zpn commited on
Commit
efb6516
·
verified ·
1 Parent(s): 744d569

Update results.json

Browse files
Files changed (1) hide show
  1. results.json +1083 -1083
results.json CHANGED
@@ -1,1104 +1,1104 @@
1
  {
2
- "vidore/arxivqa_test_subsampled":{
3
- "ndcg_at_1":0.82,
4
- "ndcg_at_3":0.86355,
5
- "ndcg_at_5":0.87267,
6
- "ndcg_at_10":0.88369,
7
- "ndcg_at_20":0.88834,
8
- "ndcg_at_50":0.89325,
9
- "ndcg_at_100":0.8939,
10
- "map_at_1":0.82,
11
- "map_at_3":0.853,
12
- "map_at_5":0.8581,
13
- "map_at_10":0.86266,
14
- "map_at_20":0.86398,
15
- "map_at_50":0.86483,
16
- "map_at_100":0.86489,
17
- "recall_at_1":0.82,
18
- "recall_at_3":0.894,
19
- "recall_at_5":0.916,
20
- "recall_at_10":0.95,
21
- "recall_at_20":0.968,
22
- "recall_at_50":0.992,
23
- "recall_at_100":0.996,
24
- "precision_at_1":0.82,
25
- "precision_at_3":0.298,
26
- "precision_at_5":0.1832,
27
- "precision_at_10":0.095,
28
- "precision_at_20":0.0484,
29
- "precision_at_50":0.01984,
30
- "precision_at_100":0.00996,
31
- "mrr_at_1":0.82,
32
- "mrr_at_3":0.8516666666666663,
33
- "mrr_at_5":0.8576666666666662,
34
- "mrr_at_10":0.8620460317460314,
35
- "mrr_at_20":0.863583752358752,
36
- "mrr_at_50":0.8644210675649312,
37
- "mrr_at_100":0.8644797173539607,
38
- "naucs_at_1_max":0.812446304659103,
39
- "naucs_at_1_std":-0.12099350148694808,
40
- "naucs_at_1_diff1":0.9116973234937766,
41
- "naucs_at_3_max":0.8052286885682325,
42
- "naucs_at_3_std":-0.10011891450579295,
43
- "naucs_at_3_diff1":0.8805530411941155,
44
- "naucs_at_5_max":0.8331665999733249,
45
- "naucs_at_5_std":-0.10378595882797696,
46
- "naucs_at_5_diff1":0.8882330710061808,
47
- "naucs_at_10_max":0.870214752567696,
48
- "naucs_at_10_std":-0.012511671335205815,
49
- "naucs_at_10_diff1":0.8939309056956121,
50
- "naucs_at_20_max":0.8751167133520102,
51
- "naucs_at_20_std":-0.03801937441644435,
52
- "naucs_at_20_diff1":0.8853291316526594,
53
- "naucs_at_50_max":0.8978758169934562,
54
- "naucs_at_50_std":-0.07457983193277996,
55
- "naucs_at_50_diff1":0.9673202614378978,
56
- "naucs_at_100_max":0.9346405228758466,
57
- "naucs_at_100_std":0.41433239962652135,
58
- "naucs_at_100_diff1":0.9346405228758466
59
  },
60
- "vidore/docvqa_test_subsampled":{
61
- "ndcg_at_1":0.49667,
62
- "ndcg_at_3":0.58045,
63
- "ndcg_at_5":0.5961,
64
- "ndcg_at_10":0.61715,
65
- "ndcg_at_20":0.63148,
66
- "ndcg_at_50":0.64476,
67
- "ndcg_at_100":0.65117,
68
- "map_at_1":0.49667,
69
- "map_at_3":0.56098,
70
- "map_at_5":0.56973,
71
- "map_at_10":0.57815,
72
- "map_at_20":0.58195,
73
- "map_at_50":0.58412,
74
- "map_at_100":0.58466,
75
- "recall_at_1":0.49667,
76
- "recall_at_3":0.63636,
77
- "recall_at_5":0.67406,
78
- "recall_at_10":0.74058,
79
- "recall_at_20":0.79823,
80
- "recall_at_50":0.86475,
81
- "recall_at_100":0.90466,
82
- "precision_at_1":0.49667,
83
- "precision_at_3":0.21212,
84
- "precision_at_5":0.13481,
85
- "precision_at_10":0.07406,
86
- "precision_at_20":0.03991,
87
- "precision_at_50":0.01729,
88
- "precision_at_100":0.00905,
89
- "mrr_at_1":0.49667405764966743,
90
- "mrr_at_3":0.5598669623059869,
91
- "mrr_at_5":0.5686252771618625,
92
- "mrr_at_10":0.5774082286277407,
93
- "mrr_at_20":0.5810969093386733,
94
- "mrr_at_50":0.5833476204155297,
95
- "mrr_at_100":0.5838896413403367,
96
- "naucs_at_1_max":0.6447171350460632,
97
- "naucs_at_1_std":-0.09484358295898986,
98
- "naucs_at_1_diff1":0.8458551941133076,
99
- "naucs_at_3_max":0.7454063347349457,
100
- "naucs_at_3_std":0.07229007919713754,
101
- "naucs_at_3_diff1":0.7797700229519104,
102
- "naucs_at_5_max":0.7393820262077632,
103
- "naucs_at_5_std":0.07367377967418601,
104
- "naucs_at_5_diff1":0.7716289000253728,
105
- "naucs_at_10_max":0.8009576009267406,
106
- "naucs_at_10_std":0.17268036524877706,
107
- "naucs_at_10_diff1":0.771081787065486,
108
- "naucs_at_20_max":0.8203029945264155,
109
- "naucs_at_20_std":0.19845745554768213,
110
- "naucs_at_20_diff1":0.7679325913145596,
111
- "naucs_at_50_max":0.8514788472516402,
112
- "naucs_at_50_std":0.4169328726103599,
113
- "naucs_at_50_diff1":0.7559123754864738,
114
- "naucs_at_100_max":0.9163273855022911,
115
- "naucs_at_100_std":0.6626096316780477,
116
- "naucs_at_100_diff1":0.7467504013388263
117
  },
118
- "vidore/infovqa_test_subsampled":{
119
- "ndcg_at_1":0.84413,
120
- "ndcg_at_3":0.88746,
121
- "ndcg_at_5":0.89835,
122
- "ndcg_at_10":0.90248,
123
- "ndcg_at_20":0.90764,
124
- "ndcg_at_50":0.90851,
125
- "ndcg_at_100":0.90882,
126
- "map_at_1":0.84413,
127
- "map_at_3":0.87719,
128
- "map_at_5":0.88327,
129
- "map_at_10":0.88509,
130
- "map_at_20":0.88653,
131
- "map_at_50":0.8867,
132
- "map_at_100":0.88672,
133
- "recall_at_1":0.84413,
134
- "recall_at_3":0.917,
135
- "recall_at_5":0.94332,
136
- "recall_at_10":0.95547,
137
- "recall_at_20":0.97571,
138
- "recall_at_50":0.97976,
139
- "recall_at_100":0.98178,
140
- "precision_at_1":0.84413,
141
- "precision_at_3":0.30567,
142
- "precision_at_5":0.18866,
143
- "precision_at_10":0.09555,
144
- "precision_at_20":0.04879,
145
- "precision_at_50":0.0196,
146
- "precision_at_100":0.00982,
147
- "mrr_at_1":0.8421052631578947,
148
- "mrr_at_3":0.8761808367071524,
149
- "mrr_at_5":0.8821524966261807,
150
- "mrr_at_10":0.8839598997493734,
151
- "mrr_at_20":0.8854126323282514,
152
- "mrr_at_50":0.8855840009206725,
153
- "mrr_at_100":0.8856042438356523,
154
- "naucs_at_1_max":0.5820526964694293,
155
- "naucs_at_1_std":-0.12258720751834291,
156
- "naucs_at_1_diff1":0.9179232290494516,
157
- "naucs_at_3_max":0.5688472589103235,
158
- "naucs_at_3_std":-0.03525896756328502,
159
- "naucs_at_3_diff1":0.8589169639952821,
160
- "naucs_at_5_max":0.658104574327871,
161
- "naucs_at_5_std":0.23877363760140033,
162
- "naucs_at_5_diff1":0.870167572146584,
163
- "naucs_at_10_max":0.7995309447871867,
164
- "naucs_at_10_std":0.4714428670492628,
165
- "naucs_at_10_diff1":0.8785680767019614,
166
- "naucs_at_20_max":0.9891165454946104,
167
- "naucs_at_20_std":0.8992936045133497,
168
- "naucs_at_20_diff1":0.8757902959599302,
169
- "naucs_at_50_max":0.9869398545935183,
170
- "naucs_at_50_std":0.9199859445982981,
171
- "naucs_at_50_diff1":0.8640085005583854,
172
- "naucs_at_100_max":0.9854887273261316,
173
- "naucs_at_100_std":0.9256067666719673,
174
- "naucs_at_100_diff1":0.8488983339537634
175
  },
176
- "vidore/tabfquad_test_subsampled":{
177
- "ndcg_at_1":0.875,
178
- "ndcg_at_3":0.92542,
179
- "ndcg_at_5":0.92972,
180
- "ndcg_at_10":0.93672,
181
- "ndcg_at_20":0.93858,
182
- "ndcg_at_50":0.93921,
183
- "ndcg_at_100":0.93921,
184
- "map_at_1":0.875,
185
- "map_at_3":0.91429,
186
- "map_at_5":0.91661,
187
- "map_at_10":0.91954,
188
- "map_at_20":0.92007,
189
- "map_at_50":0.92015,
190
- "map_at_100":0.92015,
191
- "recall_at_1":0.875,
192
- "recall_at_3":0.95714,
193
- "recall_at_5":0.96786,
194
- "recall_at_10":0.98929,
195
- "recall_at_20":0.99643,
196
- "recall_at_50":1.0,
197
- "recall_at_100":1.0,
198
- "precision_at_1":0.875,
199
- "precision_at_3":0.31905,
200
- "precision_at_5":0.19357,
201
- "precision_at_10":0.09893,
202
- "precision_at_20":0.04982,
203
- "precision_at_50":0.02,
204
- "precision_at_100":0.01,
205
- "mrr_at_1":0.875,
206
- "mrr_at_3":0.9142857142857143,
207
- "mrr_at_5":0.9166071428571427,
208
- "mrr_at_10":0.9195436507936509,
209
- "mrr_at_20":0.9200931013431013,
210
- "mrr_at_50":0.9201659876404774,
211
- "mrr_at_100":0.9201659876404774,
212
- "naucs_at_1_max":0.8578413915901933,
213
- "naucs_at_1_std":0.3373099575400639,
214
- "naucs_at_1_diff1":0.9291192987262019,
215
- "naucs_at_3_max":0.94281045751634,
216
- "naucs_at_3_std":0.7399626517273589,
217
- "naucs_at_3_diff1":0.9192732648615032,
218
- "naucs_at_5_max":0.9546114742193174,
219
- "naucs_at_5_std":0.8474945533769075,
220
- "naucs_at_5_diff1":0.9214130096483005,
221
- "naucs_at_10_max":1.0,
222
- "naucs_at_10_std":0.8638344226579515,
223
- "naucs_at_10_diff1":0.807812013694365,
224
- "naucs_at_20_max":1.0,
225
- "naucs_at_20_std":1.0,
226
- "naucs_at_20_diff1":0.8692810457516478,
227
- "naucs_at_50_max":1.0,
228
- "naucs_at_50_std":1.0,
229
- "naucs_at_50_diff1":1.0,
230
- "naucs_at_100_max":1.0,
231
- "naucs_at_100_std":1.0,
232
- "naucs_at_100_diff1":1.0
233
  },
234
- "vidore/tatdqa_test":{
235
- "ndcg_at_1":0.54678,
236
- "ndcg_at_3":0.66776,
237
- "ndcg_at_5":0.69393,
238
- "ndcg_at_10":0.71886,
239
- "ndcg_at_20":0.72921,
240
- "ndcg_at_50":0.73649,
241
- "ndcg_at_100":0.73867,
242
- "map_at_1":0.54678,
243
- "map_at_3":0.63761,
244
- "map_at_5":0.65222,
245
- "map_at_10":0.66285,
246
- "map_at_20":0.66571,
247
- "map_at_50":0.66691,
248
- "map_at_100":0.6671,
249
- "recall_at_1":0.54678,
250
- "recall_at_3":0.75516,
251
- "recall_at_5":0.81835,
252
- "recall_at_10":0.89368,
253
- "recall_at_20":0.93439,
254
- "recall_at_50":0.97084,
255
- "recall_at_100":0.9842,
256
- "precision_at_1":0.54678,
257
- "precision_at_3":0.25172,
258
- "precision_at_5":0.16367,
259
- "precision_at_10":0.08937,
260
- "precision_at_20":0.04672,
261
- "precision_at_50":0.01942,
262
- "precision_at_100":0.00984,
263
- "mrr_at_1":0.5449574726609964,
264
- "mrr_at_3":0.6363912515188347,
265
- "mrr_at_5":0.6513061968408275,
266
- "mrr_at_10":0.6619414067773731,
267
- "mrr_at_20":0.6648084703051904,
268
- "mrr_at_50":0.666014531722658,
269
- "mrr_at_100":0.6662005960985684,
270
- "naucs_at_1_max":0.2731052125785171,
271
- "naucs_at_1_std":-0.14426853499658712,
272
- "naucs_at_1_diff1":0.7112304282234161,
273
- "naucs_at_3_max":0.32666962544180816,
274
- "naucs_at_3_std":-0.07666756779655057,
275
- "naucs_at_3_diff1":0.5831996505006363,
276
- "naucs_at_5_max":0.35015803161999937,
277
- "naucs_at_5_std":-0.056362663125386854,
278
- "naucs_at_5_diff1":0.5605231352339403,
279
- "naucs_at_10_max":0.45904296783912285,
280
- "naucs_at_10_std":0.05818769804418837,
281
- "naucs_at_10_diff1":0.5464314336687579,
282
- "naucs_at_20_max":0.5489800312526507,
283
- "naucs_at_20_std":0.19000550595425766,
284
- "naucs_at_20_diff1":0.5437396218670546,
285
- "naucs_at_50_max":0.6781089810313774,
286
- "naucs_at_50_std":0.5656683520376952,
287
- "naucs_at_50_diff1":0.5981871760182872,
288
- "naucs_at_100_max":0.7245933213322641,
289
- "naucs_at_100_std":0.6419966475290947,
290
- "naucs_at_100_diff1":0.6649811059473633
291
  },
292
- "vidore/shiftproject_test":{
293
- "ndcg_at_1":0.77,
294
- "ndcg_at_3":0.86309,
295
- "ndcg_at_5":0.87171,
296
- "ndcg_at_10":0.87819,
297
- "ndcg_at_20":0.88532,
298
- "ndcg_at_50":0.88532,
299
- "ndcg_at_100":0.88532,
300
- "map_at_1":0.77,
301
- "map_at_3":0.84,
302
- "map_at_5":0.845,
303
- "map_at_10":0.84768,
304
- "map_at_20":0.84939,
305
- "map_at_50":0.84939,
306
- "map_at_100":0.84939,
307
- "recall_at_1":0.77,
308
- "recall_at_3":0.93,
309
- "recall_at_5":0.95,
310
- "recall_at_10":0.97,
311
- "recall_at_20":1.0,
312
- "recall_at_50":1.0,
313
- "recall_at_100":1.0,
314
- "precision_at_1":0.77,
315
- "precision_at_3":0.31,
316
- "precision_at_5":0.19,
317
- "precision_at_10":0.097,
318
- "precision_at_20":0.05,
319
- "precision_at_50":0.02,
320
- "precision_at_100":0.01,
321
- "mrr_at_1":0.78,
322
- "mrr_at_3":0.845,
323
- "mrr_at_5":0.85,
324
- "mrr_at_10":0.8528571428571429,
325
- "mrr_at_20":0.8545376984126984,
326
- "mrr_at_50":0.8545376984126984,
327
- "mrr_at_100":0.8545376984126984,
328
- "naucs_at_1_max":0.14487142185716537,
329
- "naucs_at_1_std":-0.49399073431660045,
330
- "naucs_at_1_diff1":0.7040576531411565,
331
- "naucs_at_3_max":0.36494597839135445,
332
- "naucs_at_3_std":-0.6566626650660264,
333
- "naucs_at_3_diff1":0.7675736961451218,
334
- "naucs_at_5_max":0.716713352007473,
335
- "naucs_at_5_std":-0.34098972922501514,
336
- "naucs_at_5_diff1":0.7301587301587323,
337
- "naucs_at_10_max":0.5714285714285722,
338
- "naucs_at_10_std":-0.8445378151260495,
339
- "naucs_at_10_diff1":0.5938375350140046,
340
- "naucs_at_20_max":1.0,
341
- "naucs_at_20_std":1.0,
342
- "naucs_at_20_diff1":1.0,
343
- "naucs_at_50_max":null,
344
- "naucs_at_50_std":null,
345
- "naucs_at_50_diff1":null,
346
- "naucs_at_100_max":null,
347
- "naucs_at_100_std":null,
348
- "naucs_at_100_diff1":null
349
  },
350
- "vidore/syntheticDocQA_artificial_intelligence_test":{
351
- "ndcg_at_1":0.94,
352
- "ndcg_at_3":0.97524,
353
- "ndcg_at_5":0.97524,
354
- "ndcg_at_10":0.97524,
355
- "ndcg_at_20":0.97524,
356
- "ndcg_at_50":0.97524,
357
- "ndcg_at_100":0.97524,
358
- "map_at_1":0.94,
359
- "map_at_3":0.96667,
360
- "map_at_5":0.96667,
361
- "map_at_10":0.96667,
362
- "map_at_20":0.96667,
363
- "map_at_50":0.96667,
364
- "map_at_100":0.96667,
365
- "recall_at_1":0.94,
366
- "recall_at_3":1.0,
367
- "recall_at_5":1.0,
368
- "recall_at_10":1.0,
369
- "recall_at_20":1.0,
370
- "recall_at_50":1.0,
371
- "recall_at_100":1.0,
372
- "precision_at_1":0.94,
373
- "precision_at_3":0.33333,
374
- "precision_at_5":0.2,
375
- "precision_at_10":0.1,
376
- "precision_at_20":0.05,
377
- "precision_at_50":0.02,
378
- "precision_at_100":0.01,
379
- "mrr_at_1":0.95,
380
- "mrr_at_3":0.9716666666666667,
381
- "mrr_at_5":0.9716666666666667,
382
- "mrr_at_10":0.9716666666666667,
383
- "mrr_at_20":0.9716666666666667,
384
- "mrr_at_50":0.9716666666666667,
385
- "mrr_at_100":0.9716666666666667,
386
- "naucs_at_1_max":0.46444133208839294,
387
- "naucs_at_1_std":0.1777155306567078,
388
- "naucs_at_1_diff1":0.9319172113289763,
389
- "naucs_at_3_max":1.0,
390
- "naucs_at_3_std":1.0,
391
- "naucs_at_3_diff1":1.0,
392
- "naucs_at_5_max":1.0,
393
- "naucs_at_5_std":1.0,
394
- "naucs_at_5_diff1":1.0,
395
- "naucs_at_10_max":1.0,
396
- "naucs_at_10_std":1.0,
397
- "naucs_at_10_diff1":1.0,
398
- "naucs_at_20_max":1.0,
399
- "naucs_at_20_std":1.0,
400
- "naucs_at_20_diff1":1.0,
401
- "naucs_at_50_max":null,
402
- "naucs_at_50_std":null,
403
- "naucs_at_50_diff1":null,
404
- "naucs_at_100_max":null,
405
- "naucs_at_100_std":null,
406
- "naucs_at_100_diff1":null
407
  },
408
- "vidore/syntheticDocQA_energy_test":{
409
- "ndcg_at_1":0.89,
410
- "ndcg_at_3":0.93286,
411
- "ndcg_at_5":0.93286,
412
- "ndcg_at_10":0.93957,
413
- "ndcg_at_20":0.93957,
414
- "ndcg_at_50":0.94334,
415
- "ndcg_at_100":0.94334,
416
- "map_at_1":0.89,
417
- "map_at_3":0.92333,
418
- "map_at_5":0.92333,
419
- "map_at_10":0.92625,
420
- "map_at_20":0.92625,
421
- "map_at_50":0.92677,
422
- "map_at_100":0.92677,
423
- "recall_at_1":0.89,
424
- "recall_at_3":0.96,
425
- "recall_at_5":0.96,
426
- "recall_at_10":0.98,
427
- "recall_at_20":0.98,
428
- "recall_at_50":1.0,
429
- "recall_at_100":1.0,
430
- "precision_at_1":0.89,
431
- "precision_at_3":0.32,
432
- "precision_at_5":0.192,
433
- "precision_at_10":0.098,
434
- "precision_at_20":0.049,
435
- "precision_at_50":0.02,
436
- "precision_at_100":0.01,
437
- "mrr_at_1":0.89,
438
- "mrr_at_3":0.9233333333333333,
439
- "mrr_at_5":0.9233333333333333,
440
- "mrr_at_10":0.9262499999999999,
441
- "mrr_at_20":0.9262499999999999,
442
- "mrr_at_50":0.9267777777777776,
443
- "mrr_at_100":0.9267777777777776,
444
- "naucs_at_1_max":0.26032986856799367,
445
- "naucs_at_1_std":-0.8372562494631047,
446
- "naucs_at_1_diff1":0.9639206253758271,
447
- "naucs_at_3_max":0.4293884220354785,
448
- "naucs_at_3_std":-0.9801587301587241,
449
- "naucs_at_3_diff1":0.9673202614379101,
450
- "naucs_at_5_max":0.42938842203548094,
451
- "naucs_at_5_std":-0.9801587301587192,
452
- "naucs_at_5_diff1":0.967320261437907,
453
- "naucs_at_10_max":-0.07586367880484816,
454
- "naucs_at_10_std":-1.445845004668519,
455
- "naucs_at_10_diff1":0.9346405228758136,
456
- "naucs_at_20_max":-0.07586367880484816,
457
- "naucs_at_20_std":-1.445845004668519,
458
- "naucs_at_20_diff1":0.9346405228758136,
459
- "naucs_at_50_max":null,
460
- "naucs_at_50_std":null,
461
- "naucs_at_50_diff1":null,
462
- "naucs_at_100_max":null,
463
- "naucs_at_100_std":null,
464
- "naucs_at_100_diff1":null
465
  },
466
- "vidore/syntheticDocQA_government_reports_test":{
467
- "ndcg_at_1":0.9,
468
- "ndcg_at_3":0.94917,
469
- "ndcg_at_5":0.9569,
470
- "ndcg_at_10":0.9569,
471
- "ndcg_at_20":0.9569,
472
- "ndcg_at_50":0.9569,
473
- "ndcg_at_100":0.9569,
474
- "map_at_1":0.9,
475
- "map_at_3":0.93833,
476
- "map_at_5":0.94233,
477
- "map_at_10":0.94233,
478
- "map_at_20":0.94233,
479
- "map_at_50":0.94233,
480
- "map_at_100":0.94233,
481
- "recall_at_1":0.9,
482
- "recall_at_3":0.98,
483
- "recall_at_5":1.0,
484
- "recall_at_10":1.0,
485
- "recall_at_20":1.0,
486
- "recall_at_50":1.0,
487
- "recall_at_100":1.0,
488
- "precision_at_1":0.9,
489
- "precision_at_3":0.32667,
490
- "precision_at_5":0.2,
491
- "precision_at_10":0.1,
492
- "precision_at_20":0.05,
493
- "precision_at_50":0.02,
494
- "precision_at_100":0.01,
495
- "mrr_at_1":0.9,
496
- "mrr_at_3":0.9383333333333332,
497
- "mrr_at_5":0.9423333333333334,
498
- "mrr_at_10":0.9423333333333334,
499
- "mrr_at_20":0.9423333333333334,
500
- "mrr_at_50":0.9423333333333334,
501
- "mrr_at_100":0.9423333333333334,
502
- "naucs_at_1_max":0.5017740429505145,
503
- "naucs_at_1_std":-0.4561624649859955,
504
- "naucs_at_1_diff1":0.8643790849673212,
505
- "naucs_at_3_max":0.7770774976657261,
506
- "naucs_at_3_std":-1.151727357609717,
507
- "naucs_at_3_diff1":0.7957516339869218,
508
- "naucs_at_5_max":1.0,
509
- "naucs_at_5_std":1.0,
510
- "naucs_at_5_diff1":1.0,
511
- "naucs_at_10_max":1.0,
512
- "naucs_at_10_std":1.0,
513
- "naucs_at_10_diff1":1.0,
514
- "naucs_at_20_max":1.0,
515
- "naucs_at_20_std":1.0,
516
- "naucs_at_20_diff1":1.0,
517
- "naucs_at_50_max":null,
518
- "naucs_at_50_std":null,
519
- "naucs_at_50_diff1":null,
520
- "naucs_at_100_max":null,
521
- "naucs_at_100_std":null,
522
- "naucs_at_100_diff1":null
523
  },
524
- "vidore/syntheticDocQA_healthcare_industry_test":{
525
- "ndcg_at_1":0.95,
526
- "ndcg_at_3":0.97893,
527
- "ndcg_at_5":0.97893,
528
- "ndcg_at_10":0.97893,
529
- "ndcg_at_20":0.97893,
530
- "ndcg_at_50":0.97893,
531
- "ndcg_at_100":0.97893,
532
- "map_at_1":0.95,
533
- "map_at_3":0.97167,
534
- "map_at_5":0.97167,
535
- "map_at_10":0.97167,
536
- "map_at_20":0.97167,
537
- "map_at_50":0.97167,
538
- "map_at_100":0.97167,
539
- "recall_at_1":0.95,
540
- "recall_at_3":1.0,
541
- "recall_at_5":1.0,
542
- "recall_at_10":1.0,
543
- "recall_at_20":1.0,
544
- "recall_at_50":1.0,
545
- "recall_at_100":1.0,
546
- "precision_at_1":0.95,
547
- "precision_at_3":0.33333,
548
- "precision_at_5":0.2,
549
- "precision_at_10":0.1,
550
- "precision_at_20":0.05,
551
- "precision_at_50":0.02,
552
- "precision_at_100":0.01,
553
- "mrr_at_1":0.95,
554
- "mrr_at_3":0.9716666666666666,
555
- "mrr_at_5":0.9716666666666666,
556
- "mrr_at_10":0.9716666666666666,
557
- "mrr_at_20":0.9716666666666666,
558
- "mrr_at_50":0.9716666666666666,
559
- "mrr_at_100":0.9716666666666666,
560
- "naucs_at_1_max":0.33015873015873015,
561
- "naucs_at_1_std":-0.5752567693744151,
562
- "naucs_at_1_diff1":0.8954248366013068,
563
- "naucs_at_3_max":1.0,
564
- "naucs_at_3_std":1.0,
565
- "naucs_at_3_diff1":1.0,
566
- "naucs_at_5_max":1.0,
567
- "naucs_at_5_std":1.0,
568
- "naucs_at_5_diff1":1.0,
569
- "naucs_at_10_max":1.0,
570
- "naucs_at_10_std":1.0,
571
- "naucs_at_10_diff1":1.0,
572
- "naucs_at_20_max":1.0,
573
- "naucs_at_20_std":1.0,
574
- "naucs_at_20_diff1":1.0,
575
- "naucs_at_50_max":null,
576
- "naucs_at_50_std":null,
577
- "naucs_at_50_diff1":null,
578
- "naucs_at_100_max":null,
579
- "naucs_at_100_std":null,
580
- "naucs_at_100_diff1":null
581
  },
582
- "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered":{
583
- "ndcg_at_1":0.61875,
584
- "ndcg_at_3":0.60533,
585
- "ndcg_at_5":0.6249,
586
- "ndcg_at_10":0.6533,
587
- "ndcg_at_20":0.68742,
588
- "ndcg_at_50":0.70992,
589
- "ndcg_at_100":0.72024,
590
- "map_at_1":0.38719,
591
- "map_at_3":0.49654,
592
- "map_at_5":0.53693,
593
- "map_at_10":0.5662,
594
- "map_at_20":0.58481,
595
- "map_at_50":0.59335,
596
- "map_at_100":0.59568,
597
- "recall_at_1":0.38719,
598
- "recall_at_3":0.55967,
599
- "recall_at_5":0.64187,
600
- "recall_at_10":0.73101,
601
- "recall_at_20":0.82946,
602
- "recall_at_50":0.8939,
603
- "recall_at_100":0.93192,
604
- "precision_at_1":0.61875,
605
- "precision_at_3":0.36875,
606
- "precision_at_5":0.27875,
607
- "precision_at_10":0.17313,
608
- "precision_at_20":0.105,
609
- "precision_at_50":0.0505,
610
- "precision_at_100":0.02744,
611
- "mrr_at_1":0.60625,
612
- "mrr_at_3":0.6947916666666666,
613
- "mrr_at_5":0.7076041666666666,
614
- "mrr_at_10":0.7141666666666665,
615
- "mrr_at_20":0.7167027497302748,
616
- "mrr_at_50":0.7175877436934345,
617
- "mrr_at_100":0.7176993508362915,
618
- "naucs_at_1_max":0.27072241887056714,
619
- "naucs_at_1_std":-0.30666589925849186,
620
- "naucs_at_1_diff1":0.37145433441729697,
621
- "naucs_at_3_max":0.1575493620566184,
622
- "naucs_at_3_std":-0.14675377187982588,
623
- "naucs_at_3_diff1":-0.012422723353258194,
624
- "naucs_at_5_max":0.12243596821473231,
625
- "naucs_at_5_std":-0.05745497027699916,
626
- "naucs_at_5_diff1":-0.11057882383111498,
627
- "naucs_at_10_max":0.09666741292736748,
628
- "naucs_at_10_std":0.06431701154571953,
629
- "naucs_at_10_diff1":-0.16892677050351262,
630
- "naucs_at_20_max":-4.1139254210270476e-05,
631
- "naucs_at_20_std":0.16775721777388994,
632
- "naucs_at_20_diff1":-0.22444494485174687,
633
- "naucs_at_50_max":-0.026208062431506616,
634
- "naucs_at_50_std":0.27289212578690536,
635
- "naucs_at_50_diff1":-0.23337444980105218,
636
- "naucs_at_100_max":-0.07013692948482042,
637
- "naucs_at_100_std":0.2614993895421859,
638
- "naucs_at_100_diff1":-0.2529383758901295
639
  },
640
- "vidore/synthetic_economics_macro_economy_2024_filtered_v1.0":{
641
- "ndcg_at_1":0.75862,
642
- "ndcg_at_3":0.66558,
643
- "ndcg_at_5":0.6364,
644
- "ndcg_at_10":0.60412,
645
- "ndcg_at_20":0.61161,
646
- "ndcg_at_50":0.6674,
647
- "ndcg_at_100":0.71286,
648
- "map_at_1":0.13294,
649
- "map_at_3":0.22432,
650
- "map_at_5":0.28141,
651
- "map_at_10":0.35042,
652
- "map_at_20":0.39877,
653
- "map_at_50":0.45406,
654
- "map_at_100":0.48535,
655
- "recall_at_1":0.13294,
656
- "recall_at_3":0.24879,
657
- "recall_at_5":0.33068,
658
- "recall_at_10":0.45414,
659
- "recall_at_20":0.57711,
660
- "recall_at_50":0.7563,
661
- "recall_at_100":0.89138,
662
- "precision_at_1":0.75862,
663
- "precision_at_3":0.59195,
664
- "precision_at_5":0.53793,
665
- "precision_at_10":0.42069,
666
- "precision_at_20":0.30517,
667
- "precision_at_50":0.19034,
668
- "precision_at_100":0.1281,
669
- "mrr_at_1":0.7586206896551724,
670
- "mrr_at_3":0.8045977011494254,
671
- "mrr_at_5":0.8166666666666668,
672
- "mrr_at_10":0.8212643678160919,
673
- "mrr_at_20":0.8248997410635341,
674
- "mrr_at_50":0.8248997410635341,
675
- "mrr_at_100":0.8248997410635341,
676
- "naucs_at_1_max":0.4227698077082209,
677
- "naucs_at_1_std":0.19946586940003241,
678
- "naucs_at_1_diff1":0.16206457409265,
679
- "naucs_at_3_max":0.5153814385463314,
680
- "naucs_at_3_std":0.33515138197678757,
681
- "naucs_at_3_diff1":-0.20009189610763917,
682
- "naucs_at_5_max":0.5900831255483465,
683
- "naucs_at_5_std":0.42933205868067004,
684
- "naucs_at_5_diff1":-0.17086750774916223,
685
- "naucs_at_10_max":0.5992696167986679,
686
- "naucs_at_10_std":0.47588375698237223,
687
- "naucs_at_10_diff1":-0.13260066848766422,
688
- "naucs_at_20_max":0.5582586435890009,
689
- "naucs_at_20_std":0.5038374365864665,
690
- "naucs_at_20_diff1":-0.1176926445837237,
691
- "naucs_at_50_max":0.5432600497682903,
692
- "naucs_at_50_std":0.5479275799361487,
693
- "naucs_at_50_diff1":-0.10889833063192782,
694
- "naucs_at_100_max":0.5229583863106058,
695
- "naucs_at_100_std":0.5435637228955296,
696
- "naucs_at_100_diff1":-0.08468927917935376
697
  },
698
- "vidore/synthetic_rse_restaurant_filtered_v1.0":{
699
- "ndcg_at_1":0.40351,
700
- "ndcg_at_3":0.45091,
701
- "ndcg_at_5":0.49439,
702
- "ndcg_at_10":0.55003,
703
- "ndcg_at_20":0.58106,
704
- "ndcg_at_50":0.5993,
705
- "ndcg_at_100":0.61956,
706
- "map_at_1":0.22383,
707
- "map_at_3":0.33472,
708
- "map_at_5":0.37842,
709
- "map_at_10":0.41671,
710
- "map_at_20":0.43823,
711
- "map_at_50":0.44683,
712
- "map_at_100":0.45288,
713
- "recall_at_1":0.22383,
714
- "recall_at_3":0.40691,
715
- "recall_at_5":0.54033,
716
- "recall_at_10":0.71479,
717
- "recall_at_20":0.8034,
718
- "recall_at_50":0.86038,
719
- "recall_at_100":0.92373,
720
- "precision_at_1":0.40351,
721
- "precision_at_3":0.30994,
722
- "precision_at_5":0.25614,
723
- "precision_at_10":0.17544,
724
- "precision_at_20":0.11316,
725
- "precision_at_50":0.05474,
726
- "precision_at_100":0.03333,
727
- "mrr_at_1":0.42105263157894735,
728
- "mrr_at_3":0.543859649122807,
729
- "mrr_at_5":0.5763157894736841,
730
- "mrr_at_10":0.5925160122528542,
731
- "mrr_at_20":0.5925160122528542,
732
- "mrr_at_50":0.59296585480796,
733
- "mrr_at_100":0.59296585480796,
734
- "naucs_at_1_max":0.3607011316641863,
735
- "naucs_at_1_std":0.16281795519485523,
736
- "naucs_at_1_diff1":0.4423264543117199,
737
- "naucs_at_3_max":0.248943549054806,
738
- "naucs_at_3_std":0.11598523586964242,
739
- "naucs_at_3_diff1":0.3693732108201387,
740
- "naucs_at_5_max":0.09070545701728222,
741
- "naucs_at_5_std":0.035895685604651485,
742
- "naucs_at_5_diff1":0.11310819654651481,
743
- "naucs_at_10_max":0.025784503411264655,
744
- "naucs_at_10_std":0.08680461640852888,
745
- "naucs_at_10_diff1":0.17678674068585096,
746
- "naucs_at_20_max":-0.05564005116785854,
747
- "naucs_at_20_std":0.07668382220435485,
748
- "naucs_at_20_diff1":0.14421544846362475,
749
- "naucs_at_50_max":-0.07299334885090104,
750
- "naucs_at_50_std":0.11838037986656147,
751
- "naucs_at_50_diff1":0.08439872237038344,
752
- "naucs_at_100_max":-0.154028488184722,
753
- "naucs_at_100_std":0.06646101830793238,
754
- "naucs_at_100_diff1":0.07594418237521101
755
  },
756
- "vidore/synthetic_axa_filtered_v1.0":{
757
- "ndcg_at_1":0.77778,
758
- "ndcg_at_3":0.6939,
759
- "ndcg_at_5":0.69627,
760
- "ndcg_at_10":0.67735,
761
- "ndcg_at_20":0.70844,
762
- "ndcg_at_50":0.74866,
763
- "ndcg_at_100":0.77447,
764
- "map_at_1":0.37182,
765
- "map_at_3":0.47004,
766
- "map_at_5":0.51407,
767
- "map_at_10":0.55255,
768
- "map_at_20":0.58582,
769
- "map_at_50":0.61023,
770
- "map_at_100":0.61746,
771
- "recall_at_1":0.37182,
772
- "recall_at_3":0.54554,
773
- "recall_at_5":0.61902,
774
- "recall_at_10":0.68077,
775
- "recall_at_20":0.78791,
776
- "recall_at_50":0.88064,
777
- "recall_at_100":0.98184,
778
- "precision_at_1":0.77778,
779
- "precision_at_3":0.44444,
780
- "precision_at_5":0.38889,
781
- "precision_at_10":0.25556,
782
- "precision_at_20":0.16389,
783
- "precision_at_50":0.08333,
784
- "precision_at_100":0.04667,
785
- "mrr_at_1":0.7777777777777778,
786
- "mrr_at_3":0.8148148148148149,
787
- "mrr_at_5":0.8287037037037037,
788
- "mrr_at_10":0.8287037037037037,
789
- "mrr_at_20":0.8287037037037037,
790
- "mrr_at_50":0.8287037037037037,
791
- "mrr_at_100":0.8296453232893912,
792
- "naucs_at_1_max":0.6008361717023135,
793
- "naucs_at_1_std":0.48745034493065986,
794
- "naucs_at_1_diff1":0.6688901649531576,
795
- "naucs_at_3_max":0.16331168559176326,
796
- "naucs_at_3_std":-0.10227627073049722,
797
- "naucs_at_3_diff1":0.11304747268745052,
798
- "naucs_at_5_max":-0.16988833169699724,
799
- "naucs_at_5_std":-0.11738566845857755,
800
- "naucs_at_5_diff1":-0.1809970467861988,
801
- "naucs_at_10_max":-0.33338325513685335,
802
- "naucs_at_10_std":-0.025510902319384403,
803
- "naucs_at_10_diff1":-0.3463189316581034,
804
- "naucs_at_20_max":-0.4314950363511429,
805
- "naucs_at_20_std":-0.07814162322249632,
806
- "naucs_at_20_diff1":-0.3597465700560062,
807
- "naucs_at_50_max":-0.47238628583373166,
808
- "naucs_at_50_std":-0.11221281815013781,
809
- "naucs_at_50_diff1":-0.40715561083773455,
810
- "naucs_at_100_max":-0.5009545254403022,
811
- "naucs_at_100_std":-0.13543075269829394,
812
- "naucs_at_100_diff1":-0.42655217053366745
813
  },
814
- "vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual":{
815
- "ndcg_at_1":0.40789,
816
- "ndcg_at_3":0.45398,
817
- "ndcg_at_5":0.49414,
818
- "ndcg_at_10":0.55175,
819
- "ndcg_at_20":0.58156,
820
- "ndcg_at_50":0.60291,
821
- "ndcg_at_100":0.61991,
822
- "map_at_1":0.22474,
823
- "map_at_3":0.33583,
824
- "map_at_5":0.37953,
825
- "map_at_10":0.42123,
826
- "map_at_20":0.44047,
827
- "map_at_50":0.45011,
828
- "map_at_100":0.45529,
829
- "recall_at_1":0.22474,
830
- "recall_at_3":0.41185,
831
- "recall_at_5":0.53813,
832
- "recall_at_10":0.71024,
833
- "recall_at_20":0.80291,
834
- "recall_at_50":0.86707,
835
- "recall_at_100":0.91936,
836
- "precision_at_1":0.40789,
837
- "precision_at_3":0.30994,
838
- "precision_at_5":0.25175,
839
- "precision_at_10":0.17895,
840
- "precision_at_20":0.1125,
841
- "precision_at_50":0.05605,
842
- "precision_at_100":0.03316,
843
- "mrr_at_1":0.41228070175438597,
844
- "mrr_at_3":0.5460526315789472,
845
- "mrr_at_5":0.5730263157894736,
846
- "mrr_at_10":0.5878254664438874,
847
- "mrr_at_20":0.5892122375675007,
848
- "mrr_at_50":0.5898023340451821,
849
- "mrr_at_100":0.5898023340451821,
850
- "naucs_at_1_max":0.2357658534604348,
851
- "naucs_at_1_std":0.20546148190736413,
852
- "naucs_at_1_diff1":0.2942997782902726,
853
- "naucs_at_3_max":0.19477834554983517,
854
- "naucs_at_3_std":0.0901616305738152,
855
- "naucs_at_3_diff1":0.31211579977785125,
856
- "naucs_at_5_max":0.1270343582677278,
857
- "naucs_at_5_std":0.10429681691824569,
858
- "naucs_at_5_diff1":0.11650041665238493,
859
- "naucs_at_10_max":0.14045225679722562,
860
- "naucs_at_10_std":0.12904084502952987,
861
- "naucs_at_10_diff1":0.07244553717017796,
862
- "naucs_at_20_max":0.10806664996215463,
863
- "naucs_at_20_std":0.1554193282914579,
864
- "naucs_at_20_diff1":0.05276148208397267,
865
- "naucs_at_50_max":0.10921282506726279,
866
- "naucs_at_50_std":0.1603346667039166,
867
- "naucs_at_50_diff1":0.03503742864425776,
868
- "naucs_at_100_max":0.04641822985754839,
869
- "naucs_at_100_std":0.10747576298030817,
870
- "naucs_at_100_diff1":0.04796089754571697
871
  },
872
- "vidore/synthetic_axa_filtered_v1.0_multilingual":{
873
- "ndcg_at_1":0.63889,
874
- "ndcg_at_3":0.6012,
875
- "ndcg_at_5":0.58827,
876
- "ndcg_at_10":0.58895,
877
- "ndcg_at_20":0.62443,
878
- "ndcg_at_50":0.68019,
879
- "ndcg_at_100":0.70219,
880
- "map_at_1":0.30333,
881
- "map_at_3":0.39672,
882
- "map_at_5":0.43249,
883
- "map_at_10":0.46899,
884
- "map_at_20":0.4991,
885
- "map_at_50":0.52563,
886
- "map_at_100":0.5314,
887
- "recall_at_1":0.30333,
888
- "recall_at_3":0.46864,
889
- "recall_at_5":0.53553,
890
- "recall_at_10":0.6324,
891
- "recall_at_20":0.73382,
892
- "recall_at_50":0.88373,
893
- "recall_at_100":0.96868,
894
- "precision_at_1":0.63889,
895
- "precision_at_3":0.39815,
896
- "precision_at_5":0.31944,
897
- "precision_at_10":0.21528,
898
- "precision_at_20":0.14583,
899
- "precision_at_50":0.08056,
900
- "precision_at_100":0.045,
901
- "mrr_at_1":0.6388888888888888,
902
- "mrr_at_3":0.712962962962963,
903
- "mrr_at_5":0.7226851851851852,
904
- "mrr_at_10":0.7293375220458554,
905
- "mrr_at_20":0.7300319664902999,
906
- "mrr_at_50":0.7310105018438352,
907
- "mrr_at_100":0.731609030458644,
908
- "naucs_at_1_max":0.5446948235308462,
909
- "naucs_at_1_std":0.5753689576495256,
910
- "naucs_at_1_diff1":0.7063537335074642,
911
- "naucs_at_3_max":0.19358302792161025,
912
- "naucs_at_3_std":0.2382851719434907,
913
- "naucs_at_3_diff1":0.0695515629856817,
914
- "naucs_at_5_max":0.09842257096341021,
915
- "naucs_at_5_std":0.19689282025634797,
916
- "naucs_at_5_diff1":-0.0671135182203377,
917
- "naucs_at_10_max":-0.029979142509033184,
918
- "naucs_at_10_std":0.16524339827950454,
919
- "naucs_at_10_diff1":-0.17108930995116722,
920
- "naucs_at_20_max":-0.12064995451986389,
921
- "naucs_at_20_std":0.11922834681158871,
922
- "naucs_at_20_diff1":-0.23678549597263934,
923
- "naucs_at_50_max":-0.24090917683281962,
924
- "naucs_at_50_std":0.029789552466275192,
925
- "naucs_at_50_diff1":-0.3198962818502687,
926
- "naucs_at_100_max":-0.27973729295702227,
927
- "naucs_at_100_std":-0.02328206863515192,
928
- "naucs_at_100_diff1":-0.3372110499232704
929
  },
930
- "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual":{
931
- "ndcg_at_1":0.54531,
932
- "ndcg_at_3":0.56617,
933
- "ndcg_at_5":0.58574,
934
- "ndcg_at_10":0.61827,
935
- "ndcg_at_20":0.65025,
936
- "ndcg_at_50":0.67359,
937
- "ndcg_at_100":0.68484,
938
- "map_at_1":0.34753,
939
- "map_at_3":0.46224,
940
- "map_at_5":0.49892,
941
- "map_at_10":0.53012,
942
- "map_at_20":0.54677,
943
- "map_at_50":0.55485,
944
- "map_at_100":0.5575,
945
- "recall_at_1":0.34753,
946
- "recall_at_3":0.53074,
947
- "recall_at_5":0.61208,
948
- "recall_at_10":0.71018,
949
- "recall_at_20":0.80497,
950
- "recall_at_50":0.87594,
951
- "recall_at_100":0.9172,
952
- "precision_at_1":0.54531,
953
- "precision_at_3":0.35104,
954
- "precision_at_5":0.26437,
955
- "precision_at_10":0.16797,
956
- "precision_at_20":0.10125,
957
- "precision_at_50":0.04875,
958
- "precision_at_100":0.02677,
959
- "mrr_at_1":0.55,
960
- "mrr_at_3":0.646614583333333,
961
- "mrr_at_5":0.6649739583333327,
962
- "mrr_at_10":0.6720951140873008,
963
- "mrr_at_20":0.6750117754582119,
964
- "mrr_at_50":0.6760599947203341,
965
- "mrr_at_100":0.6761451306608197,
966
- "naucs_at_1_max":0.29928374487258724,
967
- "naucs_at_1_std":-0.12359275842271056,
968
- "naucs_at_1_diff1":0.4201913652071598,
969
- "naucs_at_3_max":0.18873193865163934,
970
- "naucs_at_3_std":-0.06245010840351605,
971
- "naucs_at_3_diff1":-0.00536703682885494,
972
- "naucs_at_5_max":0.14100421323862303,
973
- "naucs_at_5_std":-0.027020439430341922,
974
- "naucs_at_5_diff1":-0.1077482172997515,
975
- "naucs_at_10_max":0.09344561088695642,
976
- "naucs_at_10_std":0.037090812384825686,
977
- "naucs_at_10_diff1":-0.1671981024117422,
978
- "naucs_at_20_max":0.05221627904664171,
979
- "naucs_at_20_std":0.1282632066851335,
980
- "naucs_at_20_diff1":-0.20221964901502987,
981
- "naucs_at_50_max":0.013513375852412229,
982
- "naucs_at_50_std":0.19309861534269265,
983
- "naucs_at_50_diff1":-0.2256755414561015,
984
- "naucs_at_100_max":-0.019349328678396466,
985
- "naucs_at_100_std":0.1852766642822116,
986
- "naucs_at_100_diff1":-0.23520475571331936
987
  },
988
- "vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual":{
989
- "ndcg_at_1":0.6681,
990
- "ndcg_at_3":0.60424,
991
- "ndcg_at_5":0.5747,
992
- "ndcg_at_10":0.54872,
993
- "ndcg_at_20":0.56306,
994
- "ndcg_at_50":0.63179,
995
- "ndcg_at_100":0.67493,
996
- "map_at_1":0.12387,
997
- "map_at_3":0.19949,
998
- "map_at_5":0.24693,
999
- "map_at_10":0.30745,
1000
- "map_at_20":0.35555,
1001
- "map_at_50":0.41253,
1002
- "map_at_100":0.44204,
1003
- "recall_at_1":0.12387,
1004
- "recall_at_3":0.22225,
1005
- "recall_at_5":0.29097,
1006
- "recall_at_10":0.40934,
1007
- "recall_at_20":0.53643,
1008
- "recall_at_50":0.74545,
1009
- "recall_at_100":0.87651,
1010
- "precision_at_1":0.6681,
1011
- "precision_at_3":0.53736,
1012
- "precision_at_5":0.48448,
1013
- "precision_at_10":0.38405,
1014
- "precision_at_20":0.28578,
1015
- "precision_at_50":0.18707,
1016
- "precision_at_100":0.12509,
1017
- "mrr_at_1":0.6637931034482759,
1018
- "mrr_at_3":0.7399425287356322,
1019
- "mrr_at_5":0.7505028735632185,
1020
- "mrr_at_10":0.7577620415982483,
1021
- "mrr_at_20":0.7608588507644033,
1022
- "mrr_at_50":0.7619126745219256,
1023
- "mrr_at_100":0.7619126745219256,
1024
- "naucs_at_1_max":0.41911982711960527,
1025
- "naucs_at_1_std":0.2219319741427808,
1026
- "naucs_at_1_diff1":0.3323052156631965,
1027
- "naucs_at_3_max":0.395124099923616,
1028
- "naucs_at_3_std":0.2844189407584065,
1029
- "naucs_at_3_diff1":0.01968334915007435,
1030
- "naucs_at_5_max":0.4067543990404015,
1031
- "naucs_at_5_std":0.33349301021004324,
1032
- "naucs_at_5_diff1":-0.014244035459054444,
1033
- "naucs_at_10_max":0.3990475683526399,
1034
- "naucs_at_10_std":0.38841554010300666,
1035
- "naucs_at_10_diff1":-0.041117494510292424,
1036
- "naucs_at_20_max":0.3675017859948493,
1037
- "naucs_at_20_std":0.4157443195663025,
1038
- "naucs_at_20_diff1":-0.056415429353860895,
1039
- "naucs_at_50_max":0.32391982590254215,
1040
- "naucs_at_50_std":0.42853708930677303,
1041
- "naucs_at_50_diff1":-0.08088278760860802,
1042
- "naucs_at_100_max":0.31207698778205484,
1043
- "naucs_at_100_std":0.4190495880385969,
1044
- "naucs_at_100_diff1":-0.07513720852823234
1045
  },
1046
- "vidore/restaurant_esg_reports_beir":{
1047
- "ndcg_at_1":0.58333,
1048
- "ndcg_at_3":0.59295,
1049
- "ndcg_at_5":0.59847,
1050
- "ndcg_at_10":0.62705,
1051
- "ndcg_at_20":0.65711,
1052
- "ndcg_at_50":0.68372,
1053
- "ndcg_at_100":0.70126,
1054
- "map_at_1":0.4223,
1055
- "map_at_3":0.51429,
1056
- "map_at_5":0.53744,
1057
- "map_at_10":0.55815,
1058
- "map_at_20":0.56952,
1059
- "map_at_50":0.57719,
1060
- "map_at_100":0.58103,
1061
- "recall_at_1":0.4223,
1062
- "recall_at_3":0.56429,
1063
- "recall_at_5":0.62743,
1064
- "recall_at_10":0.71155,
1065
- "recall_at_20":0.81252,
1066
- "recall_at_50":0.89204,
1067
- "recall_at_100":0.97231,
1068
- "precision_at_1":0.59615,
1069
- "precision_at_3":0.33333,
1070
- "precision_at_5":0.22308,
1071
- "precision_at_10":0.13462,
1072
- "precision_at_20":0.07981,
1073
- "precision_at_50":0.04,
1074
- "precision_at_100":0.02269,
1075
- "mrr_at_1":0.5576923076923077,
1076
- "mrr_at_3":0.6474358974358974,
1077
- "mrr_at_5":0.6560897435897435,
1078
- "mrr_at_10":0.6660485347985349,
1079
- "mrr_at_20":0.6703807410538178,
1080
- "mrr_at_50":0.6726175245406014,
1081
- "mrr_at_100":0.6729276982378719,
1082
- "naucs_at_1_max":0.2932533009402019,
1083
- "naucs_at_1_std":0.1517545343059939,
1084
- "naucs_at_1_diff1":0.5522786237911489,
1085
- "naucs_at_3_max":0.15711366105316388,
1086
- "naucs_at_3_std":0.2842435852496209,
1087
- "naucs_at_3_diff1":0.17146359446607332,
1088
- "naucs_at_5_max":0.23419658811407862,
1089
- "naucs_at_5_std":0.3633012317767692,
1090
- "naucs_at_5_diff1":0.12100489678963466,
1091
- "naucs_at_10_max":0.047216835392144454,
1092
- "naucs_at_10_std":0.2537248335660501,
1093
- "naucs_at_10_diff1":-0.022798036346065944,
1094
- "naucs_at_20_max":-0.009656649432423618,
1095
- "naucs_at_20_std":0.18171843093206275,
1096
- "naucs_at_20_diff1":-0.15378487348591693,
1097
- "naucs_at_50_max":-0.06160339362487552,
1098
- "naucs_at_50_std":0.18732123220299826,
1099
- "naucs_at_50_diff1":-0.26637045721055785,
1100
- "naucs_at_100_max":-0.11600370147170294,
1101
- "naucs_at_100_std":0.15935039822386396,
1102
- "naucs_at_100_diff1":-0.292198998284397
1103
  }
1104
  }
 
1
  {
2
+ "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
3
+ "ndcg_at_1": 0.63125,
4
+ "ndcg_at_3": 0.62606,
5
+ "ndcg_at_5": 0.64036,
6
+ "ndcg_at_10": 0.67252,
7
+ "ndcg_at_20": 0.70051,
8
+ "ndcg_at_50": 0.7225,
9
+ "ndcg_at_100": 0.73342,
10
+ "map_at_1": 0.38694,
11
+ "map_at_3": 0.5157,
12
+ "map_at_5": 0.55286,
13
+ "map_at_10": 0.58663,
14
+ "map_at_20": 0.60199,
15
+ "map_at_50": 0.61092,
16
+ "map_at_100": 0.61334,
17
+ "recall_at_1": 0.38694,
18
+ "recall_at_3": 0.58442,
19
+ "recall_at_5": 0.65538,
20
+ "recall_at_10": 0.75502,
21
+ "recall_at_20": 0.83375,
22
+ "recall_at_50": 0.89435,
23
+ "recall_at_100": 0.93847,
24
+ "precision_at_1": 0.63125,
25
+ "precision_at_3": 0.37917,
26
+ "precision_at_5": 0.28375,
27
+ "precision_at_10": 0.17875,
28
+ "precision_at_20": 0.10594,
29
+ "precision_at_50": 0.05062,
30
+ "precision_at_100": 0.02756,
31
+ "mrr_at_1": 0.6375,
32
+ "mrr_at_3": 0.7270833333333332,
33
+ "mrr_at_5": 0.7339583333333333,
34
+ "mrr_at_10": 0.7424727182539682,
35
+ "mrr_at_20": 0.7446067387473636,
36
+ "mrr_at_50": 0.7449988719519969,
37
+ "mrr_at_100": 0.7452357796521399,
38
+ "naucs_at_1_max": 0.2860227930855084,
39
+ "naucs_at_1_std": -0.3138417441324,
40
+ "naucs_at_1_diff1": 0.42744397436023296,
41
+ "naucs_at_3_max": 0.1892512065375088,
42
+ "naucs_at_3_std": -0.09854623333300405,
43
+ "naucs_at_3_diff1": 0.00578348450006455,
44
+ "naucs_at_5_max": 0.0985916495531507,
45
+ "naucs_at_5_std": -0.06582623582128855,
46
+ "naucs_at_5_diff1": -0.08828438926991423,
47
+ "naucs_at_10_max": 0.0933821578304943,
48
+ "naucs_at_10_std": 0.08155017778485431,
49
+ "naucs_at_10_diff1": -0.17980682481558072,
50
+ "naucs_at_20_max": 0.0020201283703657888,
51
+ "naucs_at_20_std": 0.10903975278089359,
52
+ "naucs_at_20_diff1": -0.2369554821180032,
53
+ "naucs_at_50_max": -0.05388593736433463,
54
+ "naucs_at_50_std": 0.21602702406052268,
55
+ "naucs_at_50_diff1": -0.25488066393739356,
56
+ "naucs_at_100_max": -0.09001262910229582,
57
+ "naucs_at_100_std": 0.2278313121002944,
58
+ "naucs_at_100_diff1": -0.25651206108102814
59
  },
60
+ "vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
61
+ "ndcg_at_1": 0.7069,
62
+ "ndcg_at_3": 0.6531,
63
+ "ndcg_at_5": 0.63125,
64
+ "ndcg_at_10": 0.60817,
65
+ "ndcg_at_20": 0.61254,
66
+ "ndcg_at_50": 0.67937,
67
+ "ndcg_at_100": 0.7167,
68
+ "map_at_1": 0.12782,
69
+ "map_at_3": 0.21562,
70
+ "map_at_5": 0.28161,
71
+ "map_at_10": 0.35497,
72
+ "map_at_20": 0.40334,
73
+ "map_at_50": 0.46201,
74
+ "map_at_100": 0.49032,
75
+ "recall_at_1": 0.12782,
76
+ "recall_at_3": 0.23164,
77
+ "recall_at_5": 0.33225,
78
+ "recall_at_10": 0.47034,
79
+ "recall_at_20": 0.59047,
80
+ "recall_at_50": 0.78316,
81
+ "recall_at_100": 0.89751,
82
+ "precision_at_1": 0.7069,
83
+ "precision_at_3": 0.59195,
84
+ "precision_at_5": 0.54138,
85
+ "precision_at_10": 0.42759,
86
+ "precision_at_20": 0.30345,
87
+ "precision_at_50": 0.1969,
88
+ "precision_at_100": 0.12741,
89
+ "mrr_at_1": 0.7241379310344828,
90
+ "mrr_at_3": 0.7729885057471265,
91
+ "mrr_at_5": 0.7850574712643678,
92
+ "mrr_at_10": 0.8005199781061849,
93
+ "mrr_at_20": 0.8015975643130815,
94
+ "mrr_at_50": 0.8015975643130815,
95
+ "mrr_at_100": 0.8015975643130815,
96
+ "naucs_at_1_max": 0.5414377044487941,
97
+ "naucs_at_1_std": 0.2885423494902651,
98
+ "naucs_at_1_diff1": 0.4517408404026178,
99
+ "naucs_at_3_max": 0.5103699198828265,
100
+ "naucs_at_3_std": 0.34891966684046116,
101
+ "naucs_at_3_diff1": 0.1460156103430603,
102
+ "naucs_at_5_max": 0.5399440580636293,
103
+ "naucs_at_5_std": 0.3199440767695221,
104
+ "naucs_at_5_diff1": 0.18068785350199154,
105
+ "naucs_at_10_max": 0.5255610151091152,
106
+ "naucs_at_10_std": 0.3925916787135598,
107
+ "naucs_at_10_diff1": 0.14785999421779913,
108
+ "naucs_at_20_max": 0.4516553789306758,
109
+ "naucs_at_20_std": 0.4790296057633737,
110
+ "naucs_at_20_diff1": 0.14584034106403623,
111
+ "naucs_at_50_max": 0.34044111140425515,
112
+ "naucs_at_50_std": 0.4292008781133996,
113
+ "naucs_at_50_diff1": 0.0657235966934423,
114
+ "naucs_at_100_max": 0.296959342986135,
115
+ "naucs_at_100_std": 0.4138623681388592,
116
+ "naucs_at_100_diff1": 0.06422150196714925
117
  },
118
+ "vidore/synthetic_rse_restaurant_filtered_v1.0": {
119
+ "ndcg_at_1": 0.40351,
120
+ "ndcg_at_3": 0.47539,
121
+ "ndcg_at_5": 0.49152,
122
+ "ndcg_at_10": 0.553,
123
+ "ndcg_at_20": 0.59699,
124
+ "ndcg_at_50": 0.62258,
125
+ "ndcg_at_100": 0.63184,
126
+ "map_at_1": 0.2155,
127
+ "map_at_3": 0.35506,
128
+ "map_at_5": 0.38442,
129
+ "map_at_10": 0.43472,
130
+ "map_at_20": 0.45888,
131
+ "map_at_50": 0.46993,
132
+ "map_at_100": 0.47398,
133
+ "recall_at_1": 0.2155,
134
+ "recall_at_3": 0.46042,
135
+ "recall_at_5": 0.5245,
136
+ "recall_at_10": 0.69217,
137
+ "recall_at_20": 0.83089,
138
+ "recall_at_50": 0.9086,
139
+ "recall_at_100": 0.93039,
140
+ "precision_at_1": 0.40351,
141
+ "precision_at_3": 0.32749,
142
+ "precision_at_5": 0.25263,
143
+ "precision_at_10": 0.18421,
144
+ "precision_at_20": 0.12105,
145
+ "precision_at_50": 0.06105,
146
+ "precision_at_100": 0.03421,
147
+ "mrr_at_1": 0.40350877192982454,
148
+ "mrr_at_3": 0.5555555555555555,
149
+ "mrr_at_5": 0.5730994152046783,
150
+ "mrr_at_10": 0.5808966861598441,
151
+ "mrr_at_20": 0.586509202298676,
152
+ "mrr_at_50": 0.5877768876410641,
153
+ "mrr_at_100": 0.5877768876410641,
154
+ "naucs_at_1_max": 0.29648339825644304,
155
+ "naucs_at_1_std": 0.06641652874714649,
156
+ "naucs_at_1_diff1": 0.5045818569761475,
157
+ "naucs_at_3_max": 0.16818047225254976,
158
+ "naucs_at_3_std": 0.17028690578931582,
159
+ "naucs_at_3_diff1": 0.17461140240553258,
160
+ "naucs_at_5_max": 0.19459542279126757,
161
+ "naucs_at_5_std": 0.24823743512641647,
162
+ "naucs_at_5_diff1": 0.19749834680039569,
163
+ "naucs_at_10_max": 0.07835810840401428,
164
+ "naucs_at_10_std": 0.19882694823881913,
165
+ "naucs_at_10_diff1": 0.13857285069040404,
166
+ "naucs_at_20_max": -0.007433838800528796,
167
+ "naucs_at_20_std": 0.19538335810174498,
168
+ "naucs_at_20_diff1": 0.0012071916296247957,
169
+ "naucs_at_50_max": -0.0902754753027608,
170
+ "naucs_at_50_std": 0.1592772246389163,
171
+ "naucs_at_50_diff1": -0.02404431111361124,
172
+ "naucs_at_100_max": -0.12119070620203119,
173
+ "naucs_at_100_std": 0.13618966353380924,
174
+ "naucs_at_100_diff1": -0.04813882401945786
175
  },
176
+ "vidore/synthetic_axa_filtered_v1.0": {
177
+ "ndcg_at_1": 0.72222,
178
+ "ndcg_at_3": 0.69497,
179
+ "ndcg_at_5": 0.66273,
180
+ "ndcg_at_10": 0.67378,
181
+ "ndcg_at_20": 0.69012,
182
+ "ndcg_at_50": 0.75042,
183
+ "ndcg_at_100": 0.77219,
184
+ "map_at_1": 0.36488,
185
+ "map_at_3": 0.47229,
186
+ "map_at_5": 0.49718,
187
+ "map_at_10": 0.54558,
188
+ "map_at_20": 0.56749,
189
+ "map_at_50": 0.60107,
190
+ "map_at_100": 0.60562,
191
+ "recall_at_1": 0.36488,
192
+ "recall_at_3": 0.54457,
193
+ "recall_at_5": 0.58939,
194
+ "recall_at_10": 0.68972,
195
+ "recall_at_20": 0.74479,
196
+ "recall_at_50": 0.89156,
197
+ "recall_at_100": 0.98955,
198
+ "precision_at_1": 0.72222,
199
+ "precision_at_3": 0.44444,
200
+ "precision_at_5": 0.33333,
201
+ "precision_at_10": 0.24444,
202
+ "precision_at_20": 0.15,
203
+ "precision_at_50": 0.08667,
204
+ "precision_at_100": 0.04667,
205
+ "mrr_at_1": 0.7222222222222222,
206
+ "mrr_at_3": 0.7962962962962963,
207
+ "mrr_at_5": 0.8101851851851852,
208
+ "mrr_at_10": 0.8101851851851852,
209
+ "mrr_at_20": 0.8101851851851852,
210
+ "mrr_at_50": 0.8101851851851852,
211
+ "mrr_at_100": 0.8109903381642511,
212
+ "naucs_at_1_max": 0.19079787602675777,
213
+ "naucs_at_1_std": 0.03533531122016283,
214
+ "naucs_at_1_diff1": 0.632680674681619,
215
+ "naucs_at_3_max": -0.31385535499287276,
216
+ "naucs_at_3_std": -0.04655749634420289,
217
+ "naucs_at_3_diff1": 0.155475737963548,
218
+ "naucs_at_5_max": -0.2472297825482412,
219
+ "naucs_at_5_std": 0.03761412944004308,
220
+ "naucs_at_5_diff1": -0.10924664115489778,
221
+ "naucs_at_10_max": -0.37765403672620185,
222
+ "naucs_at_10_std": 0.002000186439662032,
223
+ "naucs_at_10_diff1": -0.14440595994296845,
224
+ "naucs_at_20_max": -0.4699503134091192,
225
+ "naucs_at_20_std": 0.025147844173298965,
226
+ "naucs_at_20_diff1": -0.16389645563321997,
227
+ "naucs_at_50_max": -0.5068940056618596,
228
+ "naucs_at_50_std": -0.019754043372479577,
229
+ "naucs_at_50_diff1": -0.16850642524469236,
230
+ "naucs_at_100_max": -0.4767515120911255,
231
+ "naucs_at_100_std": 0.015763234490211366,
232
+ "naucs_at_100_diff1": -0.20731314235125625
233
  },
234
+ "vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
235
+ "ndcg_at_1": 0.4386,
236
+ "ndcg_at_3": 0.48147,
237
+ "ndcg_at_5": 0.51908,
238
+ "ndcg_at_10": 0.57159,
239
+ "ndcg_at_20": 0.60702,
240
+ "ndcg_at_50": 0.63417,
241
+ "ndcg_at_100": 0.64411,
242
+ "map_at_1": 0.23507,
243
+ "map_at_3": 0.35761,
244
+ "map_at_5": 0.40257,
245
+ "map_at_10": 0.44822,
246
+ "map_at_20": 0.47031,
247
+ "map_at_50": 0.48211,
248
+ "map_at_100": 0.48628,
249
+ "recall_at_1": 0.23507,
250
+ "recall_at_3": 0.4487,
251
+ "recall_at_5": 0.56129,
252
+ "recall_at_10": 0.71123,
253
+ "recall_at_20": 0.82755,
254
+ "recall_at_50": 0.90956,
255
+ "recall_at_100": 0.93439,
256
+ "precision_at_1": 0.4386,
257
+ "precision_at_3": 0.32895,
258
+ "precision_at_5": 0.27018,
259
+ "precision_at_10": 0.18991,
260
+ "precision_at_20": 0.11974,
261
+ "precision_at_50": 0.06123,
262
+ "precision_at_100": 0.03447,
263
+ "mrr_at_1": 0.4517543859649123,
264
+ "mrr_at_3": 0.5796783625730992,
265
+ "mrr_at_5": 0.6033625730994151,
266
+ "mrr_at_10": 0.6098318713450293,
267
+ "mrr_at_20": 0.6143413495606139,
268
+ "mrr_at_50": 0.6150114081677309,
269
+ "mrr_at_100": 0.6150114081677309,
270
+ "naucs_at_1_max": 0.1695609084486461,
271
+ "naucs_at_1_std": 0.06302260506626338,
272
+ "naucs_at_1_diff1": 0.34368925726365046,
273
+ "naucs_at_3_max": 0.07022225247354692,
274
+ "naucs_at_3_std": 0.10306674677084651,
275
+ "naucs_at_3_diff1": 0.14995084571990153,
276
+ "naucs_at_5_max": 0.07354175839710718,
277
+ "naucs_at_5_std": 0.16198320276362924,
278
+ "naucs_at_5_diff1": 0.06343317549781861,
279
+ "naucs_at_10_max": 0.022729360196430883,
280
+ "naucs_at_10_std": 0.1654593087070378,
281
+ "naucs_at_10_diff1": 0.04276127936743703,
282
+ "naucs_at_20_max": -0.031554725803849416,
283
+ "naucs_at_20_std": 0.1300165212363859,
284
+ "naucs_at_20_diff1": 0.006021945700144339,
285
+ "naucs_at_50_max": -0.06313785005592049,
286
+ "naucs_at_50_std": 0.13595654225029755,
287
+ "naucs_at_50_diff1": 0.008224218691189635,
288
+ "naucs_at_100_max": -0.08372981904605119,
289
+ "naucs_at_100_std": 0.12653852178262695,
290
+ "naucs_at_100_diff1": -0.012169561956816101
291
  },
292
+ "vidore/synthetic_axa_filtered_v1.0_multilingual": {
293
+ "ndcg_at_1": 0.65278,
294
+ "ndcg_at_3": 0.61009,
295
+ "ndcg_at_5": 0.59294,
296
+ "ndcg_at_10": 0.61008,
297
+ "ndcg_at_20": 0.63877,
298
+ "ndcg_at_50": 0.69737,
299
+ "ndcg_at_100": 0.72109,
300
+ "map_at_1": 0.3313,
301
+ "map_at_3": 0.41787,
302
+ "map_at_5": 0.44884,
303
+ "map_at_10": 0.49024,
304
+ "map_at_20": 0.51424,
305
+ "map_at_50": 0.54276,
306
+ "map_at_100": 0.54899,
307
+ "recall_at_1": 0.3313,
308
+ "recall_at_3": 0.46646,
309
+ "recall_at_5": 0.52791,
310
+ "recall_at_10": 0.64008,
311
+ "recall_at_20": 0.73391,
312
+ "recall_at_50": 0.8845,
313
+ "recall_at_100": 0.97673,
314
+ "precision_at_1": 0.65278,
315
+ "precision_at_3": 0.39352,
316
+ "precision_at_5": 0.30833,
317
+ "precision_at_10": 0.22222,
318
+ "precision_at_20": 0.14028,
319
+ "precision_at_50": 0.08111,
320
+ "precision_at_100": 0.04556,
321
+ "mrr_at_1": 0.6527777777777778,
322
+ "mrr_at_3": 0.7175925925925928,
323
+ "mrr_at_5": 0.7307870370370372,
324
+ "mrr_at_10": 0.7397156084656086,
325
+ "mrr_at_20": 0.7417099104599107,
326
+ "mrr_at_50": 0.7421307858807862,
327
+ "mrr_at_100": 0.7426557166541077,
328
+ "naucs_at_1_max": 0.318303386786102,
329
+ "naucs_at_1_std": 0.23808943823013543,
330
+ "naucs_at_1_diff1": 0.6508710234226615,
331
+ "naucs_at_3_max": 0.13214248537450415,
332
+ "naucs_at_3_std": 0.16151259206691232,
333
+ "naucs_at_3_diff1": 0.22229988734788014,
334
+ "naucs_at_5_max": 0.05889008903334795,
335
+ "naucs_at_5_std": 0.11423669671153379,
336
+ "naucs_at_5_diff1": 0.11548423013320717,
337
+ "naucs_at_10_max": -0.037397142604183475,
338
+ "naucs_at_10_std": 0.09416088185519944,
339
+ "naucs_at_10_diff1": 0.008856567275955608,
340
+ "naucs_at_20_max": -0.11441594604958465,
341
+ "naucs_at_20_std": 0.04973867186679883,
342
+ "naucs_at_20_diff1": -0.05320557709786541,
343
+ "naucs_at_50_max": -0.18138441233720995,
344
+ "naucs_at_50_std": 0.010825689422469654,
345
+ "naucs_at_50_diff1": -0.10510638193999315,
346
+ "naucs_at_100_max": -0.202379290531666,
347
+ "naucs_at_100_std": -0.014979683943287803,
348
+ "naucs_at_100_diff1": -0.14558601228430124
349
  },
350
+ "vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
351
+ "ndcg_at_1": 0.57344,
352
+ "ndcg_at_3": 0.59236,
353
+ "ndcg_at_5": 0.61157,
354
+ "ndcg_at_10": 0.63866,
355
+ "ndcg_at_20": 0.66879,
356
+ "ndcg_at_50": 0.69522,
357
+ "ndcg_at_100": 0.70444,
358
+ "map_at_1": 0.36007,
359
+ "map_at_3": 0.48525,
360
+ "map_at_5": 0.52371,
361
+ "map_at_10": 0.5533,
362
+ "map_at_20": 0.5688,
363
+ "map_at_50": 0.57892,
364
+ "map_at_100": 0.58096,
365
+ "recall_at_1": 0.36007,
366
+ "recall_at_3": 0.55859,
367
+ "recall_at_5": 0.63871,
368
+ "recall_at_10": 0.7243,
369
+ "recall_at_20": 0.81097,
370
+ "recall_at_50": 0.88961,
371
+ "recall_at_100": 0.92417,
372
+ "precision_at_1": 0.57344,
373
+ "precision_at_3": 0.36302,
374
+ "precision_at_5": 0.27469,
375
+ "precision_at_10": 0.17016,
376
+ "precision_at_20": 0.10219,
377
+ "precision_at_50": 0.04997,
378
+ "precision_at_100": 0.02702,
379
+ "mrr_at_1": 0.5796875,
380
+ "mrr_at_3": 0.680729166666666,
381
+ "mrr_at_5": 0.6924479166666659,
382
+ "mrr_at_10": 0.6992057291666662,
383
+ "mrr_at_20": 0.7025276038138841,
384
+ "mrr_at_50": 0.7032994002394296,
385
+ "mrr_at_100": 0.7035081912324784,
386
+ "naucs_at_1_max": 0.2618446848882775,
387
+ "naucs_at_1_std": -0.170161905683693,
388
+ "naucs_at_1_diff1": 0.4753067384546821,
389
+ "naucs_at_3_max": 0.17827521235144483,
390
+ "naucs_at_3_std": -0.060198662170649925,
391
+ "naucs_at_3_diff1": 0.05418513753300305,
392
+ "naucs_at_5_max": 0.08757447272019533,
393
+ "naucs_at_5_std": -0.049911565737325504,
394
+ "naucs_at_5_diff1": -0.04360643940712858,
395
+ "naucs_at_10_max": 0.0797198239661374,
396
+ "naucs_at_10_std": 0.03949138307521818,
397
+ "naucs_at_10_diff1": -0.09762488661941034,
398
+ "naucs_at_20_max": 0.01961040143553897,
399
+ "naucs_at_20_std": 0.10087633582361409,
400
+ "naucs_at_20_diff1": -0.17144901884144179,
401
+ "naucs_at_50_max": -0.02239975053336602,
402
+ "naucs_at_50_std": 0.1699503781904292,
403
+ "naucs_at_50_diff1": -0.1722611533882454,
404
+ "naucs_at_100_max": -0.04512586039808127,
405
+ "naucs_at_100_std": 0.17386318414141583,
406
+ "naucs_at_100_diff1": -0.1871247841007667
407
  },
408
+ "vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
409
+ "ndcg_at_1": 0.66379,
410
+ "ndcg_at_3": 0.60737,
411
+ "ndcg_at_5": 0.57718,
412
+ "ndcg_at_10": 0.55599,
413
+ "ndcg_at_20": 0.57988,
414
+ "ndcg_at_50": 0.64999,
415
+ "ndcg_at_100": 0.68674,
416
+ "map_at_1": 0.12281,
417
+ "map_at_3": 0.20294,
418
+ "map_at_5": 0.25378,
419
+ "map_at_10": 0.31487,
420
+ "map_at_20": 0.36947,
421
+ "map_at_50": 0.42823,
422
+ "map_at_100": 0.45448,
423
+ "recall_at_1": 0.12281,
424
+ "recall_at_3": 0.2256,
425
+ "recall_at_5": 0.30659,
426
+ "recall_at_10": 0.42269,
427
+ "recall_at_20": 0.56687,
428
+ "recall_at_50": 0.76718,
429
+ "recall_at_100": 0.88492,
430
+ "precision_at_1": 0.66379,
431
+ "precision_at_3": 0.5431,
432
+ "precision_at_5": 0.48362,
433
+ "precision_at_10": 0.38836,
434
+ "precision_at_20": 0.29591,
435
+ "precision_at_50": 0.19345,
436
+ "precision_at_100": 0.12414,
437
+ "mrr_at_1": 0.6767241379310345,
438
+ "mrr_at_3": 0.7399425287356323,
439
+ "mrr_at_5": 0.7548132183908046,
440
+ "mrr_at_10": 0.7652247536945812,
441
+ "mrr_at_20": 0.7667345585449032,
442
+ "mrr_at_50": 0.7675009343641154,
443
+ "mrr_at_100": 0.7675472821579604,
444
+ "naucs_at_1_max": 0.3427760433833983,
445
+ "naucs_at_1_std": 0.17486041852136283,
446
+ "naucs_at_1_diff1": 0.3493033195022897,
447
+ "naucs_at_3_max": 0.29896675454636334,
448
+ "naucs_at_3_std": 0.2241328326881254,
449
+ "naucs_at_3_diff1": 0.07681853603265505,
450
+ "naucs_at_5_max": 0.3541130170379229,
451
+ "naucs_at_5_std": 0.27779731381034506,
452
+ "naucs_at_5_diff1": 0.04428119389439255,
453
+ "naucs_at_10_max": 0.3161718142368522,
454
+ "naucs_at_10_std": 0.2654928526689307,
455
+ "naucs_at_10_diff1": 0.014100490157475373,
456
+ "naucs_at_20_max": 0.2499680124975916,
457
+ "naucs_at_20_std": 0.2633550881217926,
458
+ "naucs_at_20_diff1": -0.02686064189005896,
459
+ "naucs_at_50_max": 0.1951500660706873,
460
+ "naucs_at_50_std": 0.23487608842256993,
461
+ "naucs_at_50_diff1": -0.0871206335340013,
462
+ "naucs_at_100_max": 0.16510434929270115,
463
+ "naucs_at_100_std": 0.21054693222984838,
464
+ "naucs_at_100_diff1": -0.10274771435027014
465
  },
466
+ "vidore/restaurant_esg_reports_beir": {
467
+ "ndcg_at_1": 0.64103,
468
+ "ndcg_at_3": 0.62507,
469
+ "ndcg_at_5": 0.65665,
470
+ "ndcg_at_10": 0.67232,
471
+ "ndcg_at_20": 0.69863,
472
+ "ndcg_at_50": 0.72704,
473
+ "ndcg_at_100": 0.73746,
474
+ "map_at_1": 0.44583,
475
+ "map_at_3": 0.54321,
476
+ "map_at_5": 0.58695,
477
+ "map_at_10": 0.60061,
478
+ "map_at_20": 0.61379,
479
+ "map_at_50": 0.62209,
480
+ "map_at_100": 0.62409,
481
+ "recall_at_1": 0.44583,
482
+ "recall_at_3": 0.60335,
483
+ "recall_at_5": 0.69232,
484
+ "recall_at_10": 0.74186,
485
+ "recall_at_20": 0.81674,
486
+ "recall_at_50": 0.92301,
487
+ "recall_at_100": 0.9696,
488
+ "precision_at_1": 0.65385,
489
+ "precision_at_3": 0.33333,
490
+ "precision_at_5": 0.25385,
491
+ "precision_at_10": 0.14231,
492
+ "precision_at_20": 0.08558,
493
+ "precision_at_50": 0.04154,
494
+ "precision_at_100": 0.0225,
495
+ "mrr_at_1": 0.6538461538461539,
496
+ "mrr_at_3": 0.7211538461538461,
497
+ "mrr_at_5": 0.7288461538461538,
498
+ "mrr_at_10": 0.736935286935287,
499
+ "mrr_at_20": 0.738003663003663,
500
+ "mrr_at_50": 0.739894529945878,
501
+ "mrr_at_100": 0.7402260949326155,
502
+ "naucs_at_1_max": 0.18675644205833766,
503
+ "naucs_at_1_std": 0.12089377306440403,
504
+ "naucs_at_1_diff1": 0.23180938958754124,
505
+ "naucs_at_3_max": 0.1337570930336171,
506
+ "naucs_at_3_std": 0.2424272064488133,
507
+ "naucs_at_3_diff1": -0.21025078361612204,
508
+ "naucs_at_5_max": 0.005149088005913239,
509
+ "naucs_at_5_std": 0.30173104877190665,
510
+ "naucs_at_5_diff1": -0.3297309037027529,
511
+ "naucs_at_10_max": 0.058274590610789254,
512
+ "naucs_at_10_std": 0.32737391815331685,
513
+ "naucs_at_10_diff1": -0.390552006407966,
514
+ "naucs_at_20_max": -0.04962516887611918,
515
+ "naucs_at_20_std": 0.33292517052358606,
516
+ "naucs_at_20_diff1": -0.435159500418056,
517
+ "naucs_at_50_max": -0.0972258593819507,
518
+ "naucs_at_50_std": 0.3213589716904649,
519
+ "naucs_at_50_diff1": -0.40791385861358653,
520
+ "naucs_at_100_max": -0.16245636826248977,
521
+ "naucs_at_100_std": 0.261806614637912,
522
+ "naucs_at_100_diff1": -0.4069117709772787
523
  },
524
+ "vidore/arxivqa_test_subsampled": {
525
+ "ndcg_at_1": 0.82,
526
+ "ndcg_at_3": 0.87317,
527
+ "ndcg_at_5": 0.88134,
528
+ "ndcg_at_10": 0.88917,
529
+ "ndcg_at_20": 0.89577,
530
+ "ndcg_at_50": 0.89856,
531
+ "ndcg_at_100": 0.89953,
532
+ "map_at_1": 0.82,
533
+ "map_at_3": 0.861,
534
+ "map_at_5": 0.8655,
535
+ "map_at_10": 0.86878,
536
+ "map_at_20": 0.8706,
537
+ "map_at_50": 0.87105,
538
+ "map_at_100": 0.87113,
539
+ "recall_at_1": 0.82,
540
+ "recall_at_3": 0.908,
541
+ "recall_at_5": 0.928,
542
+ "recall_at_10": 0.952,
543
+ "recall_at_20": 0.978,
544
+ "recall_at_50": 0.992,
545
+ "recall_at_100": 0.998,
546
+ "precision_at_1": 0.82,
547
+ "precision_at_3": 0.30267,
548
+ "precision_at_5": 0.1856,
549
+ "precision_at_10": 0.0952,
550
+ "precision_at_20": 0.0489,
551
+ "precision_at_50": 0.01984,
552
+ "precision_at_100": 0.00998,
553
+ "mrr_at_1": 0.818,
554
+ "mrr_at_3": 0.8596666666666666,
555
+ "mrr_at_5": 0.8641666666666665,
556
+ "mrr_at_10": 0.8674912698412698,
557
+ "mrr_at_20": 0.8692320429570428,
558
+ "mrr_at_50": 0.8697783157643562,
559
+ "mrr_at_100": 0.8698595552455958,
560
+ "naucs_at_1_max": 0.8542625839850205,
561
+ "naucs_at_1_std": -0.15451591584976296,
562
+ "naucs_at_1_diff1": 0.9423945368432642,
563
+ "naucs_at_3_max": 0.8243413307351934,
564
+ "naucs_at_3_std": -0.019983355661106324,
565
+ "naucs_at_3_diff1": 0.8796330126253413,
566
+ "naucs_at_5_max": 0.8361733582321816,
567
+ "naucs_at_5_std": 0.04758014316837583,
568
+ "naucs_at_5_diff1": 0.8694755680049819,
569
+ "naucs_at_10_max": 0.8481948334889503,
570
+ "naucs_at_10_std": 0.00797541238717203,
571
+ "naucs_at_10_diff1": 0.8792989417989403,
572
+ "naucs_at_20_max": 0.9123588829471215,
573
+ "naucs_at_20_std": 0.13352007469653804,
574
+ "naucs_at_20_diff1": 0.9019607843137273,
575
+ "naucs_at_50_max": 0.9673202614378978,
576
+ "naucs_at_50_std": 0.24684873949577324,
577
+ "naucs_at_50_diff1": 0.9305555555555584,
578
+ "naucs_at_100_max": 1.0,
579
+ "naucs_at_100_std": 1.0,
580
+ "naucs_at_100_diff1": 1.0
581
  },
582
+ "vidore/docvqa_test_subsampled": {
583
+ "ndcg_at_1": 0.51663,
584
+ "ndcg_at_3": 0.59278,
585
+ "ndcg_at_5": 0.61529,
586
+ "ndcg_at_10": 0.63354,
587
+ "ndcg_at_20": 0.64688,
588
+ "ndcg_at_50": 0.66214,
589
+ "ndcg_at_100": 0.67157,
590
+ "map_at_1": 0.51663,
591
+ "map_at_3": 0.57391,
592
+ "map_at_5": 0.58622,
593
+ "map_at_10": 0.59393,
594
+ "map_at_20": 0.59753,
595
+ "map_at_50": 0.60011,
596
+ "map_at_100": 0.60096,
597
+ "recall_at_1": 0.51663,
598
+ "recall_at_3": 0.64745,
599
+ "recall_at_5": 0.70288,
600
+ "recall_at_10": 0.75831,
601
+ "recall_at_20": 0.81153,
602
+ "recall_at_50": 0.88692,
603
+ "recall_at_100": 0.94457,
604
+ "precision_at_1": 0.51663,
605
+ "precision_at_3": 0.21582,
606
+ "precision_at_5": 0.14058,
607
+ "precision_at_10": 0.07583,
608
+ "precision_at_20": 0.04058,
609
+ "precision_at_50": 0.01774,
610
+ "precision_at_100": 0.00945,
611
+ "mrr_at_1": 0.5144124168514412,
612
+ "mrr_at_3": 0.5731707317073172,
613
+ "mrr_at_5": 0.586031042128603,
614
+ "mrr_at_10": 0.5933419561468339,
615
+ "mrr_at_20": 0.5967957449683643,
616
+ "mrr_at_50": 0.599471176191027,
617
+ "mrr_at_100": 0.600328115684025,
618
+ "naucs_at_1_max": 0.6741589793839163,
619
+ "naucs_at_1_std": -0.16205001702916214,
620
+ "naucs_at_1_diff1": 0.8162930079294569,
621
+ "naucs_at_3_max": 0.7465129968490366,
622
+ "naucs_at_3_std": -0.09544436940181997,
623
+ "naucs_at_3_diff1": 0.7350663423580653,
624
+ "naucs_at_5_max": 0.7629182852125305,
625
+ "naucs_at_5_std": -0.050579687432907604,
626
+ "naucs_at_5_diff1": 0.7012350138123477,
627
+ "naucs_at_10_max": 0.7889385100226093,
628
+ "naucs_at_10_std": 0.04757918573005526,
629
+ "naucs_at_10_diff1": 0.6915024085662332,
630
+ "naucs_at_20_max": 0.8147748548808955,
631
+ "naucs_at_20_std": 0.10152398884541157,
632
+ "naucs_at_20_diff1": 0.704970590799652,
633
+ "naucs_at_50_max": 0.8657229702927914,
634
+ "naucs_at_50_std": 0.3246550245384335,
635
+ "naucs_at_50_diff1": 0.6989609170252572,
636
+ "naucs_at_100_max": 0.9055488370856275,
637
+ "naucs_at_100_std": 0.49971793394423536,
638
+ "naucs_at_100_diff1": 0.6936703826495957
639
  },
640
+ "vidore/infovqa_test_subsampled": {
641
+ "ndcg_at_1": 0.86842,
642
+ "ndcg_at_3": 0.90307,
643
+ "ndcg_at_5": 0.91204,
644
+ "ndcg_at_10": 0.91773,
645
+ "ndcg_at_20": 0.92031,
646
+ "ndcg_at_50": 0.92201,
647
+ "ndcg_at_100": 0.92265,
648
+ "map_at_1": 0.86842,
649
+ "map_at_3": 0.89474,
650
+ "map_at_5": 0.8996,
651
+ "map_at_10": 0.90182,
652
+ "map_at_20": 0.90254,
653
+ "map_at_50": 0.90285,
654
+ "map_at_100": 0.90291,
655
+ "recall_at_1": 0.86842,
656
+ "recall_at_3": 0.92713,
657
+ "recall_at_5": 0.94939,
658
+ "recall_at_10": 0.96761,
659
+ "recall_at_20": 0.97773,
660
+ "recall_at_50": 0.98583,
661
+ "recall_at_100": 0.98988,
662
+ "precision_at_1": 0.86842,
663
+ "precision_at_3": 0.30904,
664
+ "precision_at_5": 0.18988,
665
+ "precision_at_10": 0.09676,
666
+ "precision_at_20": 0.04889,
667
+ "precision_at_50": 0.01972,
668
+ "precision_at_100": 0.0099,
669
+ "mrr_at_1": 0.868421052631579,
670
+ "mrr_at_3": 0.894736842105263,
671
+ "mrr_at_5": 0.8996963562753034,
672
+ "mrr_at_10": 0.9018740762161812,
673
+ "mrr_at_20": 0.9025973885538661,
674
+ "mrr_at_50": 0.9029005381313663,
675
+ "mrr_at_100": 0.9029517941275169,
676
+ "naucs_at_1_max": 0.6108584962344086,
677
+ "naucs_at_1_std": -0.1359018313249994,
678
+ "naucs_at_1_diff1": 0.9136811065149164,
679
+ "naucs_at_3_max": 0.6840687823130331,
680
+ "naucs_at_3_std": 0.03370197684645164,
681
+ "naucs_at_3_diff1": 0.886059733600837,
682
+ "naucs_at_5_max": 0.7765209527928315,
683
+ "naucs_at_5_std": 0.2228524148946178,
684
+ "naucs_at_5_diff1": 0.8620463071981626,
685
+ "naucs_at_10_max": 0.8392814749886633,
686
+ "naucs_at_10_std": 0.5798638053062866,
687
+ "naucs_at_10_diff1": 0.8728108205086554,
688
+ "naucs_at_20_max": 1.0,
689
+ "naucs_at_20_std": 0.8268704165639359,
690
+ "naucs_at_20_diff1": 0.8986141894622774,
691
+ "naucs_at_50_max": 1.0,
692
+ "naucs_at_50_std": 0.8102686931758233,
693
+ "naucs_at_50_diff1": 0.8593367911642417,
694
+ "naucs_at_100_max": 1.0,
695
+ "naucs_at_100_std": 0.7899231179977639,
696
+ "naucs_at_100_diff1": 0.9183327616354471
697
  },
698
+ "vidore/tabfquad_test_subsampled": {
699
+ "ndcg_at_1": 0.89286,
700
+ "ndcg_at_3": 0.92836,
701
+ "ndcg_at_5": 0.93112,
702
+ "ndcg_at_10": 0.93804,
703
+ "ndcg_at_20": 0.94089,
704
+ "ndcg_at_50": 0.94232,
705
+ "ndcg_at_100": 0.94232,
706
+ "map_at_1": 0.89286,
707
+ "map_at_3": 0.91964,
708
+ "map_at_5": 0.92107,
709
+ "map_at_10": 0.92391,
710
+ "map_at_20": 0.92477,
711
+ "map_at_50": 0.925,
712
+ "map_at_100": 0.925,
713
+ "recall_at_1": 0.89286,
714
+ "recall_at_3": 0.95357,
715
+ "recall_at_5": 0.96071,
716
+ "recall_at_10": 0.98214,
717
+ "recall_at_20": 0.99286,
718
+ "recall_at_50": 1.0,
719
+ "recall_at_100": 1.0,
720
+ "precision_at_1": 0.89286,
721
+ "precision_at_3": 0.31786,
722
+ "precision_at_5": 0.19214,
723
+ "precision_at_10": 0.09821,
724
+ "precision_at_20": 0.04964,
725
+ "precision_at_50": 0.02,
726
+ "precision_at_100": 0.01,
727
+ "mrr_at_1": 0.8928571428571429,
728
+ "mrr_at_3": 0.9196428571428571,
729
+ "mrr_at_5": 0.9210714285714285,
730
+ "mrr_at_10": 0.9239129818594106,
731
+ "mrr_at_20": 0.9247733714698002,
732
+ "mrr_at_50": 0.9250078037042323,
733
+ "mrr_at_100": 0.9250078037042323,
734
+ "naucs_at_1_max": 0.8354945054945048,
735
+ "naucs_at_1_std": 0.37345368916797433,
736
+ "naucs_at_1_diff1": 0.9218210361067499,
737
+ "naucs_at_3_max": 0.9657042304101127,
738
+ "naucs_at_3_std": 0.7062773827479698,
739
+ "naucs_at_3_diff1": 0.9396681749622927,
740
+ "naucs_at_5_max": 0.9594686359392222,
741
+ "naucs_at_5_std": 0.6647568118156384,
742
+ "naucs_at_5_diff1": 0.9286987522281656,
743
+ "naucs_at_10_max": 1.0,
744
+ "naucs_at_10_std": 0.9738562091503306,
745
+ "naucs_at_10_diff1": 0.9477124183006519,
746
+ "naucs_at_20_max": 1.0,
747
+ "naucs_at_20_std": 1.0,
748
+ "naucs_at_20_diff1": 1.0,
749
+ "naucs_at_50_max": 1.0,
750
+ "naucs_at_50_std": 1.0,
751
+ "naucs_at_50_diff1": 1.0,
752
+ "naucs_at_100_max": 1.0,
753
+ "naucs_at_100_std": 1.0,
754
+ "naucs_at_100_diff1": 1.0
755
  },
756
+ "vidore/tatdqa_test": {
757
+ "ndcg_at_1": 0.60571,
758
+ "ndcg_at_3": 0.71371,
759
+ "ndcg_at_5": 0.73981,
760
+ "ndcg_at_10": 0.7601,
761
+ "ndcg_at_20": 0.76893,
762
+ "ndcg_at_50": 0.7733,
763
+ "ndcg_at_100": 0.77517,
764
+ "map_at_1": 0.60571,
765
+ "map_at_3": 0.68702,
766
+ "map_at_5": 0.70154,
767
+ "map_at_10": 0.71006,
768
+ "map_at_20": 0.71253,
769
+ "map_at_50": 0.71329,
770
+ "map_at_100": 0.71345,
771
+ "recall_at_1": 0.60571,
772
+ "recall_at_3": 0.79101,
773
+ "recall_at_5": 0.85419,
774
+ "recall_at_10": 0.91616,
775
+ "recall_at_20": 0.95079,
776
+ "recall_at_50": 0.97205,
777
+ "recall_at_100": 0.9836,
778
+ "precision_at_1": 0.60571,
779
+ "precision_at_3": 0.26367,
780
+ "precision_at_5": 0.17084,
781
+ "precision_at_10": 0.09162,
782
+ "precision_at_20": 0.04754,
783
+ "precision_at_50": 0.01944,
784
+ "precision_at_100": 0.00984,
785
+ "mrr_at_1": 0.6038882138517618,
786
+ "mrr_at_3": 0.6857027136492516,
787
+ "mrr_at_5": 0.7003138922640758,
788
+ "mrr_at_10": 0.7090893749156212,
789
+ "mrr_at_20": 0.7114126192954364,
790
+ "mrr_at_50": 0.7121742514967643,
791
+ "mrr_at_100": 0.7123364657648046,
792
+ "naucs_at_1_max": 0.3821214020038102,
793
+ "naucs_at_1_std": -0.13489407631885159,
794
+ "naucs_at_1_diff1": 0.7298383859421139,
795
+ "naucs_at_3_max": 0.45115702284602416,
796
+ "naucs_at_3_std": -0.04154958812127681,
797
+ "naucs_at_3_diff1": 0.6171010959328003,
798
+ "naucs_at_5_max": 0.4834741295717716,
799
+ "naucs_at_5_std": -0.03652161720284896,
800
+ "naucs_at_5_diff1": 0.6133480640518033,
801
+ "naucs_at_10_max": 0.5818884435678058,
802
+ "naucs_at_10_std": 0.1493431453981439,
803
+ "naucs_at_10_diff1": 0.6125109504507562,
804
+ "naucs_at_20_max": 0.7030343359941152,
805
+ "naucs_at_20_std": 0.3539243062200548,
806
+ "naucs_at_20_diff1": 0.6751362244435348,
807
+ "naucs_at_50_max": 0.7344845360513886,
808
+ "naucs_at_50_std": 0.5609137914009904,
809
+ "naucs_at_50_diff1": 0.6435577411690651,
810
+ "naucs_at_100_max": 0.7291790977931831,
811
+ "naucs_at_100_std": 0.7412505638179597,
812
+ "naucs_at_100_diff1": 0.6088543824874393
813
  },
814
+ "vidore/shiftproject_test": {
815
+ "ndcg_at_1": 0.74,
816
+ "ndcg_at_3": 0.85333,
817
+ "ndcg_at_5": 0.85764,
818
+ "ndcg_at_10": 0.87455,
819
+ "ndcg_at_20": 0.8769,
820
+ "ndcg_at_50": 0.8769,
821
+ "ndcg_at_100": 0.8769,
822
+ "map_at_1": 0.74,
823
+ "map_at_3": 0.82667,
824
+ "map_at_5": 0.82917,
825
+ "map_at_10": 0.8366,
826
+ "map_at_20": 0.83715,
827
+ "map_at_50": 0.83715,
828
+ "map_at_100": 0.83715,
829
+ "recall_at_1": 0.74,
830
+ "recall_at_3": 0.93,
831
+ "recall_at_5": 0.94,
832
+ "recall_at_10": 0.99,
833
+ "recall_at_20": 1.0,
834
+ "recall_at_50": 1.0,
835
+ "recall_at_100": 1.0,
836
+ "precision_at_1": 0.74,
837
+ "precision_at_3": 0.31,
838
+ "precision_at_5": 0.188,
839
+ "precision_at_10": 0.099,
840
+ "precision_at_20": 0.05,
841
+ "precision_at_50": 0.02,
842
+ "precision_at_100": 0.01,
843
+ "mrr_at_1": 0.74,
844
+ "mrr_at_3": 0.8266666666666665,
845
+ "mrr_at_5": 0.8291666666666666,
846
+ "mrr_at_10": 0.8365952380952381,
847
+ "mrr_at_20": 0.8371834733893557,
848
+ "mrr_at_50": 0.8371834733893557,
849
+ "mrr_at_100": 0.8371834733893557,
850
+ "naucs_at_1_max": 0.36659097360204357,
851
+ "naucs_at_1_std": -0.13924820566886958,
852
+ "naucs_at_1_diff1": 0.7847208142411088,
853
+ "naucs_at_3_max": 0.7129518474056293,
854
+ "naucs_at_3_std": -0.039482459650526366,
855
+ "naucs_at_3_diff1": 0.8102574363078549,
856
+ "naucs_at_5_max": 0.8603330220977291,
857
+ "naucs_at_5_std": 0.24393090569561146,
858
+ "naucs_at_5_diff1": 0.8004201680672299,
859
+ "naucs_at_10_max": 0.5541549953314738,
860
+ "naucs_at_10_std": 0.12278244631185926,
861
+ "naucs_at_10_diff1": 0.35807656395891135,
862
+ "naucs_at_20_max": 1.0,
863
+ "naucs_at_20_std": 1.0,
864
+ "naucs_at_20_diff1": 1.0,
865
+ "naucs_at_50_max": null,
866
+ "naucs_at_50_std": null,
867
+ "naucs_at_50_diff1": null,
868
+ "naucs_at_100_max": null,
869
+ "naucs_at_100_std": null,
870
+ "naucs_at_100_diff1": null
871
  },
872
+ "vidore/syntheticDocQA_artificial_intelligence_test": {
873
+ "ndcg_at_1": 0.96,
874
+ "ndcg_at_3": 0.98393,
875
+ "ndcg_at_5": 0.98393,
876
+ "ndcg_at_10": 0.98393,
877
+ "ndcg_at_20": 0.98393,
878
+ "ndcg_at_50": 0.98393,
879
+ "ndcg_at_100": 0.98393,
880
+ "map_at_1": 0.96,
881
+ "map_at_3": 0.97833,
882
+ "map_at_5": 0.97833,
883
+ "map_at_10": 0.97833,
884
+ "map_at_20": 0.97833,
885
+ "map_at_50": 0.97833,
886
+ "map_at_100": 0.97833,
887
+ "recall_at_1": 0.96,
888
+ "recall_at_3": 1.0,
889
+ "recall_at_5": 1.0,
890
+ "recall_at_10": 1.0,
891
+ "recall_at_20": 1.0,
892
+ "recall_at_50": 1.0,
893
+ "recall_at_100": 1.0,
894
+ "precision_at_1": 0.96,
895
+ "precision_at_3": 0.33333,
896
+ "precision_at_5": 0.2,
897
+ "precision_at_10": 0.1,
898
+ "precision_at_20": 0.05,
899
+ "precision_at_50": 0.02,
900
+ "precision_at_100": 0.01,
901
+ "mrr_at_1": 0.96,
902
+ "mrr_at_3": 0.9783333333333333,
903
+ "mrr_at_5": 0.9783333333333333,
904
+ "mrr_at_10": 0.9783333333333333,
905
+ "mrr_at_20": 0.9783333333333333,
906
+ "mrr_at_50": 0.9783333333333333,
907
+ "mrr_at_100": 0.9783333333333333,
908
+ "naucs_at_1_max": 0.7373949579831944,
909
+ "naucs_at_1_std": -0.32784780578897976,
910
+ "naucs_at_1_diff1": 0.9346405228758167,
911
+ "naucs_at_3_max": 1.0,
912
+ "naucs_at_3_std": 1.0,
913
+ "naucs_at_3_diff1": 1.0,
914
+ "naucs_at_5_max": 1.0,
915
+ "naucs_at_5_std": 1.0,
916
+ "naucs_at_5_diff1": 1.0,
917
+ "naucs_at_10_max": 1.0,
918
+ "naucs_at_10_std": 1.0,
919
+ "naucs_at_10_diff1": 1.0,
920
+ "naucs_at_20_max": 1.0,
921
+ "naucs_at_20_std": 1.0,
922
+ "naucs_at_20_diff1": 1.0,
923
+ "naucs_at_50_max": null,
924
+ "naucs_at_50_std": null,
925
+ "naucs_at_50_diff1": null,
926
+ "naucs_at_100_max": null,
927
+ "naucs_at_100_std": null,
928
+ "naucs_at_100_diff1": null
929
  },
930
+ "vidore/syntheticDocQA_energy_test": {
931
+ "ndcg_at_1": 0.94,
932
+ "ndcg_at_3": 0.95262,
933
+ "ndcg_at_5": 0.95693,
934
+ "ndcg_at_10": 0.96008,
935
+ "ndcg_at_20": 0.96287,
936
+ "ndcg_at_50": 0.96511,
937
+ "ndcg_at_100": 0.96511,
938
+ "map_at_1": 0.94,
939
+ "map_at_3": 0.95,
940
+ "map_at_5": 0.9525,
941
+ "map_at_10": 0.95375,
942
+ "map_at_20": 0.95466,
943
+ "map_at_50": 0.95514,
944
+ "map_at_100": 0.95514,
945
+ "recall_at_1": 0.94,
946
+ "recall_at_3": 0.96,
947
+ "recall_at_5": 0.97,
948
+ "recall_at_10": 0.98,
949
+ "recall_at_20": 0.99,
950
+ "recall_at_50": 1.0,
951
+ "recall_at_100": 1.0,
952
+ "precision_at_1": 0.94,
953
+ "precision_at_3": 0.32,
954
+ "precision_at_5": 0.194,
955
+ "precision_at_10": 0.098,
956
+ "precision_at_20": 0.0495,
957
+ "precision_at_50": 0.02,
958
+ "precision_at_100": 0.01,
959
+ "mrr_at_1": 0.94,
960
+ "mrr_at_3": 0.95,
961
+ "mrr_at_5": 0.9525,
962
+ "mrr_at_10": 0.95375,
963
+ "mrr_at_20": 0.9551590909090909,
964
+ "mrr_at_50": 0.9551590909090909,
965
+ "mrr_at_100": 0.9551590909090909,
966
+ "naucs_at_1_max": 0.16293183940242884,
967
+ "naucs_at_1_std": -1.0354808590102687,
968
+ "naucs_at_1_diff1": 0.9782135076252712,
969
+ "naucs_at_3_max": 0.31500933706816353,
970
+ "naucs_at_3_std": -0.9773576097105482,
971
+ "naucs_at_3_diff1": 1.0,
972
+ "naucs_at_5_max": 0.08667911609088073,
973
+ "naucs_at_5_std": -1.5438842203547984,
974
+ "naucs_at_5_diff1": 1.0,
975
+ "naucs_at_10_max": -0.3699813258636707,
976
+ "naucs_at_10_std": -1.7399626517273414,
977
+ "naucs_at_10_diff1": 1.0,
978
+ "naucs_at_20_max": 1.0,
979
+ "naucs_at_20_std": -1.7399626517273863,
980
+ "naucs_at_20_diff1": 1.0,
981
+ "naucs_at_50_max": null,
982
+ "naucs_at_50_std": null,
983
+ "naucs_at_50_diff1": null,
984
+ "naucs_at_100_max": null,
985
+ "naucs_at_100_std": null,
986
+ "naucs_at_100_diff1": null
987
  },
988
+ "vidore/syntheticDocQA_government_reports_test": {
989
+ "ndcg_at_1": 0.9,
990
+ "ndcg_at_3": 0.95678,
991
+ "ndcg_at_5": 0.95678,
992
+ "ndcg_at_10": 0.95994,
993
+ "ndcg_at_20": 0.95994,
994
+ "ndcg_at_50": 0.95994,
995
+ "ndcg_at_100": 0.95994,
996
+ "map_at_1": 0.9,
997
+ "map_at_3": 0.945,
998
+ "map_at_5": 0.945,
999
+ "map_at_10": 0.94625,
1000
+ "map_at_20": 0.94625,
1001
+ "map_at_50": 0.94625,
1002
+ "map_at_100": 0.94625,
1003
+ "recall_at_1": 0.9,
1004
+ "recall_at_3": 0.99,
1005
+ "recall_at_5": 0.99,
1006
+ "recall_at_10": 1.0,
1007
+ "recall_at_20": 1.0,
1008
+ "recall_at_50": 1.0,
1009
+ "recall_at_100": 1.0,
1010
+ "precision_at_1": 0.9,
1011
+ "precision_at_3": 0.33,
1012
+ "precision_at_5": 0.198,
1013
+ "precision_at_10": 0.1,
1014
+ "precision_at_20": 0.05,
1015
+ "precision_at_50": 0.02,
1016
+ "precision_at_100": 0.01,
1017
+ "mrr_at_1": 0.9,
1018
+ "mrr_at_3": 0.945,
1019
+ "mrr_at_5": 0.945,
1020
+ "mrr_at_10": 0.9464285714285714,
1021
+ "mrr_at_20": 0.9464285714285714,
1022
+ "mrr_at_50": 0.9464285714285714,
1023
+ "mrr_at_100": 0.9464285714285714,
1024
+ "naucs_at_1_max": 0.5815126050420164,
1025
+ "naucs_at_1_std": -0.42105508870214864,
1026
+ "naucs_at_1_diff1": 0.9330065359477123,
1027
+ "naucs_at_3_max": 0.5541549953314585,
1028
+ "naucs_at_3_std": -1.7399626517274398,
1029
+ "naucs_at_3_diff1": 0.8692810457516356,
1030
+ "naucs_at_5_max": 0.5541549953314738,
1031
+ "naucs_at_5_std": -1.7399626517273863,
1032
+ "naucs_at_5_diff1": 0.8692810457516413,
1033
+ "naucs_at_10_max": 1.0,
1034
+ "naucs_at_10_std": 1.0,
1035
+ "naucs_at_10_diff1": 1.0,
1036
+ "naucs_at_20_max": 1.0,
1037
+ "naucs_at_20_std": 1.0,
1038
+ "naucs_at_20_diff1": 1.0,
1039
+ "naucs_at_50_max": null,
1040
+ "naucs_at_50_std": null,
1041
+ "naucs_at_50_diff1": null,
1042
+ "naucs_at_100_max": null,
1043
+ "naucs_at_100_std": null,
1044
+ "naucs_at_100_diff1": null
1045
  },
1046
+ "vidore/syntheticDocQA_healthcare_industry_test": {
1047
+ "ndcg_at_1": 0.96,
1048
+ "ndcg_at_3": 0.97893,
1049
+ "ndcg_at_5": 0.98323,
1050
+ "ndcg_at_10": 0.98323,
1051
+ "ndcg_at_20": 0.98323,
1052
+ "ndcg_at_50": 0.98323,
1053
+ "ndcg_at_100": 0.98323,
1054
+ "map_at_1": 0.96,
1055
+ "map_at_3": 0.975,
1056
+ "map_at_5": 0.9775,
1057
+ "map_at_10": 0.9775,
1058
+ "map_at_20": 0.9775,
1059
+ "map_at_50": 0.9775,
1060
+ "map_at_100": 0.9775,
1061
+ "recall_at_1": 0.96,
1062
+ "recall_at_3": 0.99,
1063
+ "recall_at_5": 1.0,
1064
+ "recall_at_10": 1.0,
1065
+ "recall_at_20": 1.0,
1066
+ "recall_at_50": 1.0,
1067
+ "recall_at_100": 1.0,
1068
+ "precision_at_1": 0.96,
1069
+ "precision_at_3": 0.33,
1070
+ "precision_at_5": 0.2,
1071
+ "precision_at_10": 0.1,
1072
+ "precision_at_20": 0.05,
1073
+ "precision_at_50": 0.02,
1074
+ "precision_at_100": 0.01,
1075
+ "mrr_at_1": 0.96,
1076
+ "mrr_at_3": 0.975,
1077
+ "mrr_at_5": 0.9775,
1078
+ "mrr_at_10": 0.9775,
1079
+ "mrr_at_20": 0.9775,
1080
+ "mrr_at_50": 0.9775,
1081
+ "mrr_at_100": 0.9775,
1082
+ "naucs_at_1_max": 0.7006302521008423,
1083
+ "naucs_at_1_std": -0.7350606909430405,
1084
+ "naucs_at_1_diff1": 0.9305555555555578,
1085
+ "naucs_at_3_max": 0.7222222222222157,
1086
+ "naucs_at_3_std": -1.1517273576097802,
1087
+ "naucs_at_3_diff1": 1.0,
1088
+ "naucs_at_5_max": 1.0,
1089
+ "naucs_at_5_std": 1.0,
1090
+ "naucs_at_5_diff1": 1.0,
1091
+ "naucs_at_10_max": 1.0,
1092
+ "naucs_at_10_std": 1.0,
1093
+ "naucs_at_10_diff1": 1.0,
1094
+ "naucs_at_20_max": 1.0,
1095
+ "naucs_at_20_std": 1.0,
1096
+ "naucs_at_20_diff1": 1.0,
1097
+ "naucs_at_50_max": null,
1098
+ "naucs_at_50_std": null,
1099
+ "naucs_at_50_diff1": null,
1100
+ "naucs_at_100_max": null,
1101
+ "naucs_at_100_std": null,
1102
+ "naucs_at_100_diff1": null
1103
  }
1104
  }