_1_std": -0.3201058201058171, "naucs_at_1_diff1": 0.9564270152505444, "naucs_at_3_max": 1.0, "naucs_at_3_std": -0.5634920634921204, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_energy_test": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.91655, "ndcg_at_5": 0.92859, "ndcg_at_10": 0.9316, "ndcg_at_20": 0.9316, "ndcg_at_100": 0.93378, "ndcg_at_1000": 0.93378, "map_at_1": 0.87, "map_at_3": 0.905, "map_at_5": 0.9115, "map_at_10": 0.91261, "map_at_20": 0.91261, "map_at_100": 0.91305, "map_at_1000": 0.91305, "recall_at_1": 0.87, "recall_at_3": 0.95, "recall_at_5": 0.98, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.31667, "precision_at_5": 0.196, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.87, "mrr_at_3": 0.91, "mrr_at_5": 0.9139999999999999, "mrr_at_10": 0.9152499999999999, "mrr_at_20": 0.9152499999999999, "mrr_at_100": 0.9157045454545454, "mrr_at_1000": 0.9157045454545454, "naucs_at_1_max": 0.2051766274161294, "naucs_at_1_std": -0.443160779086129, "naucs_at_1_diff1": 0.9218692142486855, "naucs_at_3_max": -0.14724556489262278, "naucs_at_3_std": -0.7007469654528471, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": -0.661531279178339, "naucs_at_5_std": -0.9556489262371534, "naucs_at_5_diff1": 0.9346405228758136, "naucs_at_10_max": -1.1517273576097316, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": -1.1517273576097316, "naucs_at_20_std": -1.7399626517273863, "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}, "vidore/syntheticDocQA_government_reports_test": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.95655, "ndcg_at_5": 0.96042, "ndcg_at_10": 0.96398, "ndcg_at_20": 0.96398, "ndcg_at_100": 0.96398, "ndcg_at_1000": 0.96398, "map_at_1": 0.92, "map_at_3": 0.94833, "map_at_5": 0.95033, "map_at_10": 0.952, "map_at_20": 0.952, "map_at_100": 0.952, "map_at_1000": 0.952, "recall_at_1": 0.92, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.94, "mrr_at_3": 0.9583333333333333, "mrr_at_5": 0.9603333333333333, "mrr_at_10": 0.9620000000000001, "mrr_at_20": 0.9620000000000001, "mrr_at_100": 0.9620000000000001, "mrr_at_1000": 0.9620000000000001, "naucs_at_1_max": 0.8082983193277313, "naucs_at_1_std": -0.12400793650793779, "naucs_at_1_diff1": 0.9325980392156855, "naucs_at_3_max": 0.7770774976657261, "naucs_at_3_std": -0.9556489262371661, "naucs_at_3_diff1": 0.8611111111111119, "naucs_at_5_max": 0.5541549953314738, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.7222222222222276, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_healthcare_industry_test": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.96417, "ndcg_at_5": 0.96417, "ndcg_at_10": 0.96417, "ndcg_at_20": 0.96417, "ndcg_at_100": 0.96417, "ndcg_at_1000": 0.96417, "map_at_1": 0.91, "map_at_3": 0.95167, "map_at_5": 0.95167, "map_at_10": 0.95167, "map_at_20": 0.95167, "map_at_100": 0.95167, "map_at_1000": 0.95167, "recall_at_1": 0.91, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.9583333333333335, "mrr_at_5": 0.9583333333333335, "mrr_at_10": 0.9583333333333335, "mrr_at_20": 0.9583333333333335, "mrr_at_100": 0.9583333333333335, "mrr_at_1000": 0.9583333333333335, "naucs_at_1_max": 0.6672891378773725, "naucs_at_1_std": -0.03304284676833719, "naucs_at_1_diff1": 0.9400871459694983, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}