Update results.json
Browse files- results.json +1 -466
results.json
CHANGED
|
@@ -1,466 +1 @@
|
|
| 1 |
-
{"vidore/esg_reports_human_labeled_v2": {"ndcg_at_1": 0.62179, "ndcg_at_3": 0.57934, "ndcg_at_5": 0.62234, "ndcg_at_10": 0.65262, "ndcg_at_20": 0.67475, "ndcg_at_50": 0.70087, "ndcg_at_100": 0.71211, "map_at_1": 0.43526, "map_at_3": 0.50267, "map_at_5": 0.55008, "map_at_10": 0.57335, "map_at_20": 0.58435, "map_at_50": 0.59308, "map_at_100": 0.5954, "recall_at_1": 0.43526, "recall_at_3": 0.53333, "recall_at_5": 0.66204, "recall_at_10": 0.75262, "recall_at_20": 0.81833, "recall_at_50": 0.91518, "recall_at_100": 0.96614, "precision_at_1": 0.63462, "precision_at_3": 0.30769, "precision_at_5": 0.24615, "precision_at_10": 0.14808, "precision_at_20": 0.08654, "precision_at_50": 0.04115, "precision_at_100": 0.02212, "mrr_at_1": 0.5961538461538461, "mrr_at_3": 0.6442307692307693, "mrr_at_5": 0.6721153846153847, "mrr_at_10": 0.678792735042735, "mrr_at_20": 0.6830509768009766, "mrr_at_50": 0.6843387515262513, "mrr_at_100": 0.6846592643467642, "naucs_at_1_max": 0.007278669575223614, "naucs_at_1_std": -0.16862511436532815, "naucs_at_1_diff1": 0.37195886708166814, "naucs_at_3_max": -0.11224357092950424, "naucs_at_3_std": -0.13484611004600808, "naucs_at_3_diff1": 0.12647962031083498, "naucs_at_5_max": -0.08235536599427677, "naucs_at_5_std": 0.029280898603991155, "naucs_at_5_diff1": 0.03850576951146517, "naucs_at_10_max": -0.05329392017057177, "naucs_at_10_std": 0.07795337723139084, "naucs_at_10_diff1": -0.13170232588923755, "naucs_at_20_max": -0.13017358757688524, "naucs_at_20_std": -0.008088492748358699, "naucs_at_20_diff1": -0.2193370407928556, "naucs_at_50_max": -0.09015721409307421, "naucs_at_50_std": 0.022247428759607314, "naucs_at_50_diff1": -0.2736453927338279, "naucs_at_100_max": -0.14696693886931617, "naucs_at_100_std": -0.010945474748335252, "naucs_at_100_diff1": -0.3271662812920136},
|
| 2 |
-
"vidore/economics_reports_v2": {
|
| 3 |
-
"ndcg_at_1": 0.55603,
|
| 4 |
-
"ndcg_at_3": 0.54807,
|
| 5 |
-
"ndcg_at_5": 0.53157,
|
| 6 |
-
"ndcg_at_10": 0.5146,
|
| 7 |
-
"ndcg_at_20": 0.54585,
|
| 8 |
-
"ndcg_at_50": 0.61451,
|
| 9 |
-
"ndcg_at_100": 0.6553,
|
| 10 |
-
"map_at_1": 0.0783,
|
| 11 |
-
"map_at_3": 0.16664,
|
| 12 |
-
"map_at_5": 0.21874,
|
| 13 |
-
"map_at_10": 0.28014,
|
| 14 |
-
"map_at_20": 0.3378,
|
| 15 |
-
"map_at_50": 0.39242,
|
| 16 |
-
"map_at_100": 0.42099,
|
| 17 |
-
"recall_at_1": 0.0783,
|
| 18 |
-
"recall_at_3": 0.20216,
|
| 19 |
-
"recall_at_5": 0.28814,
|
| 20 |
-
"recall_at_10": 0.41158,
|
| 21 |
-
"recall_at_20": 0.55969,
|
| 22 |
-
"recall_at_50": 0.76372,
|
| 23 |
-
"recall_at_100": 0.88571,
|
| 24 |
-
"precision_at_1": 0.55603,
|
| 25 |
-
"precision_at_3": 0.51293,
|
| 26 |
-
"precision_at_5": 0.47328,
|
| 27 |
-
"precision_at_10": 0.38103,
|
| 28 |
-
"precision_at_20": 0.29483,
|
| 29 |
-
"precision_at_50": 0.18716,
|
| 30 |
-
"precision_at_100": 0.1244,
|
| 31 |
-
"mrr_at_1": 0.5474137931034483,
|
| 32 |
-
"mrr_at_3": 0.6666666666666666,
|
| 33 |
-
"mrr_at_5": 0.6847701149425288,
|
| 34 |
-
"mrr_at_10": 0.6911022167487685,
|
| 35 |
-
"mrr_at_20": 0.6938394796748926,
|
| 36 |
-
"mrr_at_50": 0.6948904461025456,
|
| 37 |
-
"mrr_at_100": 0.6948904461025456,
|
| 38 |
-
"naucs_at_1_max": 0.07994091110523227,
|
| 39 |
-
"naucs_at_1_std": 0.12444987153144782,
|
| 40 |
-
"naucs_at_1_diff1": 0.09424460432630058,
|
| 41 |
-
"naucs_at_3_max": 0.16923654602805172,
|
| 42 |
-
"naucs_at_3_std": 0.2045449370458442,
|
| 43 |
-
"naucs_at_3_diff1": 0.09926647816044282,
|
| 44 |
-
"naucs_at_5_max": 0.17728557191005953,
|
| 45 |
-
"naucs_at_5_std": 0.2565334951047491,
|
| 46 |
-
"naucs_at_5_diff1": 0.07759845826151261,
|
| 47 |
-
"naucs_at_10_max": 0.13245740814133947,
|
| 48 |
-
"naucs_at_10_std": 0.21617752015273486,
|
| 49 |
-
"naucs_at_10_diff1": 0.023098575182872085,
|
| 50 |
-
"naucs_at_20_max": 0.0673142638543018,
|
| 51 |
-
"naucs_at_20_std": 0.19206721484700626,
|
| 52 |
-
"naucs_at_20_diff1": -0.007872307371572145,
|
| 53 |
-
"naucs_at_50_max": -0.02207912884522245,
|
| 54 |
-
"naucs_at_50_std": 0.14587302006330063,
|
| 55 |
-
"naucs_at_50_diff1": -0.048901378247186766,
|
| 56 |
-
"naucs_at_100_max": -0.07381834254515347,
|
| 57 |
-
"naucs_at_100_std": 0.10309591458261987,
|
| 58 |
-
"naucs_at_100_diff1": -0.0369817902657747
|
| 59 |
-
},
|
| 60 |
-
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
| 61 |
-
"ndcg_at_1": 0.55556,
|
| 62 |
-
"ndcg_at_3": 0.57286,
|
| 63 |
-
"ndcg_at_5": 0.57184,
|
| 64 |
-
"ndcg_at_10": 0.57514,
|
| 65 |
-
"ndcg_at_20": 0.60015,
|
| 66 |
-
"ndcg_at_50": 0.64497,
|
| 67 |
-
"ndcg_at_100": 0.67229,
|
| 68 |
-
"map_at_1": 0.27024,
|
| 69 |
-
"map_at_3": 0.35733,
|
| 70 |
-
"map_at_5": 0.40728,
|
| 71 |
-
"map_at_10": 0.4556,
|
| 72 |
-
"map_at_20": 0.48059,
|
| 73 |
-
"map_at_50": 0.50401,
|
| 74 |
-
"map_at_100": 0.51134,
|
| 75 |
-
"recall_at_1": 0.27024,
|
| 76 |
-
"recall_at_3": 0.42572,
|
| 77 |
-
"recall_at_5": 0.50846,
|
| 78 |
-
"recall_at_10": 0.61625,
|
| 79 |
-
"recall_at_20": 0.70808,
|
| 80 |
-
"recall_at_50": 0.81979,
|
| 81 |
-
"recall_at_100": 0.92724,
|
| 82 |
-
"precision_at_1": 0.55556,
|
| 83 |
-
"precision_at_3": 0.40741,
|
| 84 |
-
"precision_at_5": 0.34444,
|
| 85 |
-
"precision_at_10": 0.24028,
|
| 86 |
-
"precision_at_20": 0.15,
|
| 87 |
-
"precision_at_50": 0.07972,
|
| 88 |
-
"precision_at_100": 0.04542,
|
| 89 |
-
"mrr_at_1": 0.5138888888888888,
|
| 90 |
-
"mrr_at_3": 0.6388888888888888,
|
| 91 |
-
"mrr_at_5": 0.6486111111111111,
|
| 92 |
-
"mrr_at_10": 0.6532407407407407,
|
| 93 |
-
"mrr_at_20": 0.6550035612535612,
|
| 94 |
-
"mrr_at_50": 0.6554515899273964,
|
| 95 |
-
"mrr_at_100": 0.6562765438177584,
|
| 96 |
-
"naucs_at_1_max": 0.06394991291872823,
|
| 97 |
-
"naucs_at_1_std": 0.2339109450954795,
|
| 98 |
-
"naucs_at_1_diff1": 0.30591875421589343,
|
| 99 |
-
"naucs_at_3_max": -0.17975083964563082,
|
| 100 |
-
"naucs_at_3_std": 0.027577428119795747,
|
| 101 |
-
"naucs_at_3_diff1": 0.09852366590105074,
|
| 102 |
-
"naucs_at_5_max": -0.23673003232880171,
|
| 103 |
-
"naucs_at_5_std": -0.01855706256438857,
|
| 104 |
-
"naucs_at_5_diff1": 0.03504088887398939,
|
| 105 |
-
"naucs_at_10_max": -0.32103926214321127,
|
| 106 |
-
"naucs_at_10_std": -0.06117912492226144,
|
| 107 |
-
"naucs_at_10_diff1": -0.14080922308311572,
|
| 108 |
-
"naucs_at_20_max": -0.34694147283910304,
|
| 109 |
-
"naucs_at_20_std": -0.04490360729046198,
|
| 110 |
-
"naucs_at_20_diff1": -0.17565284792297425,
|
| 111 |
-
"naucs_at_50_max": -0.3890920945387956,
|
| 112 |
-
"naucs_at_50_std": -0.06731905750861354,
|
| 113 |
-
"naucs_at_50_diff1": -0.19417578723003429,
|
| 114 |
-
"naucs_at_100_max": -0.41189447174112953,
|
| 115 |
-
"naucs_at_100_std": -0.0755751130681716,
|
| 116 |
-
"naucs_at_100_diff1": -0.21048470142462247
|
| 117 |
-
},
|
| 118 |
-
"vidore/biomedical_lectures_eng_v2": {
|
| 119 |
-
"ndcg_at_1": 0.59375,
|
| 120 |
-
"ndcg_at_3": 0.59937,
|
| 121 |
-
"ndcg_at_5": 0.6176,
|
| 122 |
-
"ndcg_at_10": 0.65125,
|
| 123 |
-
"ndcg_at_20": 0.68031,
|
| 124 |
-
"ndcg_at_50": 0.70414,
|
| 125 |
-
"ndcg_at_100": 0.7118,
|
| 126 |
-
"map_at_1": 0.35678,
|
| 127 |
-
"map_at_3": 0.48409,
|
| 128 |
-
"map_at_5": 0.52133,
|
| 129 |
-
"map_at_10": 0.55746,
|
| 130 |
-
"map_at_20": 0.57311,
|
| 131 |
-
"map_at_50": 0.582,
|
| 132 |
-
"map_at_100": 0.58404,
|
| 133 |
-
"recall_at_1": 0.35678,
|
| 134 |
-
"recall_at_3": 0.5553,
|
| 135 |
-
"recall_at_5": 0.6424,
|
| 136 |
-
"recall_at_10": 0.74954,
|
| 137 |
-
"recall_at_20": 0.83273,
|
| 138 |
-
"recall_at_50": 0.90356,
|
| 139 |
-
"recall_at_100": 0.92956,
|
| 140 |
-
"precision_at_1": 0.59375,
|
| 141 |
-
"precision_at_3": 0.36875,
|
| 142 |
-
"precision_at_5": 0.2775,
|
| 143 |
-
"precision_at_10": 0.18,
|
| 144 |
-
"precision_at_20": 0.10656,
|
| 145 |
-
"precision_at_50": 0.05138,
|
| 146 |
-
"precision_at_100": 0.02756,
|
| 147 |
-
"mrr_at_1": 0.5875,
|
| 148 |
-
"mrr_at_3": 0.6791666666666667,
|
| 149 |
-
"mrr_at_5": 0.6979166666666667,
|
| 150 |
-
"mrr_at_10": 0.7059871031746032,
|
| 151 |
-
"mrr_at_20": 0.7082808189563704,
|
| 152 |
-
"mrr_at_50": 0.7090456790962306,
|
| 153 |
-
"mrr_at_100": 0.7091433353462306,
|
| 154 |
-
"naucs_at_1_max": 0.249983882109141,
|
| 155 |
-
"naucs_at_1_std": -0.041280221045360686,
|
| 156 |
-
"naucs_at_1_diff1": 0.4059037531660143,
|
| 157 |
-
"naucs_at_3_max": 0.01878691845110894,
|
| 158 |
-
"naucs_at_3_std": -0.06513153750357396,
|
| 159 |
-
"naucs_at_3_diff1": -0.04117906448220925,
|
| 160 |
-
"naucs_at_5_max": -0.03604209381453121,
|
| 161 |
-
"naucs_at_5_std": -0.026999419446342467,
|
| 162 |
-
"naucs_at_5_diff1": -0.2004747312183539,
|
| 163 |
-
"naucs_at_10_max": -0.15546557639975261,
|
| 164 |
-
"naucs_at_10_std": -0.12249727214166432,
|
| 165 |
-
"naucs_at_10_diff1": -0.28313723428030524,
|
| 166 |
-
"naucs_at_20_max": -0.230360039337395,
|
| 167 |
-
"naucs_at_20_std": -0.11871250920639782,
|
| 168 |
-
"naucs_at_20_diff1": -0.35374918579255926,
|
| 169 |
-
"naucs_at_50_max": -0.21935608877014798,
|
| 170 |
-
"naucs_at_50_std": -0.04506401935703416,
|
| 171 |
-
"naucs_at_50_diff1": -0.34518311048379996,
|
| 172 |
-
"naucs_at_100_max": -0.22834972168166315,
|
| 173 |
-
"naucs_at_100_std": -0.04987710526052404,
|
| 174 |
-
"naucs_at_100_diff1": -0.33362168437999984
|
| 175 |
-
},
|
| 176 |
-
"vidore/esg_reports_eng_v2": {
|
| 177 |
-
"ndcg_at_1": 0.52632,
|
| 178 |
-
"ndcg_at_3": 0.48702,
|
| 179 |
-
"ndcg_at_5": 0.53392,
|
| 180 |
-
"ndcg_at_10": 0.5786,
|
| 181 |
-
"ndcg_at_20": 0.62288,
|
| 182 |
-
"ndcg_at_50": 0.64776,
|
| 183 |
-
"ndcg_at_100": 0.66238,
|
| 184 |
-
"map_at_1": 0.23981,
|
| 185 |
-
"map_at_3": 0.34792,
|
| 186 |
-
"map_at_5": 0.408,
|
| 187 |
-
"map_at_10": 0.4528,
|
| 188 |
-
"map_at_20": 0.48189,
|
| 189 |
-
"map_at_50": 0.49681,
|
| 190 |
-
"map_at_100": 0.50309,
|
| 191 |
-
"recall_at_1": 0.23981,
|
| 192 |
-
"recall_at_3": 0.41261,
|
| 193 |
-
"recall_at_5": 0.55802,
|
| 194 |
-
"recall_at_10": 0.71472,
|
| 195 |
-
"recall_at_20": 0.85539,
|
| 196 |
-
"recall_at_50": 0.9246,
|
| 197 |
-
"recall_at_100": 0.97368,
|
| 198 |
-
"precision_at_1": 0.52632,
|
| 199 |
-
"precision_at_3": 0.35088,
|
| 200 |
-
"precision_at_5": 0.29474,
|
| 201 |
-
"precision_at_10": 0.2,
|
| 202 |
-
"precision_at_20": 0.13158,
|
| 203 |
-
"precision_at_50": 0.06877,
|
| 204 |
-
"precision_at_100": 0.0386,
|
| 205 |
-
"mrr_at_1": 0.5087719298245614,
|
| 206 |
-
"mrr_at_3": 0.5877192982456141,
|
| 207 |
-
"mrr_at_5": 0.6149122807017543,
|
| 208 |
-
"mrr_at_10": 0.6263575605680868,
|
| 209 |
-
"mrr_at_20": 0.6303891040733146,
|
| 210 |
-
"mrr_at_50": 0.6303891040733146,
|
| 211 |
-
"mrr_at_100": 0.6305757408780925,
|
| 212 |
-
"naucs_at_1_max": -0.08333796614169701,
|
| 213 |
-
"naucs_at_1_std": 0.02230843203992766,
|
| 214 |
-
"naucs_at_1_diff1": 0.05161927720353975,
|
| 215 |
-
"naucs_at_3_max": -0.03209945113922174,
|
| 216 |
-
"naucs_at_3_std": 0.04489217019394448,
|
| 217 |
-
"naucs_at_3_diff1": -0.03516139834577249,
|
| 218 |
-
"naucs_at_5_max": -0.08062920691129684,
|
| 219 |
-
"naucs_at_5_std": 0.05137467110356768,
|
| 220 |
-
"naucs_at_5_diff1": -0.11589678137851257,
|
| 221 |
-
"naucs_at_10_max": -0.19710514484783043,
|
| 222 |
-
"naucs_at_10_std": -0.019483171394852755,
|
| 223 |
-
"naucs_at_10_diff1": -0.19216047549364354,
|
| 224 |
-
"naucs_at_20_max": -0.2492809947138442,
|
| 225 |
-
"naucs_at_20_std": -0.019880591668848344,
|
| 226 |
-
"naucs_at_20_diff1": -0.13918128050450226,
|
| 227 |
-
"naucs_at_50_max": -0.297692866142236,
|
| 228 |
-
"naucs_at_50_std": 0.015944137484135215,
|
| 229 |
-
"naucs_at_50_diff1": -0.10169694250184191,
|
| 230 |
-
"naucs_at_100_max": -0.3263966784104191,
|
| 231 |
-
"naucs_at_100_std": -0.004102727593586926,
|
| 232 |
-
"naucs_at_100_diff1": -0.06847320679987662
|
| 233 |
-
},
|
| 234 |
-
"vidore/esg_reports_v2": {
|
| 235 |
-
"ndcg_at_1": 0.51754,
|
| 236 |
-
"ndcg_at_3": 0.50334,
|
| 237 |
-
"ndcg_at_5": 0.54222,
|
| 238 |
-
"ndcg_at_10": 0.58819,
|
| 239 |
-
"ndcg_at_20": 0.6317,
|
| 240 |
-
"ndcg_at_50": 0.65775,
|
| 241 |
-
"ndcg_at_100": 0.67204,
|
| 242 |
-
"map_at_1": 0.24814,
|
| 243 |
-
"map_at_3": 0.36856,
|
| 244 |
-
"map_at_5": 0.42073,
|
| 245 |
-
"map_at_10": 0.4663,
|
| 246 |
-
"map_at_20": 0.49471,
|
| 247 |
-
"map_at_50": 0.50962,
|
| 248 |
-
"map_at_100": 0.51599,
|
| 249 |
-
"recall_at_1": 0.24814,
|
| 250 |
-
"recall_at_3": 0.43973,
|
| 251 |
-
"recall_at_5": 0.56658,
|
| 252 |
-
"recall_at_10": 0.71523,
|
| 253 |
-
"recall_at_20": 0.85844,
|
| 254 |
-
"recall_at_50": 0.93536,
|
| 255 |
-
"recall_at_100": 0.97971,
|
| 256 |
-
"precision_at_1": 0.51754,
|
| 257 |
-
"precision_at_3": 0.3538,
|
| 258 |
-
"precision_at_5": 0.29123,
|
| 259 |
-
"precision_at_10": 0.20219,
|
| 260 |
-
"precision_at_20": 0.13246,
|
| 261 |
-
"precision_at_50": 0.06825,
|
| 262 |
-
"precision_at_100": 0.03855,
|
| 263 |
-
"mrr_at_1": 0.5263157894736842,
|
| 264 |
-
"mrr_at_3": 0.6016081871345029,
|
| 265 |
-
"mrr_at_5": 0.6288011695906434,
|
| 266 |
-
"mrr_at_10": 0.6403230297967141,
|
| 267 |
-
"mrr_at_20": 0.6438437895094242,
|
| 268 |
-
"mrr_at_50": 0.6443535683849544,
|
| 269 |
-
"mrr_at_100": 0.644453714963128,
|
| 270 |
-
"naucs_at_1_max": 0.01943705593605114,
|
| 271 |
-
"naucs_at_1_std": 0.10857657836709796,
|
| 272 |
-
"naucs_at_1_diff1": 0.31024815892610824,
|
| 273 |
-
"naucs_at_3_max": -0.026602088034168622,
|
| 274 |
-
"naucs_at_3_std": 0.06693038369249117,
|
| 275 |
-
"naucs_at_3_diff1": 0.06536575914252513,
|
| 276 |
-
"naucs_at_5_max": -0.10400806660437836,
|
| 277 |
-
"naucs_at_5_std": 0.011805949215176312,
|
| 278 |
-
"naucs_at_5_diff1": -0.040514684440300354,
|
| 279 |
-
"naucs_at_10_max": -0.16246054552831016,
|
| 280 |
-
"naucs_at_10_std": -0.004963201865618914,
|
| 281 |
-
"naucs_at_10_diff1": -0.14424024163286125,
|
| 282 |
-
"naucs_at_20_max": -0.2068822330886405,
|
| 283 |
-
"naucs_at_20_std": 0.01182183229908038,
|
| 284 |
-
"naucs_at_20_diff1": -0.14776288061245282,
|
| 285 |
-
"naucs_at_50_max": -0.2382304805368312,
|
| 286 |
-
"naucs_at_50_std": 0.06100699728024982,
|
| 287 |
-
"naucs_at_50_diff1": -0.16038145767725714,
|
| 288 |
-
"naucs_at_100_max": -0.2526736911992193,
|
| 289 |
-
"naucs_at_100_std": 0.07538174516910437,
|
| 290 |
-
"naucs_at_100_diff1": -0.1425829565807366
|
| 291 |
-
},
|
| 292 |
-
"vidore/biomedical_lectures_v2": {
|
| 293 |
-
"ndcg_at_1": 0.55,
|
| 294 |
-
"ndcg_at_3": 0.54747,
|
| 295 |
-
"ndcg_at_5": 0.56523,
|
| 296 |
-
"ndcg_at_10": 0.60236,
|
| 297 |
-
"ndcg_at_20": 0.63192,
|
| 298 |
-
"ndcg_at_50": 0.65894,
|
| 299 |
-
"ndcg_at_100": 0.66916,
|
| 300 |
-
"map_at_1": 0.32887,
|
| 301 |
-
"map_at_3": 0.43891,
|
| 302 |
-
"map_at_5": 0.47556,
|
| 303 |
-
"map_at_10": 0.51112,
|
| 304 |
-
"map_at_20": 0.52597,
|
| 305 |
-
"map_at_50": 0.53502,
|
| 306 |
-
"map_at_100": 0.53747,
|
| 307 |
-
"recall_at_1": 0.32887,
|
| 308 |
-
"recall_at_3": 0.50621,
|
| 309 |
-
"recall_at_5": 0.59078,
|
| 310 |
-
"recall_at_10": 0.7021,
|
| 311 |
-
"recall_at_20": 0.78896,
|
| 312 |
-
"recall_at_50": 0.87545,
|
| 313 |
-
"recall_at_100": 0.91215,
|
| 314 |
-
"precision_at_1": 0.55,
|
| 315 |
-
"precision_at_3": 0.33698,
|
| 316 |
-
"precision_at_5": 0.25625,
|
| 317 |
-
"precision_at_10": 0.16797,
|
| 318 |
-
"precision_at_20": 0.10016,
|
| 319 |
-
"precision_at_50": 0.04875,
|
| 320 |
-
"precision_at_100": 0.02653,
|
| 321 |
-
"mrr_at_1": 0.5421875,
|
| 322 |
-
"mrr_at_3": 0.6315104166666667,
|
| 323 |
-
"mrr_at_5": 0.6464322916666666,
|
| 324 |
-
"mrr_at_10": 0.6572829861111111,
|
| 325 |
-
"mrr_at_20": 0.6611296462086782,
|
| 326 |
-
"mrr_at_50": 0.6623597304996574,
|
| 327 |
-
"mrr_at_100": 0.6624612115027679,
|
| 328 |
-
"naucs_at_1_max": 0.21639796742259326,
|
| 329 |
-
"naucs_at_1_std": -0.03628975637155085,
|
| 330 |
-
"naucs_at_1_diff1": 0.4459120269606122,
|
| 331 |
-
"naucs_at_3_max": 0.03669633870346066,
|
| 332 |
-
"naucs_at_3_std": -0.08520389607094239,
|
| 333 |
-
"naucs_at_3_diff1": 0.040408263382322174,
|
| 334 |
-
"naucs_at_5_max": -0.04548934564318856,
|
| 335 |
-
"naucs_at_5_std": -0.07038321737921435,
|
| 336 |
-
"naucs_at_5_diff1": -0.10616437737784175,
|
| 337 |
-
"naucs_at_10_max": -0.1278578682315184,
|
| 338 |
-
"naucs_at_10_std": -0.10363742277920715,
|
| 339 |
-
"naucs_at_10_diff1": -0.1945365842241381,
|
| 340 |
-
"naucs_at_20_max": -0.1602047364202233,
|
| 341 |
-
"naucs_at_20_std": -0.09160204736420194,
|
| 342 |
-
"naucs_at_20_diff1": -0.2459548568724758,
|
| 343 |
-
"naucs_at_50_max": -0.16751679776268727,
|
| 344 |
-
"naucs_at_50_std": -0.029600561994848625,
|
| 345 |
-
"naucs_at_50_diff1": -0.28501697067776877,
|
| 346 |
-
"naucs_at_100_max": -0.1840412781009732,
|
| 347 |
-
"naucs_at_100_std": -0.029290750955906976,
|
| 348 |
-
"naucs_at_100_diff1": -0.27754478203216754
|
| 349 |
-
},
|
| 350 |
-
"vidore/synthetic_axa_filtered_v1.0": {
|
| 351 |
-
"ndcg_at_1": 0.61111,
|
| 352 |
-
"ndcg_at_3": 0.63835,
|
| 353 |
-
"ndcg_at_5": 0.65099,
|
| 354 |
-
"ndcg_at_10": 0.66413,
|
| 355 |
-
"ndcg_at_20": 0.67711,
|
| 356 |
-
"ndcg_at_50": 0.72121,
|
| 357 |
-
"ndcg_at_100": 0.73402,
|
| 358 |
-
"map_at_1": 0.29544,
|
| 359 |
-
"map_at_3": 0.39626,
|
| 360 |
-
"map_at_5": 0.4688,
|
| 361 |
-
"map_at_10": 0.53459,
|
| 362 |
-
"map_at_20": 0.55814,
|
| 363 |
-
"map_at_50": 0.5817,
|
| 364 |
-
"map_at_100": 0.58632,
|
| 365 |
-
"recall_at_1": 0.29544,
|
| 366 |
-
"recall_at_3": 0.49889,
|
| 367 |
-
"recall_at_5": 0.59938,
|
| 368 |
-
"recall_at_10": 0.74741,
|
| 369 |
-
"recall_at_20": 0.80396,
|
| 370 |
-
"recall_at_50": 0.93358,
|
| 371 |
-
"recall_at_100": 0.97068,
|
| 372 |
-
"precision_at_1": 0.61111,
|
| 373 |
-
"precision_at_3": 0.46296,
|
| 374 |
-
"precision_at_5": 0.41111,
|
| 375 |
-
"precision_at_10": 0.28889,
|
| 376 |
-
"precision_at_20": 0.17222,
|
| 377 |
-
"precision_at_50": 0.08556,
|
| 378 |
-
"precision_at_100": 0.04611,
|
| 379 |
-
"mrr_at_1": 0.6111111111111112,
|
| 380 |
-
"mrr_at_3": 0.712962962962963,
|
| 381 |
-
"mrr_at_5": 0.712962962962963,
|
| 382 |
-
"mrr_at_10": 0.7222222222222222,
|
| 383 |
-
"mrr_at_20": 0.7222222222222222,
|
| 384 |
-
"mrr_at_50": 0.7239057239057238,
|
| 385 |
-
"mrr_at_100": 0.7239057239057238,
|
| 386 |
-
"naucs_at_1_max": 0.021377128555080525,
|
| 387 |
-
"naucs_at_1_std": -0.0024330874521297486,
|
| 388 |
-
"naucs_at_1_diff1": 0.6766922062442021,
|
| 389 |
-
"naucs_at_3_max": -0.5386403640030516,
|
| 390 |
-
"naucs_at_3_std": -0.339024827473691,
|
| 391 |
-
"naucs_at_3_diff1": -0.13999146573412896,
|
| 392 |
-
"naucs_at_5_max": -0.5536345449068457,
|
| 393 |
-
"naucs_at_5_std": -0.32978315319997686,
|
| 394 |
-
"naucs_at_5_diff1": -0.1515416702953352,
|
| 395 |
-
"naucs_at_10_max": -0.6913115857640982,
|
| 396 |
-
"naucs_at_10_std": -0.3590368655225717,
|
| 397 |
-
"naucs_at_10_diff1": -0.4262436564575138,
|
| 398 |
-
"naucs_at_20_max": -0.6790472085176197,
|
| 399 |
-
"naucs_at_20_std": -0.2636829434018275,
|
| 400 |
-
"naucs_at_20_diff1": -0.46059572736900606,
|
| 401 |
-
"naucs_at_50_max": -0.6436105950460144,
|
| 402 |
-
"naucs_at_50_std": -0.17446418069026137,
|
| 403 |
-
"naucs_at_50_diff1": -0.5059059487831842,
|
| 404 |
-
"naucs_at_100_max": -0.6463006925980164,
|
| 405 |
-
"naucs_at_100_std": -0.1497578630779427,
|
| 406 |
-
"naucs_at_100_diff1": -0.5112033641662738
|
| 407 |
-
},
|
| 408 |
-
"vidore/economics_reports_eng_v2": {
|
| 409 |
-
"ndcg_at_1": 0.65517,
|
| 410 |
-
"ndcg_at_3": 0.63819,
|
| 411 |
-
"ndcg_at_5": 0.61521,
|
| 412 |
-
"ndcg_at_10": 0.5906,
|
| 413 |
-
"ndcg_at_20": 0.60536,
|
| 414 |
-
"ndcg_at_50": 0.66285,
|
| 415 |
-
"ndcg_at_100": 0.70251,
|
| 416 |
-
"map_at_1": 0.06921,
|
| 417 |
-
"map_at_3": 0.18532,
|
| 418 |
-
"map_at_5": 0.25479,
|
| 419 |
-
"map_at_10": 0.33604,
|
| 420 |
-
"map_at_20": 0.39502,
|
| 421 |
-
"map_at_50": 0.44809,
|
| 422 |
-
"map_at_100": 0.47767,
|
| 423 |
-
"recall_at_1": 0.06921,
|
| 424 |
-
"recall_at_3": 0.23206,
|
| 425 |
-
"recall_at_5": 0.33701,
|
| 426 |
-
"recall_at_10": 0.4769,
|
| 427 |
-
"recall_at_20": 0.60612,
|
| 428 |
-
"recall_at_50": 0.78689,
|
| 429 |
-
"recall_at_100": 0.90662,
|
| 430 |
-
"precision_at_1": 0.65517,
|
| 431 |
-
"precision_at_3": 0.6092,
|
| 432 |
-
"precision_at_5": 0.55862,
|
| 433 |
-
"precision_at_10": 0.4431,
|
| 434 |
-
"precision_at_20": 0.32241,
|
| 435 |
-
"precision_at_50": 0.19414,
|
| 436 |
-
"precision_at_100": 0.12759,
|
| 437 |
-
"mrr_at_1": 0.6206896551724138,
|
| 438 |
-
"mrr_at_3": 0.735632183908046,
|
| 439 |
-
"mrr_at_5": 0.7468390804597702,
|
| 440 |
-
"mrr_at_10": 0.7525862068965516,
|
| 441 |
-
"mrr_at_20": 0.753448275862069,
|
| 442 |
-
"mrr_at_50": 0.7547113805734496,
|
| 443 |
-
"mrr_at_100": 0.7547113805734496,
|
| 444 |
-
"naucs_at_1_max": 0.3467227583809364,
|
| 445 |
-
"naucs_at_1_std": 0.46598561053805343,
|
| 446 |
-
"naucs_at_1_diff1": 0.2918337389920708,
|
| 447 |
-
"naucs_at_3_max": 0.2797595385222247,
|
| 448 |
-
"naucs_at_3_std": 0.2864952959792759,
|
| 449 |
-
"naucs_at_3_diff1": 0.3913734193294228,
|
| 450 |
-
"naucs_at_5_max": 0.25393027831323856,
|
| 451 |
-
"naucs_at_5_std": 0.3095747235773235,
|
| 452 |
-
"naucs_at_5_diff1": 0.3645542505594328,
|
| 453 |
-
"naucs_at_10_max": 0.2700390408547681,
|
| 454 |
-
"naucs_at_10_std": 0.32232824677308325,
|
| 455 |
-
"naucs_at_10_diff1": 0.2680868235374596,
|
| 456 |
-
"naucs_at_20_max": 0.17701498139167485,
|
| 457 |
-
"naucs_at_20_std": 0.2949738297548142,
|
| 458 |
-
"naucs_at_20_diff1": 0.22778015683462374,
|
| 459 |
-
"naucs_at_50_max": 0.005866671306298476,
|
| 460 |
-
"naucs_at_50_std": 0.18617183360877715,
|
| 461 |
-
"naucs_at_50_diff1": 0.2543543566117715,
|
| 462 |
-
"naucs_at_100_max": -0.051660558691400224,
|
| 463 |
-
"naucs_at_100_std": 0.12365631128720926,
|
| 464 |
-
"naucs_at_100_diff1": 0.27211571635112025
|
| 465 |
-
},
|
| 466 |
-
"validation_set": {"ndcg_at_1": 0.774, "ndcg_at_3": 0.83243, "ndcg_at_5": 0.84895, "ndcg_at_10": 0.85814, "ndcg_at_20": 0.8643, "ndcg_at_100": 0.86854, "ndcg_at_1000": 0.87018, "map_at_1": 0.774, "map_at_3": 0.81867, "map_at_5": 0.82787, "map_at_10": 0.83174, "map_at_20": 0.83348, "map_at_100": 0.83399, "map_at_1000": 0.83407, "recall_at_1": 0.774, "recall_at_3": 0.872, "recall_at_5": 0.912, "recall_at_10": 0.94, "recall_at_20": 0.964, "recall_at_100": 0.988, "recall_at_1000": 1.0, "precision_at_1": 0.774, "precision_at_3": 0.29067, "precision_at_5": 0.1824, "precision_at_10": 0.094, "precision_at_20": 0.0482, "precision_at_100": 0.00988, "precision_at_1000": 0.001, "mrr_at_1": 0.778, "mrr_at_3": 0.821, "mrr_at_5": 0.8286999999999999, "mrr_at_10": 0.8335484126984126, "mrr_at_20": 0.8347260450333979, "mrr_at_100": 0.8354386595905559, "mrr_at_1000": 0.8355249939420808, "naucs_at_1_max": -0.0145170587484219, "naucs_at_1_std": 0.006309262814839989, "naucs_at_1_diff1": 0.8950447836378629, "naucs_at_3_max": 0.021200161668434796, "naucs_at_3_std": 0.20331461011654423, "naucs_at_3_diff1": 0.8777295662755695, "naucs_at_5_max": 0.08481716987168389, "naucs_at_5_std": 0.35063874034462167, "naucs_at_5_diff1": 0.8777528653012975, "naucs_at_10_max": 0.09851459770146549, "naucs_at_10_std": 0.5862433862433853, "naucs_at_10_diff1": 0.9003930543110488, "naucs_at_20_max": -0.04060065920783268, "naucs_at_20_std": 0.6889718850503177, "naucs_at_20_diff1": 0.9353989134331586, "naucs_at_100_max": 0.4440696998264123, "naucs_at_100_std": 0.8537970743853125, "naucs_at_100_diff1": 0.9341234384048992, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": -0.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.89786, "ndcg_at_5": 0.9099, "ndcg_at_10": 0.91346, "ndcg_at_20": 0.91346, "ndcg_at_100": 0.91879, "ndcg_at_1000": 0.91879, "map_at_1": 0.85, "map_at_3": 0.88667, "map_at_5": 0.89317, "map_at_10": 0.89483, "map_at_20": 0.89483, "map_at_100": 0.89545, "map_at_1000": 0.89545, "recall_at_1": 0.85, "recall_at_3": 0.93, "recall_at_5": 0.96, "recall_at_10": 0.97, "recall_at_20": 0.97, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.31, "precision_at_5": 0.192, "precision_at_10": 0.097, "precision_at_20": 0.0485, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.895, "mrr_at_5": 0.9009999999999999, "mrr_at_10": 0.9009999999999999, "mrr_at_20": 0.9009999999999999, "mrr_at_100": 0.9016280663780663, "mrr_at_1000": 0.9016280663780663, "naucs_at_1_max": 0.2105750182116147, "naucs_at_1_std": -0.1620891636836963, "naucs_at_1_diff1": 0.9412806884333085, "naucs_at_3_max": -0.038548439319115155, "naucs_at_3_std": -0.30092036814725776, "naucs_at_3_diff1": 0.9024795103226442, "naucs_at_5_max": 0.46231071243125327, "naucs_at_5_std": -0.20074696545284348, "naucs_at_5_diff1": 0.93100944081336, "naucs_at_10_max": 0.5739365102913813, "naucs_at_10_std": -0.45238095238095277, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.5739365102913813, "naucs_at_20_std": -0.45238095238095277, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.93547, "ndcg_at_5": 0.94365, "ndcg_at_10": 0.94365, "ndcg_at_20": 0.94365, "ndcg_at_100": 0.94515, "ndcg_at_1000": 0.94515, "map_at_1": 0.88, "map_at_3": 0.92333, "map_at_5": 0.92783, "map_at_10": 0.92783, "map_at_20": 0.92783, "map_at_100": 0.92793, "map_at_1000": 0.92793, "recall_at_1": 0.88, "recall_at_3": 0.97, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.32333, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.89, "mrr_at_3": 0.9283333333333332, "mrr_at_5": 0.9328333333333333, "mrr_at_10": 0.9328333333333333, "mrr_at_20": 0.9328333333333333, "mrr_at_100": 0.9329364261168385, "mrr_at_1000": 0.9329364261168385, "naucs_at_1_max": 0.3449858099592377, "naucs_at_1_std": -0.2542554883868911, "naucs_at_1_diff1": 0.8584721869131066, "naucs_at_3_max": 0.19373303220940802, "naucs_at_3_std": -1.0210084033613431, "naucs_at_3_diff1": 0.8314665575583057, "naucs_at_5_max": 0.3612909644732028, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.8787143723468824, "naucs_at_10_max": 0.3612909644732028, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.8787143723468824, "naucs_at_20_max": 0.3612909644732028, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 0.8787143723468824, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96155, "ndcg_at_5": 0.96155, "ndcg_at_10": 0.96488, "ndcg_at_20": 0.96488, "ndcg_at_100": 0.96663, "ndcg_at_1000": 0.96663, "map_at_1": 0.93, "map_at_3": 0.955, "map_at_5": 0.955, "map_at_10": 0.95643, "map_at_20": 0.95643, "map_at_100": 0.95662, "map_at_1000": 0.95662, "recall_at_1": 0.93, "recall_at_3": 0.98, "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": 0.93, "precision_at_3": 0.32667, "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": 0.93, "mrr_at_3": 0.955, "mrr_at_5": 0.955, "mrr_at_10": 0.9564285714285714, "mrr_at_20": 0.9564285714285714, "mrr_at_100": 0.9566285714285715, "mrr_at_1000": 0.9566285714285715, "naucs_at_1_max": -0.0004962491760935482, "naucs_at_1_std": -0.31752701080432255, "naucs_at_1_diff1": 0.8859352860974721, "naucs_at_3_max": -1.393329269612857, "naucs_at_3_std": -1.7399626517273692, "naucs_at_3_diff1": 0.9999999999999902, "naucs_at_5_max": -1.3933292696128265, "naucs_at_5_std": -1.7399626517273497, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": -1.1259495904684838, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": -1.1259495904684838, "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}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.91417, "ndcg_at_5": 0.92709, "ndcg_at_10": 0.92998, "ndcg_at_20": 0.92998, "ndcg_at_100": 0.92998, "ndcg_at_1000": 0.92998, "map_at_1": 0.85, "map_at_3": 0.89833, "map_at_5": 0.90583, "map_at_10": 0.90683, "map_at_20": 0.90683, "map_at_100": 0.90683, "map_at_1000": 0.90683, "recall_at_1": 0.85, "recall_at_3": 0.96, "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": 0.85, "precision_at_3": 0.32, "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": 0.86, "mrr_at_3": 0.9083333333333331, "mrr_at_5": 0.9133333333333331, "mrr_at_10": 0.9144444444444443, "mrr_at_20": 0.9144444444444443, "mrr_at_100": 0.9144444444444443, "mrr_at_1000": 0.9144444444444443, "naucs_at_1_max": 0.0728385886905621, "naucs_at_1_std": -0.27940123657663585, "naucs_at_1_diff1": 0.838404544865166, "naucs_at_3_max": 0.43264898785631317, "naucs_at_3_std": 0.3535247432306253, "naucs_at_3_diff1": 0.7950946429181002, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.8692810457516413, "naucs_at_5_diff1": 0.5715286132037668, "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}, "infovqa_subsampled": {"ndcg_at_1": 0.746, "ndcg_at_3": 0.80343, "ndcg_at_5": 0.81832, "ndcg_at_10": 0.82857, "ndcg_at_20": 0.83312, "ndcg_at_100": 0.84258, "ndcg_at_1000": 0.84537, "map_at_1": 0.746, "map_at_3": 0.79, "map_at_5": 0.7983, "map_at_10": 0.80247, "map_at_20": 0.80372, "map_at_100": 0.8051, "map_at_1000": 0.8052, "recall_at_1": 0.746, "recall_at_3": 0.842, "recall_at_5": 0.878, "recall_at_10": 0.91, "recall_at_20": 0.928, "recall_at_100": 0.978, "recall_at_1000": 1.0, "precision_at_1": 0.746, "precision_at_3": 0.28067, "precision_at_5": 0.1756, "precision_at_10": 0.091, "precision_at_20": 0.0464, "precision_at_100": 0.00978, "precision_at_1000": 0.001, "mrr_at_1": 0.752, "mrr_at_3": 0.7953333333333332, "mrr_at_5": 0.8023333333333331, "mrr_at_10": 0.8065706349206349, "mrr_at_20": 0.8078986539174619, "mrr_at_100": 0.8091823645081221, "mrr_at_1000": 0.809263223979117, "naucs_at_1_max": 0.24674907189259504, "naucs_at_1_std": 0.11457666064661158, "naucs_at_1_diff1": 0.8740250282732915, "naucs_at_3_max": 0.23413123236282346, "naucs_at_3_std": 0.20991570348483488, "naucs_at_3_diff1": 0.8357975149102336, "naucs_at_5_max": 0.35286707023572256, "naucs_at_5_std": 0.37199604959947313, "naucs_at_5_diff1": 0.8207018895992207, "naucs_at_10_max": 0.3522596496009211, "naucs_at_10_std": 0.3307189542483652, "naucs_at_10_diff1": 0.8090976640617076, "naucs_at_20_max": 0.4744509713295461, "naucs_at_20_std": 0.47494553376906107, "naucs_at_20_diff1": 0.7939471631070897, "naucs_at_100_max": 0.44440793303781984, "naucs_at_100_std": 0.8327815974874812, "naucs_at_100_diff1": 0.8297168584345167, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.456, "ndcg_at_3": 0.52447, "ndcg_at_5": 0.54427, "ndcg_at_10": 0.56508, "ndcg_at_20": 0.58069, "ndcg_at_100": 0.60433, "ndcg_at_1000": 0.62051, "map_at_1": 0.456, "map_at_3": 0.508, "map_at_5": 0.519, "map_at_10": 0.52765, "map_at_20": 0.5319, "map_at_100": 0.53515, "map_at_1000": 0.53576, "recall_at_1": 0.456, "recall_at_3": 0.572, "recall_at_5": 0.62, "recall_at_10": 0.684, "recall_at_20": 0.746, "recall_at_100": 0.874, "recall_at_1000": 1.0, "precision_at_1": 0.456, "precision_at_3": 0.19067, "precision_at_5": 0.124, "precision_at_10": 0.0684, "precision_at_20": 0.0373, "precision_at_100": 0.00874, "precision_at_1000": 0.001, "mrr_at_1": 0.452, "mrr_at_3": 0.505, "mrr_at_5": 0.5164000000000001, "mrr_at_10": 0.5254579365079365, "mrr_at_20": 0.5290178752190362, "mrr_at_100": 0.5325203981148059, "mrr_at_1000": 0.5330986506794522, "naucs_at_1_max": 0.010704720337137848, "naucs_at_1_std": 0.4181494661921707, "naucs_at_1_diff1": 0.7688057111458236, "naucs_at_3_max": -0.0067852838115276684, "naucs_at_3_std": 0.408076792525558, "naucs_at_3_diff1": 0.7055654080347042, "naucs_at_5_max": -0.011161683506439484, "naucs_at_5_std": 0.452272097960188, "naucs_at_5_diff1": 0.6829497998035559, "naucs_at_10_max": -0.06663979903420814, "naucs_at_10_std": 0.4644934958160017, "naucs_at_10_diff1": 0.6670322281267268, "naucs_at_20_max": -0.08314881099503675, "naucs_at_20_std": 0.5636259190226841, "naucs_at_20_diff1": 0.6475212710859795, "naucs_at_100_max": -0.15012530637692442, "naucs_at_100_std": 0.8336557354576346, "naucs_at_100_diff1": 0.6215172139879154, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 2.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.724, "ndcg_at_3": 0.77659, "ndcg_at_5": 0.7914, "ndcg_at_10": 0.80967, "ndcg_at_20": 0.81716, "ndcg_at_100": 0.82667, "ndcg_at_1000": 0.82854, "map_at_1": 0.724, "map_at_3": 0.76367, "map_at_5": 0.77187, "map_at_10": 0.77989, "map_at_20": 0.78189, "map_at_100": 0.78316, "map_at_1000": 0.78324, "recall_at_1": 0.724, "recall_at_3": 0.814, "recall_at_5": 0.85, "recall_at_10": 0.904, "recall_at_20": 0.934, "recall_at_100": 0.986, "recall_at_1000": 1.0, "precision_at_1": 0.724, "precision_at_3": 0.27133, "precision_at_5": 0.17, "precision_at_10": 0.0904, "precision_at_20": 0.0467, "precision_at_100": 0.00986, "precision_at_1000": 0.001, "mrr_at_1": 0.72, "mrr_at_3": 0.7606666666666666, "mrr_at_5": 0.7704666666666665, "mrr_at_10": 0.7783031746031746, "mrr_at_20": 0.7798739388062916, "mrr_at_100": 0.7811347665019601, "mrr_at_1000": 0.781219393810504, "naucs_at_1_max": 0.016575744452395444, "naucs_at_1_std": 0.14620481415983924, "naucs_at_1_diff1": 0.8319131181262124, "naucs_at_3_max": -0.025943897313719388, "naucs_at_3_std": 0.19927764658111108, "naucs_at_3_diff1": 0.7774553764676329, "naucs_at_5_max": -0.0448735069102902, "naucs_at_5_std": 0.26161405792385234, "naucs_at_5_diff1": 0.7677282039192751, "naucs_at_10_max": -0.10797954318975009, "naucs_at_10_std": 0.20837223778400116, "naucs_at_10_diff1": 0.7147052306317629, "naucs_at_20_max": -0.00911433048928522, "naucs_at_20_std": 0.4119910590498834, "naucs_at_20_diff1": 0.7000503290790163, "naucs_at_100_max": 0.5246753983500644, "naucs_at_100_std": 0.8289315726290336, "naucs_at_100_diff1": 0.6839271409113703, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.75357, "ndcg_at_3": 0.82768, "ndcg_at_5": 0.83936, "ndcg_at_10": 0.85309, "ndcg_at_20": 0.85858, "ndcg_at_100": 0.86371, "ndcg_at_1000": 0.86371, "map_at_1": 0.75357, "map_at_3": 0.80893, "map_at_5": 0.81536, "map_at_10": 0.82095, "map_at_20": 0.8225, "map_at_100": 0.82339, "map_at_1000": 0.82339, "recall_at_1": 0.75357, "recall_at_3": 0.88214, "recall_at_5": 0.91071, "recall_at_10": 0.95357, "recall_at_20": 0.975, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.75357, "precision_at_3": 0.29405, "precision_at_5": 0.18214, "precision_at_10": 0.09536, "precision_at_20": 0.04875, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.7535714285714286, "mrr_at_3": 0.8101190476190477, "mrr_at_5": 0.8167261904761904, "mrr_at_10": 0.8221357709750566, "mrr_at_20": 0.8239959162569457, "mrr_at_100": 0.8248561140910201, "mrr_at_1000": 0.8248561140910201, "naucs_at_1_max": 0.5304566374894598, "naucs_at_1_std": 0.1615906461054432, "naucs_at_1_diff1": 0.8208688581619074, "naucs_at_3_max": 0.4836484318803355, "naucs_at_3_std": 0.21076407932338395, "naucs_at_3_diff1": 0.7733693395413521, "naucs_at_5_max": 0.4612358016225636, "naucs_at_5_std": 0.27449112978524876, "naucs_at_5_diff1": 0.7189851642886126, "naucs_at_10_max": 0.5759036686726754, "naucs_at_10_std": 0.32575594340300035, "naucs_at_10_diff1": 0.7358166602027056, "naucs_at_20_max": 0.47733910929211887, "naucs_at_20_std": 0.25596905428838695, "naucs_at_20_diff1": 0.7967511397858333, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": -0.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.53097, "ndcg_at_3": 0.62877, "ndcg_at_5": 0.65801, "ndcg_at_10": 0.68473, "ndcg_at_20": 0.69746, "ndcg_at_100": 0.71145, "ndcg_at_1000": 0.7146, "map_at_1": 0.53097, "map_at_3": 0.60443, "map_at_5": 0.62052, "map_at_10": 0.63158, "map_at_20": 0.63505, "map_at_100": 0.63713, "map_at_1000": 0.63728, "recall_at_1": 0.53097, "recall_at_3": 0.69934, "recall_at_5": 0.7709, "recall_at_10": 0.85328, "recall_at_20": 0.90379, "recall_at_100": 0.97715, "recall_at_1000": 1.0, "precision_at_1": 0.53097, "precision_at_3": 0.23311, "precision_at_5": 0.15418, "precision_at_10": 0.08533, "precision_at_20": 0.04519, "precision_at_100": 0.00977, "precision_at_1000": 0.001, "mrr_at_1": 0.5267588695129285, "mrr_at_3": 0.6032270996191631, "mrr_at_5": 0.61913209059932, "mrr_at_10": 0.6304894577594526, "mrr_at_20": 0.6337674299282028, "mrr_at_100": 0.6358829720309133, "mrr_at_1000": 0.6360412330135795, "naucs_at_1_max": 0.12207506980114474, "naucs_at_1_std": -0.06857703877057526, "naucs_at_1_diff1": 0.6350798605456752, "naucs_at_3_max": 0.13028071020881998, "naucs_at_3_std": -0.03204133285184471, "naucs_at_3_diff1": 0.536055692458893, "naucs_at_5_max": 0.14913490780176689, "naucs_at_5_std": 0.0019238783137197706, "naucs_at_5_diff1": 0.5114302291162272, "naucs_at_10_max": 0.152124608400107, "naucs_at_10_std": 0.10791232460205795, "naucs_at_10_diff1": 0.48383898061381275, "naucs_at_20_max": 0.1449130314981855, "naucs_at_20_std": 0.22594318462810645, "naucs_at_20_diff1": 0.43552881290118256, "naucs_at_100_max": -0.12684151303788002, "naucs_at_100_std": 0.5145680511335288, "naucs_at_100_diff1": 0.5095488271113825, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.55, "ndcg_at_3": 0.71488, "ndcg_at_5": 0.73167, "ndcg_at_10": 0.74796, "ndcg_at_20": 0.75568, "ndcg_at_100": 0.76079, "ndcg_at_1000": 0.76366, "map_at_1": 0.55, "map_at_3": 0.675, "map_at_5": 0.6845, "map_at_10": 0.69131, "map_at_20": 0.6935, "map_at_100": 0.69406, "map_at_1000": 0.69422, "recall_at_1": 0.55, "recall_at_3": 0.83, "recall_at_5": 0.87, "recall_at_10": 0.92, "recall_at_20": 0.95, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.55, "precision_at_3": 0.27667, "precision_at_5": 0.174, "precision_at_10": 0.092, "precision_at_20": 0.0475, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.57, "mrr_at_3": 0.69, "mrr_at_5": 0.6970000000000001, "mrr_at_10": 0.7041230158730158, "mrr_at_20": 0.7063159983291563, "mrr_at_100": 0.7069244639376219, "mrr_at_1000": 0.7070891464773044, "naucs_at_1_max": -0.13381190246642352, "naucs_at_1_std": -0.30200098293898753, "naucs_at_1_diff1": 0.5594199548867977, "naucs_at_3_max": -0.2639588734077385, "naucs_at_3_std": -0.5422302200034823, "naucs_at_3_diff1": 0.6073825476848427, "naucs_at_5_max": -0.2204135305072195, "naucs_at_5_std": -0.4037250981263389, "naucs_at_5_diff1": 0.4991023586585799, "naucs_at_10_max": -0.16129215914007541, "naucs_at_10_std": -0.5218253968253913, "naucs_at_10_diff1": 0.4407238859736181, "naucs_at_20_max": -0.38175400241396046, "naucs_at_20_std": -0.7713352007469497, "naucs_at_20_diff1": 0.5734029421882291, "naucs_at_100_max": -1.1341349547949189, "naucs_at_100_std": -0.6909430438842147, "naucs_at_100_diff1": 0.48572411420708356, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|
|
|
|
| 1 |
+
{"validation_set": {"ndcg_at_1": 0.774, "ndcg_at_3": 0.83243, "ndcg_at_5": 0.84895, "ndcg_at_10": 0.85814, "ndcg_at_20": 0.8643, "ndcg_at_100": 0.86854, "ndcg_at_1000": 0.87018, "map_at_1": 0.774, "map_at_3": 0.81867, "map_at_5": 0.82787, "map_at_10": 0.83174, "map_at_20": 0.83348, "map_at_100": 0.83399, "map_at_1000": 0.83407, "recall_at_1": 0.774, "recall_at_3": 0.872, "recall_at_5": 0.912, "recall_at_10": 0.94, "recall_at_20": 0.964, "recall_at_100": 0.988, "recall_at_1000": 1.0, "precision_at_1": 0.774, "precision_at_3": 0.29067, "precision_at_5": 0.1824, "precision_at_10": 0.094, "precision_at_20": 0.0482, "precision_at_100": 0.00988, "precision_at_1000": 0.001, "mrr_at_1": 0.778, "mrr_at_3": 0.821, "mrr_at_5": 0.8286999999999999, "mrr_at_10": 0.8335484126984126, "mrr_at_20": 0.8347260450333979, "mrr_at_100": 0.8354386595905559, "mrr_at_1000": 0.8355249939420808, "naucs_at_1_max": -0.0145170587484219, "naucs_at_1_std": 0.006309262814839989, "naucs_at_1_diff1": 0.8950447836378629, "naucs_at_3_max": 0.021200161668434796, "naucs_at_3_std": 0.20331461011654423, "naucs_at_3_diff1": 0.8777295662755695, "naucs_at_5_max": 0.08481716987168389, "naucs_at_5_std": 0.35063874034462167, "naucs_at_5_diff1": 0.8777528653012975, "naucs_at_10_max": 0.09851459770146549, "naucs_at_10_std": 0.5862433862433853, "naucs_at_10_diff1": 0.9003930543110488, "naucs_at_20_max": -0.04060065920783268, "naucs_at_20_std": 0.6889718850503177, "naucs_at_20_diff1": 0.9353989134331586, "naucs_at_100_max": 0.4440696998264123, "naucs_at_100_std": 0.8537970743853125, "naucs_at_100_diff1": 0.9341234384048992, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": -0.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.89786, "ndcg_at_5": 0.9099, "ndcg_at_10": 0.91346, "ndcg_at_20": 0.91346, "ndcg_at_100": 0.91879, "ndcg_at_1000": 0.91879, "map_at_1": 0.85, "map_at_3": 0.88667, "map_at_5": 0.89317, "map_at_10": 0.89483, "map_at_20": 0.89483, "map_at_100": 0.89545, "map_at_1000": 0.89545, "recall_at_1": 0.85, "recall_at_3": 0.93, "recall_at_5": 0.96, "recall_at_10": 0.97, "recall_at_20": 0.97, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.85, "precision_at_3": 0.31, "precision_at_5": 0.192, "precision_at_10": 0.097, "precision_at_20": 0.0485, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.895, "mrr_at_5": 0.9009999999999999, "mrr_at_10": 0.9009999999999999, "mrr_at_20": 0.9009999999999999, "mrr_at_100": 0.9016280663780663, "mrr_at_1000": 0.9016280663780663, "naucs_at_1_max": 0.2105750182116147, "naucs_at_1_std": -0.1620891636836963, "naucs_at_1_diff1": 0.9412806884333085, "naucs_at_3_max": -0.038548439319115155, "naucs_at_3_std": -0.30092036814725776, "naucs_at_3_diff1": 0.9024795103226442, "naucs_at_5_max": 0.46231071243125327, "naucs_at_5_std": -0.20074696545284348, "naucs_at_5_diff1": 0.93100944081336, "naucs_at_10_max": 0.5739365102913813, "naucs_at_10_std": -0.45238095238095277, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 0.5739365102913813, "naucs_at_20_std": -0.45238095238095277, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.93547, "ndcg_at_5": 0.94365, "ndcg_at_10": 0.94365, "ndcg_at_20": 0.94365, "ndcg_at_100": 0.94515, "ndcg_at_1000": 0.94515, "map_at_1": 0.88, "map_at_3": 0.92333, "map_at_5": 0.92783, "map_at_10": 0.92783, "map_at_20": 0.92783, "map_at_100": 0.92793, "map_at_1000": 0.92793, "recall_at_1": 0.88, "recall_at_3": 0.97, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.32333, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.89, "mrr_at_3": 0.9283333333333332, "mrr_at_5": 0.9328333333333333, "mrr_at_10": 0.9328333333333333, "mrr_at_20": 0.9328333333333333, "mrr_at_100": 0.9329364261168385, "mrr_at_1000": 0.9329364261168385, "naucs_at_1_max": 0.3449858099592377, "naucs_at_1_std": -0.2542554883868911, "naucs_at_1_diff1": 0.8584721869131066, "naucs_at_3_max": 0.19373303220940802, "naucs_at_3_std": -1.0210084033613431, "naucs_at_3_diff1": 0.8314665575583057, "naucs_at_5_max": 0.3612909644732028, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.8787143723468824, "naucs_at_10_max": 0.3612909644732028, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.8787143723468824, "naucs_at_20_max": 0.3612909644732028, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 0.8787143723468824, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96155, "ndcg_at_5": 0.96155, "ndcg_at_10": 0.96488, "ndcg_at_20": 0.96488, "ndcg_at_100": 0.96663, "ndcg_at_1000": 0.96663, "map_at_1": 0.93, "map_at_3": 0.955, "map_at_5": 0.955, "map_at_10": 0.95643, "map_at_20": 0.95643, "map_at_100": 0.95662, "map_at_1000": 0.95662, "recall_at_1": 0.93, "recall_at_3": 0.98, "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": 0.93, "precision_at_3": 0.32667, "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": 0.93, "mrr_at_3": 0.955, "mrr_at_5": 0.955, "mrr_at_10": 0.9564285714285714, "mrr_at_20": 0.9564285714285714, "mrr_at_100": 0.9566285714285715, "mrr_at_1000": 0.9566285714285715, "naucs_at_1_max": -0.0004962491760935482, "naucs_at_1_std": -0.31752701080432255, "naucs_at_1_diff1": 0.8859352860974721, "naucs_at_3_max": -1.393329269612857, "naucs_at_3_std": -1.7399626517273692, "naucs_at_3_diff1": 0.9999999999999902, "naucs_at_5_max": -1.3933292696128265, "naucs_at_5_std": -1.7399626517273497, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": -1.1259495904684838, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": -1.1259495904684838, "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}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.85, "ndcg_at_3": 0.91417, "ndcg_at_5": 0.92709, "ndcg_at_10": 0.92998, "ndcg_at_20": 0.92998, "ndcg_at_100": 0.92998, "ndcg_at_1000": 0.92998, "map_at_1": 0.85, "map_at_3": 0.89833, "map_at_5": 0.90583, "map_at_10": 0.90683, "map_at_20": 0.90683, "map_at_100": 0.90683, "map_at_1000": 0.90683, "recall_at_1": 0.85, "recall_at_3": 0.96, "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": 0.85, "precision_at_3": 0.32, "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": 0.86, "mrr_at_3": 0.9083333333333331, "mrr_at_5": 0.9133333333333331, "mrr_at_10": 0.9144444444444443, "mrr_at_20": 0.9144444444444443, "mrr_at_100": 0.9144444444444443, "mrr_at_1000": 0.9144444444444443, "naucs_at_1_max": 0.0728385886905621, "naucs_at_1_std": -0.27940123657663585, "naucs_at_1_diff1": 0.838404544865166, "naucs_at_3_max": 0.43264898785631317, "naucs_at_3_std": 0.3535247432306253, "naucs_at_3_diff1": 0.7950946429181002, "naucs_at_5_max": 1.0, "naucs_at_5_std": 0.8692810457516413, "naucs_at_5_diff1": 0.5715286132037668, "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}, "infovqa_subsampled": {"ndcg_at_1": 0.746, "ndcg_at_3": 0.80343, "ndcg_at_5": 0.81832, "ndcg_at_10": 0.82857, "ndcg_at_20": 0.83312, "ndcg_at_100": 0.84258, "ndcg_at_1000": 0.84537, "map_at_1": 0.746, "map_at_3": 0.79, "map_at_5": 0.7983, "map_at_10": 0.80247, "map_at_20": 0.80372, "map_at_100": 0.8051, "map_at_1000": 0.8052, "recall_at_1": 0.746, "recall_at_3": 0.842, "recall_at_5": 0.878, "recall_at_10": 0.91, "recall_at_20": 0.928, "recall_at_100": 0.978, "recall_at_1000": 1.0, "precision_at_1": 0.746, "precision_at_3": 0.28067, "precision_at_5": 0.1756, "precision_at_10": 0.091, "precision_at_20": 0.0464, "precision_at_100": 0.00978, "precision_at_1000": 0.001, "mrr_at_1": 0.752, "mrr_at_3": 0.7953333333333332, "mrr_at_5": 0.8023333333333331, "mrr_at_10": 0.8065706349206349, "mrr_at_20": 0.8078986539174619, "mrr_at_100": 0.8091823645081221, "mrr_at_1000": 0.809263223979117, "naucs_at_1_max": 0.24674907189259504, "naucs_at_1_std": 0.11457666064661158, "naucs_at_1_diff1": 0.8740250282732915, "naucs_at_3_max": 0.23413123236282346, "naucs_at_3_std": 0.20991570348483488, "naucs_at_3_diff1": 0.8357975149102336, "naucs_at_5_max": 0.35286707023572256, "naucs_at_5_std": 0.37199604959947313, "naucs_at_5_diff1": 0.8207018895992207, "naucs_at_10_max": 0.3522596496009211, "naucs_at_10_std": 0.3307189542483652, "naucs_at_10_diff1": 0.8090976640617076, "naucs_at_20_max": 0.4744509713295461, "naucs_at_20_std": 0.47494553376906107, "naucs_at_20_diff1": 0.7939471631070897, "naucs_at_100_max": 0.44440793303781984, "naucs_at_100_std": 0.8327815974874812, "naucs_at_100_diff1": 0.8297168584345167, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.456, "ndcg_at_3": 0.52447, "ndcg_at_5": 0.54427, "ndcg_at_10": 0.56508, "ndcg_at_20": 0.58069, "ndcg_at_100": 0.60433, "ndcg_at_1000": 0.62051, "map_at_1": 0.456, "map_at_3": 0.508, "map_at_5": 0.519, "map_at_10": 0.52765, "map_at_20": 0.5319, "map_at_100": 0.53515, "map_at_1000": 0.53576, "recall_at_1": 0.456, "recall_at_3": 0.572, "recall_at_5": 0.62, "recall_at_10": 0.684, "recall_at_20": 0.746, "recall_at_100": 0.874, "recall_at_1000": 1.0, "precision_at_1": 0.456, "precision_at_3": 0.19067, "precision_at_5": 0.124, "precision_at_10": 0.0684, "precision_at_20": 0.0373, "precision_at_100": 0.00874, "precision_at_1000": 0.001, "mrr_at_1": 0.452, "mrr_at_3": 0.505, "mrr_at_5": 0.5164000000000001, "mrr_at_10": 0.5254579365079365, "mrr_at_20": 0.5290178752190362, "mrr_at_100": 0.5325203981148059, "mrr_at_1000": 0.5330986506794522, "naucs_at_1_max": 0.010704720337137848, "naucs_at_1_std": 0.4181494661921707, "naucs_at_1_diff1": 0.7688057111458236, "naucs_at_3_max": -0.0067852838115276684, "naucs_at_3_std": 0.408076792525558, "naucs_at_3_diff1": 0.7055654080347042, "naucs_at_5_max": -0.011161683506439484, "naucs_at_5_std": 0.452272097960188, "naucs_at_5_diff1": 0.6829497998035559, "naucs_at_10_max": -0.06663979903420814, "naucs_at_10_std": 0.4644934958160017, "naucs_at_10_diff1": 0.6670322281267268, "naucs_at_20_max": -0.08314881099503675, "naucs_at_20_std": 0.5636259190226841, "naucs_at_20_diff1": 0.6475212710859795, "naucs_at_100_max": -0.15012530637692442, "naucs_at_100_std": 0.8336557354576346, "naucs_at_100_diff1": 0.6215172139879154, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 2.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.724, "ndcg_at_3": 0.77659, "ndcg_at_5": 0.7914, "ndcg_at_10": 0.80967, "ndcg_at_20": 0.81716, "ndcg_at_100": 0.82667, "ndcg_at_1000": 0.82854, "map_at_1": 0.724, "map_at_3": 0.76367, "map_at_5": 0.77187, "map_at_10": 0.77989, "map_at_20": 0.78189, "map_at_100": 0.78316, "map_at_1000": 0.78324, "recall_at_1": 0.724, "recall_at_3": 0.814, "recall_at_5": 0.85, "recall_at_10": 0.904, "recall_at_20": 0.934, "recall_at_100": 0.986, "recall_at_1000": 1.0, "precision_at_1": 0.724, "precision_at_3": 0.27133, "precision_at_5": 0.17, "precision_at_10": 0.0904, "precision_at_20": 0.0467, "precision_at_100": 0.00986, "precision_at_1000": 0.001, "mrr_at_1": 0.72, "mrr_at_3": 0.7606666666666666, "mrr_at_5": 0.7704666666666665, "mrr_at_10": 0.7783031746031746, "mrr_at_20": 0.7798739388062916, "mrr_at_100": 0.7811347665019601, "mrr_at_1000": 0.781219393810504, "naucs_at_1_max": 0.016575744452395444, "naucs_at_1_std": 0.14620481415983924, "naucs_at_1_diff1": 0.8319131181262124, "naucs_at_3_max": -0.025943897313719388, "naucs_at_3_std": 0.19927764658111108, "naucs_at_3_diff1": 0.7774553764676329, "naucs_at_5_max": -0.0448735069102902, "naucs_at_5_std": 0.26161405792385234, "naucs_at_5_diff1": 0.7677282039192751, "naucs_at_10_max": -0.10797954318975009, "naucs_at_10_std": 0.20837223778400116, "naucs_at_10_diff1": 0.7147052306317629, "naucs_at_20_max": -0.00911433048928522, "naucs_at_20_std": 0.4119910590498834, "naucs_at_20_diff1": 0.7000503290790163, "naucs_at_100_max": 0.5246753983500644, "naucs_at_100_std": 0.8289315726290336, "naucs_at_100_diff1": 0.6839271409113703, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.75357, "ndcg_at_3": 0.82768, "ndcg_at_5": 0.83936, "ndcg_at_10": 0.85309, "ndcg_at_20": 0.85858, "ndcg_at_100": 0.86371, "ndcg_at_1000": 0.86371, "map_at_1": 0.75357, "map_at_3": 0.80893, "map_at_5": 0.81536, "map_at_10": 0.82095, "map_at_20": 0.8225, "map_at_100": 0.82339, "map_at_1000": 0.82339, "recall_at_1": 0.75357, "recall_at_3": 0.88214, "recall_at_5": 0.91071, "recall_at_10": 0.95357, "recall_at_20": 0.975, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.75357, "precision_at_3": 0.29405, "precision_at_5": 0.18214, "precision_at_10": 0.09536, "precision_at_20": 0.04875, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.7535714285714286, "mrr_at_3": 0.8101190476190477, "mrr_at_5": 0.8167261904761904, "mrr_at_10": 0.8221357709750566, "mrr_at_20": 0.8239959162569457, "mrr_at_100": 0.8248561140910201, "mrr_at_1000": 0.8248561140910201, "naucs_at_1_max": 0.5304566374894598, "naucs_at_1_std": 0.1615906461054432, "naucs_at_1_diff1": 0.8208688581619074, "naucs_at_3_max": 0.4836484318803355, "naucs_at_3_std": 0.21076407932338395, "naucs_at_3_diff1": 0.7733693395413521, "naucs_at_5_max": 0.4612358016225636, "naucs_at_5_std": 0.27449112978524876, "naucs_at_5_diff1": 0.7189851642886126, "naucs_at_10_max": 0.5759036686726754, "naucs_at_10_std": 0.32575594340300035, "naucs_at_10_diff1": 0.7358166602027056, "naucs_at_20_max": 0.47733910929211887, "naucs_at_20_std": 0.25596905428838695, "naucs_at_20_diff1": 0.7967511397858333, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": -0.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.53097, "ndcg_at_3": 0.62877, "ndcg_at_5": 0.65801, "ndcg_at_10": 0.68473, "ndcg_at_20": 0.69746, "ndcg_at_100": 0.71145, "ndcg_at_1000": 0.7146, "map_at_1": 0.53097, "map_at_3": 0.60443, "map_at_5": 0.62052, "map_at_10": 0.63158, "map_at_20": 0.63505, "map_at_100": 0.63713, "map_at_1000": 0.63728, "recall_at_1": 0.53097, "recall_at_3": 0.69934, "recall_at_5": 0.7709, "recall_at_10": 0.85328, "recall_at_20": 0.90379, "recall_at_100": 0.97715, "recall_at_1000": 1.0, "precision_at_1": 0.53097, "precision_at_3": 0.23311, "precision_at_5": 0.15418, "precision_at_10": 0.08533, "precision_at_20": 0.04519, "precision_at_100": 0.00977, "precision_at_1000": 0.001, "mrr_at_1": 0.5267588695129285, "mrr_at_3": 0.6032270996191631, "mrr_at_5": 0.61913209059932, "mrr_at_10": 0.6304894577594526, "mrr_at_20": 0.6337674299282028, "mrr_at_100": 0.6358829720309133, "mrr_at_1000": 0.6360412330135795, "naucs_at_1_max": 0.12207506980114474, "naucs_at_1_std": -0.06857703877057526, "naucs_at_1_diff1": 0.6350798605456752, "naucs_at_3_max": 0.13028071020881998, "naucs_at_3_std": -0.03204133285184471, "naucs_at_3_diff1": 0.536055692458893, "naucs_at_5_max": 0.14913490780176689, "naucs_at_5_std": 0.0019238783137197706, "naucs_at_5_diff1": 0.5114302291162272, "naucs_at_10_max": 0.152124608400107, "naucs_at_10_std": 0.10791232460205795, "naucs_at_10_diff1": 0.48383898061381275, "naucs_at_20_max": 0.1449130314981855, "naucs_at_20_std": 0.22594318462810645, "naucs_at_20_diff1": 0.43552881290118256, "naucs_at_100_max": -0.12684151303788002, "naucs_at_100_std": 0.5145680511335288, "naucs_at_100_diff1": 0.5095488271113825, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.55, "ndcg_at_3": 0.71488, "ndcg_at_5": 0.73167, "ndcg_at_10": 0.74796, "ndcg_at_20": 0.75568, "ndcg_at_100": 0.76079, "ndcg_at_1000": 0.76366, "map_at_1": 0.55, "map_at_3": 0.675, "map_at_5": 0.6845, "map_at_10": 0.69131, "map_at_20": 0.6935, "map_at_100": 0.69406, "map_at_1000": 0.69422, "recall_at_1": 0.55, "recall_at_3": 0.83, "recall_at_5": 0.87, "recall_at_10": 0.92, "recall_at_20": 0.95, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.55, "precision_at_3": 0.27667, "precision_at_5": 0.174, "precision_at_10": 0.092, "precision_at_20": 0.0475, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.57, "mrr_at_3": 0.69, "mrr_at_5": 0.6970000000000001, "mrr_at_10": 0.7041230158730158, "mrr_at_20": 0.7063159983291563, "mrr_at_100": 0.7069244639376219, "mrr_at_1000": 0.7070891464773044, "naucs_at_1_max": -0.13381190246642352, "naucs_at_1_std": -0.30200098293898753, "naucs_at_1_diff1": 0.5594199548867977, "naucs_at_3_max": -0.2639588734077385, "naucs_at_3_std": -0.5422302200034823, "naucs_at_3_diff1": 0.6073825476848427, "naucs_at_5_max": -0.2204135305072195, "naucs_at_5_std": -0.4037250981263389, "naucs_at_5_diff1": 0.4991023586585799, "naucs_at_10_max": -0.16129215914007541, "naucs_at_10_std": -0.5218253968253913, "naucs_at_10_diff1": 0.4407238859736181, "naucs_at_20_max": -0.38175400241396046, "naucs_at_20_std": -0.7713352007469497, "naucs_at_20_diff1": 0.5734029421882291, "naucs_at_100_max": -1.1341349547949189, "naucs_at_100_std": -0.6909430438842147, "naucs_at_100_diff1": 0.48572411420708356, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|