Upload results.json
Browse files- results.json +430 -430
results.json
CHANGED
@@ -1,175 +1,175 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"timestamp": "2025-01-
|
4 |
"vidore_benchmark_version": "4.0.3.dev20+g2d72668"
|
5 |
},
|
6 |
"metrics": {
|
7 |
-
"arxivqa_test_subsampled": {
|
8 |
-
"ndcg_at_1": 0.
|
9 |
-
"ndcg_at_3": 0.
|
10 |
-
"ndcg_at_5": 0.
|
11 |
-
"ndcg_at_10": 0.
|
12 |
-
"ndcg_at_20": 0.
|
13 |
-
"ndcg_at_50": 0.
|
14 |
-
"ndcg_at_100": 0.
|
15 |
-
"map_at_1": 0.
|
16 |
-
"map_at_3": 0.
|
17 |
-
"map_at_5": 0.
|
18 |
-
"map_at_10": 0.
|
19 |
-
"map_at_20": 0.
|
20 |
-
"map_at_50": 0.
|
21 |
-
"map_at_100": 0.
|
22 |
-
"recall_at_1": 0.
|
23 |
-
"recall_at_3": 0.
|
24 |
-
"recall_at_5": 0.
|
25 |
-
"recall_at_10": 0.
|
26 |
"recall_at_20": 0.98,
|
27 |
"recall_at_50": 0.99,
|
28 |
"recall_at_100": 0.996,
|
29 |
-
"precision_at_1": 0.
|
30 |
-
"precision_at_3": 0.
|
31 |
-
"precision_at_5": 0.
|
32 |
-
"precision_at_10": 0.
|
33 |
"precision_at_20": 0.049,
|
34 |
"precision_at_50": 0.0198,
|
35 |
"precision_at_100": 0.00996,
|
36 |
-
"mrr_at_1": 0.
|
37 |
-
"mrr_at_3": 0.
|
38 |
-
"mrr_at_5": 0.
|
39 |
-
"mrr_at_10": 0.
|
40 |
-
"mrr_at_20": 0.
|
41 |
-
"mrr_at_50": 0.
|
42 |
-
"mrr_at_100": 0.
|
43 |
-
"naucs_at_1_max": 0.
|
44 |
-
"naucs_at_1_std":
|
45 |
-
"naucs_at_1_diff1": 0.
|
46 |
-
"naucs_at_3_max": 0.
|
47 |
-
"naucs_at_3_std": 0.
|
48 |
-
"naucs_at_3_diff1": 0.
|
49 |
-
"naucs_at_5_max": 0.
|
50 |
-
"naucs_at_5_std": 0.
|
51 |
-
"naucs_at_5_diff1": 0.
|
52 |
-
"naucs_at_10_max": 0.
|
53 |
-
"naucs_at_10_std": 0.
|
54 |
-
"naucs_at_10_diff1": 0.
|
55 |
-
"naucs_at_20_max": 0.
|
56 |
-
"naucs_at_20_std":
|
57 |
-
"naucs_at_20_diff1": 0.
|
58 |
-
"naucs_at_50_max": 0.
|
59 |
-
"naucs_at_50_std": 0.
|
60 |
-
"naucs_at_50_diff1": 0.
|
61 |
"naucs_at_100_max": 1.0,
|
62 |
"naucs_at_100_std": 1.0,
|
63 |
-
"naucs_at_100_diff1": 0
|
64 |
},
|
65 |
-
"docvqa_test_subsampled": {
|
66 |
-
"ndcg_at_1": 0.
|
67 |
-
"ndcg_at_3": 0.
|
68 |
-
"ndcg_at_5": 0.
|
69 |
-
"ndcg_at_10": 0.
|
70 |
-
"ndcg_at_20": 0.
|
71 |
-
"ndcg_at_50": 0.
|
72 |
-
"ndcg_at_100": 0.
|
73 |
-
"map_at_1": 0.
|
74 |
-
"map_at_3": 0.
|
75 |
-
"map_at_5": 0.
|
76 |
-
"map_at_10": 0.
|
77 |
-
"map_at_20": 0.
|
78 |
-
"map_at_50": 0.
|
79 |
-
"map_at_100": 0.
|
80 |
-
"recall_at_1": 0.
|
81 |
-
"recall_at_3": 0.
|
82 |
-
"recall_at_5": 0.
|
83 |
-
"recall_at_10": 0.
|
84 |
-
"recall_at_20": 0.
|
85 |
-
"recall_at_50": 0.
|
86 |
-
"recall_at_100": 0.
|
87 |
-
"precision_at_1": 0.
|
88 |
-
"precision_at_3": 0.
|
89 |
-
"precision_at_5": 0.
|
90 |
-
"precision_at_10": 0.
|
91 |
-
"precision_at_20": 0.
|
92 |
-
"precision_at_50": 0.
|
93 |
-
"precision_at_100": 0.
|
94 |
-
"mrr_at_1": 0.
|
95 |
-
"mrr_at_3": 0.
|
96 |
-
"mrr_at_5": 0.
|
97 |
-
"mrr_at_10": 0.
|
98 |
-
"mrr_at_20": 0.
|
99 |
-
"mrr_at_50": 0.
|
100 |
-
"mrr_at_100": 0.
|
101 |
-
"naucs_at_1_max": 0.
|
102 |
-
"naucs_at_1_std": 0.
|
103 |
-
"naucs_at_1_diff1": 0.
|
104 |
-
"naucs_at_3_max": 0.
|
105 |
-
"naucs_at_3_std": 0.
|
106 |
-
"naucs_at_3_diff1": 0.
|
107 |
-
"naucs_at_5_max": 0.
|
108 |
-
"naucs_at_5_std": 0.
|
109 |
-
"naucs_at_5_diff1": 0.
|
110 |
-
"naucs_at_10_max": 0.
|
111 |
-
"naucs_at_10_std": 0.
|
112 |
-
"naucs_at_10_diff1": 0.
|
113 |
-
"naucs_at_20_max": 0.
|
114 |
-
"naucs_at_20_std": 0.
|
115 |
-
"naucs_at_20_diff1": 0.
|
116 |
-
"naucs_at_50_max": 0.
|
117 |
-
"naucs_at_50_std": 0.
|
118 |
-
"naucs_at_50_diff1": 0.
|
119 |
-
"naucs_at_100_max": -0.
|
120 |
-
"naucs_at_100_std": 0.
|
121 |
-
"naucs_at_100_diff1": 0.
|
122 |
},
|
123 |
-
"syntheticDocQA_energy_test": {
|
124 |
-
"ndcg_at_1": 0.
|
125 |
-
"ndcg_at_3": 0.
|
126 |
-
"ndcg_at_5": 0.
|
127 |
-
"ndcg_at_10": 0.
|
128 |
-
"ndcg_at_20": 0.
|
129 |
-
"ndcg_at_50": 0.
|
130 |
-
"ndcg_at_100": 0.
|
131 |
-
"map_at_1": 0.
|
132 |
-
"map_at_3": 0.
|
133 |
-
"map_at_5": 0.
|
134 |
-
"map_at_10": 0.
|
135 |
-
"map_at_20": 0.
|
136 |
-
"map_at_50": 0.
|
137 |
-
"map_at_100": 0.
|
138 |
-
"recall_at_1": 0.
|
139 |
-
"recall_at_3": 0.
|
140 |
-
"recall_at_5": 0.
|
141 |
"recall_at_10": 0.98,
|
142 |
"recall_at_20": 0.99,
|
143 |
"recall_at_50": 1.0,
|
144 |
"recall_at_100": 1.0,
|
145 |
-
"precision_at_1": 0.
|
146 |
-
"precision_at_3": 0.
|
147 |
-
"precision_at_5": 0.
|
148 |
"precision_at_10": 0.098,
|
149 |
"precision_at_20": 0.0495,
|
150 |
"precision_at_50": 0.02,
|
151 |
"precision_at_100": 0.01,
|
152 |
-
"mrr_at_1": 0.
|
153 |
-
"mrr_at_3": 0.
|
154 |
-
"mrr_at_5": 0.
|
155 |
-
"mrr_at_10": 0.
|
156 |
-
"mrr_at_20": 0.
|
157 |
-
"mrr_at_50": 0.
|
158 |
-
"mrr_at_100": 0.
|
159 |
-
"naucs_at_1_max": 0.
|
160 |
-
"naucs_at_1_std": -0.
|
161 |
-
"naucs_at_1_diff1": 0
|
162 |
-
"naucs_at_3_max": 0.
|
163 |
-
"naucs_at_3_std": -0.
|
164 |
-
"naucs_at_3_diff1": 0
|
165 |
-
"naucs_at_5_max": 0.
|
166 |
-
"naucs_at_5_std": -0.
|
167 |
-
"naucs_at_5_diff1": 0
|
168 |
-
"naucs_at_10_max": 0.
|
169 |
-
"naucs_at_10_std": -0.
|
170 |
-
"naucs_at_10_diff1": 0
|
171 |
-
"naucs_at_20_max": 0
|
172 |
-
"naucs_at_20_std": -0.
|
173 |
"naucs_at_20_diff1": 1.0,
|
174 |
"naucs_at_50_max": null,
|
175 |
"naucs_at_50_std": null,
|
@@ -178,161 +178,161 @@
|
|
178 |
"naucs_at_100_std": null,
|
179 |
"naucs_at_100_diff1": null
|
180 |
},
|
181 |
-
"tatdqa_test": {
|
182 |
-
"ndcg_at_1": 0.
|
183 |
-
"ndcg_at_3": 0.
|
184 |
-
"ndcg_at_5": 0.
|
185 |
-
"ndcg_at_10": 0.
|
186 |
-
"ndcg_at_20": 0.
|
187 |
-
"ndcg_at_50": 0.
|
188 |
-
"ndcg_at_100": 0.
|
189 |
-
"map_at_1": 0.
|
190 |
-
"map_at_3": 0.
|
191 |
-
"map_at_5": 0.
|
192 |
-
"map_at_10": 0.
|
193 |
-
"map_at_20": 0.
|
194 |
-
"map_at_50": 0.
|
195 |
-
"map_at_100": 0.
|
196 |
-
"recall_at_1": 0.
|
197 |
-
"recall_at_3": 0.
|
198 |
-
"recall_at_5": 0.
|
199 |
-
"recall_at_10": 0.
|
200 |
-
"recall_at_20": 0.
|
201 |
-
"recall_at_50": 0.
|
202 |
-
"recall_at_100": 0.
|
203 |
-
"precision_at_1": 0.
|
204 |
-
"precision_at_3": 0.
|
205 |
-
"precision_at_5": 0.
|
206 |
-
"precision_at_10": 0.
|
207 |
-
"precision_at_20": 0.
|
208 |
-
"precision_at_50": 0.
|
209 |
"precision_at_100": 0.00988,
|
210 |
-
"mrr_at_1": 0.
|
211 |
-
"mrr_at_3": 0.
|
212 |
-
"mrr_at_5": 0.
|
213 |
-
"mrr_at_10": 0.
|
214 |
-
"mrr_at_20": 0.
|
215 |
-
"mrr_at_50": 0.
|
216 |
-
"mrr_at_100": 0.
|
217 |
-
"naucs_at_1_max": 0.
|
218 |
-
"naucs_at_1_std": -0.
|
219 |
-
"naucs_at_1_diff1": 0.
|
220 |
-
"naucs_at_3_max": 0.
|
221 |
-
"naucs_at_3_std": -0.
|
222 |
-
"naucs_at_3_diff1": 0.
|
223 |
-
"naucs_at_5_max": 0.
|
224 |
-
"naucs_at_5_std": 0.
|
225 |
-
"naucs_at_5_diff1": 0.
|
226 |
-
"naucs_at_10_max": 0.
|
227 |
-
"naucs_at_10_std": 0.
|
228 |
-
"naucs_at_10_diff1": 0.
|
229 |
-
"naucs_at_20_max": 0.
|
230 |
-
"naucs_at_20_std": 0.
|
231 |
-
"naucs_at_20_diff1": 0.
|
232 |
-
"naucs_at_50_max": 0.
|
233 |
-
"naucs_at_50_std": 0.
|
234 |
-
"naucs_at_50_diff1": 0.
|
235 |
-
"naucs_at_100_max": 0.
|
236 |
-
"naucs_at_100_std": 0.
|
237 |
-
"naucs_at_100_diff1": 0.
|
238 |
},
|
239 |
-
"infovqa_test_subsampled": {
|
240 |
-
"ndcg_at_1": 0.
|
241 |
-
"ndcg_at_3": 0.
|
242 |
-
"ndcg_at_5": 0.
|
243 |
-
"ndcg_at_10": 0.
|
244 |
-
"ndcg_at_20": 0.
|
245 |
-
"ndcg_at_50": 0.
|
246 |
-
"ndcg_at_100": 0.
|
247 |
-
"map_at_1": 0.
|
248 |
-
"map_at_3": 0.
|
249 |
-
"map_at_5": 0.
|
250 |
-
"map_at_10": 0.
|
251 |
-
"map_at_20": 0.
|
252 |
-
"map_at_50": 0.
|
253 |
-
"map_at_100": 0.
|
254 |
-
"recall_at_1": 0.
|
255 |
"recall_at_3": 0.93927,
|
256 |
"recall_at_5": 0.95547,
|
257 |
-
"recall_at_10": 0.
|
258 |
-
"recall_at_20": 0.
|
259 |
"recall_at_50": 0.98785,
|
260 |
-
"recall_at_100": 0.
|
261 |
-
"precision_at_1": 0.
|
262 |
"precision_at_3": 0.31309,
|
263 |
"precision_at_5": 0.19109,
|
264 |
-
"precision_at_10": 0.
|
265 |
-
"precision_at_20": 0.
|
266 |
"precision_at_50": 0.01976,
|
267 |
-
"precision_at_100": 0.
|
268 |
"mrr_at_1": 0.8846153846153846,
|
269 |
"mrr_at_3": 0.9092442645074225,
|
270 |
-
"mrr_at_5": 0.
|
271 |
-
"mrr_at_10": 0.
|
272 |
-
"mrr_at_20": 0.
|
273 |
-
"mrr_at_50": 0.
|
274 |
-
"mrr_at_100": 0.
|
275 |
-
"naucs_at_1_max": 0.
|
276 |
-
"naucs_at_1_std": -0.
|
277 |
-
"naucs_at_1_diff1": 0.
|
278 |
-
"naucs_at_3_max": 0.
|
279 |
-
"naucs_at_3_std": 0.
|
280 |
-
"naucs_at_3_diff1": 0.
|
281 |
-
"naucs_at_5_max": 0.
|
282 |
-
"naucs_at_5_std": 0.
|
283 |
-
"naucs_at_5_diff1": 0.
|
284 |
-
"naucs_at_10_max": 0.
|
285 |
-
"naucs_at_10_std": 0.
|
286 |
-
"naucs_at_10_diff1": 0.
|
287 |
-
"naucs_at_20_max": 0.
|
288 |
-
"naucs_at_20_std": 0.
|
289 |
-
"naucs_at_20_diff1": 0.
|
290 |
-
"naucs_at_50_max": 0.
|
291 |
-
"naucs_at_50_std": 0.
|
292 |
-
"naucs_at_50_diff1": 0.
|
293 |
-
"naucs_at_100_max": 0
|
294 |
-
"naucs_at_100_std": 0.
|
295 |
-
"naucs_at_100_diff1": 0.
|
296 |
},
|
297 |
-
"syntheticDocQA_healthcare_industry_test": {
|
298 |
-
"ndcg_at_1": 0.
|
299 |
-
"ndcg_at_3": 0.
|
300 |
-
"ndcg_at_5": 0.
|
301 |
-
"ndcg_at_10": 0.
|
302 |
-
"ndcg_at_20": 0.
|
303 |
-
"ndcg_at_50": 0.
|
304 |
-
"ndcg_at_100": 0.
|
305 |
-
"map_at_1": 0.
|
306 |
-
"map_at_3": 0.
|
307 |
-
"map_at_5": 0.
|
308 |
-
"map_at_10": 0.
|
309 |
-
"map_at_20": 0.
|
310 |
-
"map_at_50": 0.
|
311 |
-
"map_at_100": 0.
|
312 |
-
"recall_at_1": 0.
|
313 |
"recall_at_3": 1.0,
|
314 |
"recall_at_5": 1.0,
|
315 |
"recall_at_10": 1.0,
|
316 |
"recall_at_20": 1.0,
|
317 |
"recall_at_50": 1.0,
|
318 |
"recall_at_100": 1.0,
|
319 |
-
"precision_at_1": 0.
|
320 |
"precision_at_3": 0.33333,
|
321 |
"precision_at_5": 0.2,
|
322 |
"precision_at_10": 0.1,
|
323 |
"precision_at_20": 0.05,
|
324 |
"precision_at_50": 0.02,
|
325 |
"precision_at_100": 0.01,
|
326 |
-
"mrr_at_1": 0.
|
327 |
-
"mrr_at_3": 0.
|
328 |
-
"mrr_at_5": 0.
|
329 |
-
"mrr_at_10": 0.
|
330 |
-
"mrr_at_20": 0.
|
331 |
-
"mrr_at_50": 0.
|
332 |
-
"mrr_at_100": 0.
|
333 |
-
"naucs_at_1_max": 0.
|
334 |
-
"naucs_at_1_std": -0.
|
335 |
-
"naucs_at_1_diff1": 0.
|
336 |
"naucs_at_3_max": 1.0,
|
337 |
"naucs_at_3_std": 1.0,
|
338 |
"naucs_at_3_diff1": 1.0,
|
@@ -352,56 +352,56 @@
|
|
352 |
"naucs_at_100_std": null,
|
353 |
"naucs_at_100_diff1": null
|
354 |
},
|
355 |
-
"tabfquad_test_subsampled": {
|
356 |
-
"ndcg_at_1": 0.
|
357 |
-
"ndcg_at_3": 0.
|
358 |
-
"ndcg_at_5": 0.
|
359 |
-
"ndcg_at_10": 0.
|
360 |
-
"ndcg_at_20": 0.
|
361 |
-
"ndcg_at_50": 0.
|
362 |
-
"ndcg_at_100": 0.
|
363 |
-
"map_at_1": 0.
|
364 |
-
"map_at_3": 0.
|
365 |
-
"map_at_5": 0.
|
366 |
-
"map_at_10": 0.
|
367 |
-
"map_at_20": 0.
|
368 |
-
"map_at_50": 0.
|
369 |
-
"map_at_100": 0.
|
370 |
-
"recall_at_1": 0.
|
371 |
-
"recall_at_3": 0.
|
372 |
-
"recall_at_5": 0.
|
373 |
-
"recall_at_10": 0.
|
374 |
"recall_at_20": 0.98929,
|
375 |
"recall_at_50": 1.0,
|
376 |
"recall_at_100": 1.0,
|
377 |
-
"precision_at_1": 0.
|
378 |
-
"precision_at_3": 0.
|
379 |
-
"precision_at_5": 0.
|
380 |
-
"precision_at_10": 0.
|
381 |
"precision_at_20": 0.04946,
|
382 |
"precision_at_50": 0.02,
|
383 |
"precision_at_100": 0.01,
|
384 |
-
"mrr_at_1": 0.
|
385 |
-
"mrr_at_3": 0.
|
386 |
-
"mrr_at_5": 0.
|
387 |
-
"mrr_at_10": 0.
|
388 |
-
"mrr_at_20": 0.
|
389 |
-
"mrr_at_50": 0.
|
390 |
-
"mrr_at_100": 0.
|
391 |
-
"naucs_at_1_max": 0.
|
392 |
-
"naucs_at_1_std": 0.
|
393 |
-
"naucs_at_1_diff1": 0.
|
394 |
-
"naucs_at_3_max": 0.
|
395 |
-
"naucs_at_3_std": 0.
|
396 |
-
"naucs_at_3_diff1": 0.
|
397 |
-
"naucs_at_5_max": 0.
|
398 |
-
"naucs_at_5_std": 0.
|
399 |
-
"naucs_at_5_diff1": 0.
|
400 |
-
"naucs_at_10_max": 0.
|
401 |
-
"naucs_at_10_std": 0.
|
402 |
-
"naucs_at_10_diff1": 0.
|
403 |
-
"naucs_at_20_max": 0.
|
404 |
-
"naucs_at_20_std": 0.
|
405 |
"naucs_at_20_diff1": 0.9564270152505505,
|
406 |
"naucs_at_50_max": 1.0,
|
407 |
"naucs_at_50_std": 1.0,
|
@@ -410,50 +410,50 @@
|
|
410 |
"naucs_at_100_std": 1.0,
|
411 |
"naucs_at_100_diff1": 1.0
|
412 |
},
|
413 |
-
"syntheticDocQA_government_reports_test": {
|
414 |
-
"ndcg_at_1": 0.
|
415 |
-
"ndcg_at_3": 0.
|
416 |
-
"ndcg_at_5": 0.
|
417 |
-
"ndcg_at_10": 0.
|
418 |
-
"ndcg_at_20": 0.
|
419 |
-
"ndcg_at_50": 0.
|
420 |
-
"ndcg_at_100": 0.
|
421 |
-
"map_at_1": 0.
|
422 |
-
"map_at_3": 0.
|
423 |
-
"map_at_5": 0.
|
424 |
-
"map_at_10": 0.
|
425 |
-
"map_at_20": 0.
|
426 |
-
"map_at_50": 0.
|
427 |
-
"map_at_100": 0.
|
428 |
-
"recall_at_1": 0.
|
429 |
-
"recall_at_3": 0.
|
430 |
"recall_at_5": 0.99,
|
431 |
"recall_at_10": 1.0,
|
432 |
"recall_at_20": 1.0,
|
433 |
"recall_at_50": 1.0,
|
434 |
"recall_at_100": 1.0,
|
435 |
-
"precision_at_1": 0.
|
436 |
-
"precision_at_3": 0.
|
437 |
"precision_at_5": 0.198,
|
438 |
"precision_at_10": 0.1,
|
439 |
"precision_at_20": 0.05,
|
440 |
"precision_at_50": 0.02,
|
441 |
"precision_at_100": 0.01,
|
442 |
-
"mrr_at_1": 0.
|
443 |
-
"mrr_at_3": 0.
|
444 |
-
"mrr_at_5": 0.
|
445 |
-
"mrr_at_10": 0.
|
446 |
-
"mrr_at_20": 0.
|
447 |
-
"mrr_at_50": 0.
|
448 |
-
"mrr_at_100": 0.
|
449 |
-
"naucs_at_1_max": 0.
|
450 |
-
"naucs_at_1_std": 0.
|
451 |
-
"naucs_at_1_diff1": 0.
|
452 |
-
"naucs_at_3_max": 0
|
453 |
-
"naucs_at_3_std": 0.
|
454 |
-
"naucs_at_3_diff1": 0
|
455 |
-
"naucs_at_5_max": 0
|
456 |
-
"naucs_at_5_std":
|
457 |
"naucs_at_5_diff1": 1.0,
|
458 |
"naucs_at_10_max": 1.0,
|
459 |
"naucs_at_10_std": 1.0,
|
@@ -468,57 +468,57 @@
|
|
468 |
"naucs_at_100_std": null,
|
469 |
"naucs_at_100_diff1": null
|
470 |
},
|
471 |
-
"shiftproject_test": {
|
472 |
-
"ndcg_at_1": 0.
|
473 |
-
"ndcg_at_3": 0.
|
474 |
-
"ndcg_at_5": 0.
|
475 |
-
"ndcg_at_10": 0.
|
476 |
-
"ndcg_at_20": 0.
|
477 |
-
"ndcg_at_50": 0.
|
478 |
-
"ndcg_at_100": 0.
|
479 |
-
"map_at_1": 0.
|
480 |
-
"map_at_3": 0.
|
481 |
-
"map_at_5": 0.
|
482 |
-
"map_at_10": 0.
|
483 |
-
"map_at_20": 0.
|
484 |
-
"map_at_50": 0.
|
485 |
-
"map_at_100": 0.
|
486 |
-
"recall_at_1": 0.
|
487 |
-
"recall_at_3": 0.
|
488 |
"recall_at_5": 0.94,
|
489 |
-
"recall_at_10": 0.
|
490 |
-
"recall_at_20": 0.
|
491 |
"recall_at_50": 1.0,
|
492 |
"recall_at_100": 1.0,
|
493 |
-
"precision_at_1": 0.
|
494 |
-
"precision_at_3": 0.
|
495 |
"precision_at_5": 0.188,
|
496 |
-
"precision_at_10": 0.
|
497 |
-
"precision_at_20": 0.
|
498 |
"precision_at_50": 0.02,
|
499 |
"precision_at_100": 0.01,
|
500 |
-
"mrr_at_1": 0.
|
501 |
-
"mrr_at_3": 0.
|
502 |
-
"mrr_at_5": 0.
|
503 |
-
"mrr_at_10": 0.
|
504 |
-
"mrr_at_20": 0.
|
505 |
-
"mrr_at_50": 0.
|
506 |
-
"mrr_at_100": 0.
|
507 |
-
"naucs_at_1_max": -0.
|
508 |
-
"naucs_at_1_std": -0.
|
509 |
-
"naucs_at_1_diff1": 0.
|
510 |
-
"naucs_at_3_max":
|
511 |
-
"naucs_at_3_std": -0.
|
512 |
-
"naucs_at_3_diff1": 0.
|
513 |
-
"naucs_at_5_max": 0.
|
514 |
-
"naucs_at_5_std": -0.
|
515 |
-
"naucs_at_5_diff1": 0.
|
516 |
-
"naucs_at_10_max": 0.
|
517 |
-
"naucs_at_10_std": -0.
|
518 |
-
"naucs_at_10_diff1": 0.
|
519 |
-
"naucs_at_20_max":
|
520 |
-
"naucs_at_20_std":
|
521 |
-
"naucs_at_20_diff1": 0.
|
522 |
"naucs_at_50_max": null,
|
523 |
"naucs_at_50_std": null,
|
524 |
"naucs_at_50_diff1": null,
|
@@ -526,44 +526,44 @@
|
|
526 |
"naucs_at_100_std": null,
|
527 |
"naucs_at_100_diff1": null
|
528 |
},
|
529 |
-
"syntheticDocQA_artificial_intelligence_test": {
|
530 |
-
"ndcg_at_1": 0.
|
531 |
-
"ndcg_at_3": 0.
|
532 |
-
"ndcg_at_5": 0.
|
533 |
-
"ndcg_at_10": 0.
|
534 |
-
"ndcg_at_20": 0.
|
535 |
-
"ndcg_at_50": 0.
|
536 |
-
"ndcg_at_100": 0.
|
537 |
-
"map_at_1": 0.
|
538 |
-
"map_at_3": 0.
|
539 |
-
"map_at_5": 0.
|
540 |
-
"map_at_10": 0.
|
541 |
-
"map_at_20": 0.
|
542 |
-
"map_at_50": 0.
|
543 |
-
"map_at_100": 0.
|
544 |
-
"recall_at_1": 0.
|
545 |
"recall_at_3": 1.0,
|
546 |
"recall_at_5": 1.0,
|
547 |
"recall_at_10": 1.0,
|
548 |
"recall_at_20": 1.0,
|
549 |
"recall_at_50": 1.0,
|
550 |
"recall_at_100": 1.0,
|
551 |
-
"precision_at_1": 0.
|
552 |
"precision_at_3": 0.33333,
|
553 |
"precision_at_5": 0.2,
|
554 |
"precision_at_10": 0.1,
|
555 |
"precision_at_20": 0.05,
|
556 |
"precision_at_50": 0.02,
|
557 |
"precision_at_100": 0.01,
|
558 |
-
"mrr_at_1": 0.
|
559 |
-
"mrr_at_3": 0.
|
560 |
-
"mrr_at_5": 0.
|
561 |
-
"mrr_at_10": 0.
|
562 |
-
"mrr_at_20": 0.
|
563 |
-
"mrr_at_50": 0.
|
564 |
-
"mrr_at_100": 0.
|
565 |
-
"naucs_at_1_max": 0.
|
566 |
-
"naucs_at_1_std": -0.
|
567 |
"naucs_at_1_diff1": 1.0,
|
568 |
"naucs_at_3_max": 1.0,
|
569 |
"naucs_at_3_std": 1.0,
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"timestamp": "2025-01-31T14:00:16.349261",
|
4 |
"vidore_benchmark_version": "4.0.3.dev20+g2d72668"
|
5 |
},
|
6 |
"metrics": {
|
7 |
+
"data_dir/eval_vidore/arxivqa_test_subsampled": {
|
8 |
+
"ndcg_at_1": 0.856,
|
9 |
+
"ndcg_at_3": 0.88745,
|
10 |
+
"ndcg_at_5": 0.89227,
|
11 |
+
"ndcg_at_10": 0.90332,
|
12 |
+
"ndcg_at_20": 0.90941,
|
13 |
+
"ndcg_at_50": 0.91153,
|
14 |
+
"ndcg_at_100": 0.91252,
|
15 |
+
"map_at_1": 0.856,
|
16 |
+
"map_at_3": 0.87967,
|
17 |
+
"map_at_5": 0.88227,
|
18 |
+
"map_at_10": 0.88687,
|
19 |
+
"map_at_20": 0.88854,
|
20 |
+
"map_at_50": 0.88895,
|
21 |
+
"map_at_100": 0.88904,
|
22 |
+
"recall_at_1": 0.856,
|
23 |
+
"recall_at_3": 0.91,
|
24 |
+
"recall_at_5": 0.922,
|
25 |
+
"recall_at_10": 0.956,
|
26 |
"recall_at_20": 0.98,
|
27 |
"recall_at_50": 0.99,
|
28 |
"recall_at_100": 0.996,
|
29 |
+
"precision_at_1": 0.856,
|
30 |
+
"precision_at_3": 0.30333,
|
31 |
+
"precision_at_5": 0.1844,
|
32 |
+
"precision_at_10": 0.0956,
|
33 |
"precision_at_20": 0.049,
|
34 |
"precision_at_50": 0.0198,
|
35 |
"precision_at_100": 0.00996,
|
36 |
+
"mrr_at_1": 0.854,
|
37 |
+
"mrr_at_3": 0.8773333333333334,
|
38 |
+
"mrr_at_5": 0.8809333333333332,
|
39 |
+
"mrr_at_10": 0.8855674603174604,
|
40 |
+
"mrr_at_20": 0.8873665921453847,
|
41 |
+
"mrr_at_50": 0.8876643128304966,
|
42 |
+
"mrr_at_100": 0.887751797810069,
|
43 |
+
"naucs_at_1_max": 0.8146679814134421,
|
44 |
+
"naucs_at_1_std": 0.07396801383185674,
|
45 |
+
"naucs_at_1_diff1": 0.9423560082126644,
|
46 |
+
"naucs_at_3_max": 0.8066396929142029,
|
47 |
+
"naucs_at_3_std": 0.07559912854030806,
|
48 |
+
"naucs_at_3_diff1": 0.9181969083929873,
|
49 |
+
"naucs_at_5_max": 0.8034068328185975,
|
50 |
+
"naucs_at_5_std": 0.02020637314754663,
|
51 |
+
"naucs_at_5_diff1": 0.9160860925566815,
|
52 |
+
"naucs_at_10_max": 0.825566590272474,
|
53 |
+
"naucs_at_10_std": -0.15187590187589842,
|
54 |
+
"naucs_at_10_diff1": 0.9390968508615584,
|
55 |
+
"naucs_at_20_max": 0.8921568627450932,
|
56 |
+
"naucs_at_20_std": 0.0641923436041116,
|
57 |
+
"naucs_at_20_diff1": 0.9738562091503187,
|
58 |
+
"naucs_at_50_max": 0.947712418300658,
|
59 |
+
"naucs_at_50_std": 0.37030812324930756,
|
60 |
+
"naucs_at_50_diff1": 0.9738562091503188,
|
61 |
"naucs_at_100_max": 1.0,
|
62 |
"naucs_at_100_std": 1.0,
|
63 |
+
"naucs_at_100_diff1": 1.0
|
64 |
},
|
65 |
+
"data_dir/eval_vidore/docvqa_test_subsampled": {
|
66 |
+
"ndcg_at_1": 0.55876,
|
67 |
+
"ndcg_at_3": 0.61485,
|
68 |
+
"ndcg_at_5": 0.63222,
|
69 |
+
"ndcg_at_10": 0.65493,
|
70 |
+
"ndcg_at_20": 0.66746,
|
71 |
+
"ndcg_at_50": 0.67657,
|
72 |
+
"ndcg_at_100": 0.68329,
|
73 |
+
"map_at_1": 0.55876,
|
74 |
+
"map_at_3": 0.60126,
|
75 |
+
"map_at_5": 0.6109,
|
76 |
+
"map_at_10": 0.62013,
|
77 |
+
"map_at_20": 0.62368,
|
78 |
+
"map_at_50": 0.62509,
|
79 |
+
"map_at_100": 0.62564,
|
80 |
+
"recall_at_1": 0.55876,
|
81 |
+
"recall_at_3": 0.6541,
|
82 |
+
"recall_at_5": 0.69623,
|
83 |
+
"recall_at_10": 0.76718,
|
84 |
+
"recall_at_20": 0.81596,
|
85 |
+
"recall_at_50": 0.86253,
|
86 |
+
"recall_at_100": 0.90466,
|
87 |
+
"precision_at_1": 0.55876,
|
88 |
+
"precision_at_3": 0.21803,
|
89 |
+
"precision_at_5": 0.13925,
|
90 |
+
"precision_at_10": 0.07672,
|
91 |
+
"precision_at_20": 0.0408,
|
92 |
+
"precision_at_50": 0.01725,
|
93 |
+
"precision_at_100": 0.00905,
|
94 |
+
"mrr_at_1": 0.5543237250554324,
|
95 |
+
"mrr_at_3": 0.599039172209904,
|
96 |
+
"mrr_at_5": 0.609349593495935,
|
97 |
+
"mrr_at_10": 0.6183401963889769,
|
98 |
+
"mrr_at_20": 0.6209344044461912,
|
99 |
+
"mrr_at_50": 0.6227106859869997,
|
100 |
+
"mrr_at_100": 0.6232889837626537,
|
101 |
+
"naucs_at_1_max": 0.29569387287927856,
|
102 |
+
"naucs_at_1_std": 0.6842470452244832,
|
103 |
+
"naucs_at_1_diff1": 0.9092758189268736,
|
104 |
+
"naucs_at_3_max": 0.21005633503267365,
|
105 |
+
"naucs_at_3_std": 0.805068083051039,
|
106 |
+
"naucs_at_3_diff1": 0.8754563618133548,
|
107 |
+
"naucs_at_5_max": 0.19259019824979384,
|
108 |
+
"naucs_at_5_std": 0.8409490067520664,
|
109 |
+
"naucs_at_5_diff1": 0.8726101181684977,
|
110 |
+
"naucs_at_10_max": 0.048646855770537796,
|
111 |
+
"naucs_at_10_std": 0.8833213018935924,
|
112 |
+
"naucs_at_10_diff1": 0.8643899050698751,
|
113 |
+
"naucs_at_20_max": -0.06225799483664109,
|
114 |
+
"naucs_at_20_std": 0.9127300541361831,
|
115 |
+
"naucs_at_20_diff1": 0.8597071895030789,
|
116 |
+
"naucs_at_50_max": -0.24442668101014947,
|
117 |
+
"naucs_at_50_std": 0.930294669379938,
|
118 |
+
"naucs_at_50_diff1": 0.8714057920484658,
|
119 |
+
"naucs_at_100_max": -0.3617257884810223,
|
120 |
+
"naucs_at_100_std": 0.9386292283530702,
|
121 |
+
"naucs_at_100_diff1": 0.8597379463433718
|
122 |
},
|
123 |
+
"data_dir/eval_vidore/syntheticDocQA_energy_test": {
|
124 |
+
"ndcg_at_1": 0.93,
|
125 |
+
"ndcg_at_3": 0.95893,
|
126 |
+
"ndcg_at_5": 0.95893,
|
127 |
+
"ndcg_at_10": 0.95893,
|
128 |
+
"ndcg_at_20": 0.96163,
|
129 |
+
"ndcg_at_50": 0.96365,
|
130 |
+
"ndcg_at_100": 0.96365,
|
131 |
+
"map_at_1": 0.93,
|
132 |
+
"map_at_3": 0.95167,
|
133 |
+
"map_at_5": 0.95167,
|
134 |
+
"map_at_10": 0.95167,
|
135 |
+
"map_at_20": 0.9525,
|
136 |
+
"map_at_50": 0.95283,
|
137 |
+
"map_at_100": 0.95283,
|
138 |
+
"recall_at_1": 0.93,
|
139 |
+
"recall_at_3": 0.98,
|
140 |
+
"recall_at_5": 0.98,
|
141 |
"recall_at_10": 0.98,
|
142 |
"recall_at_20": 0.99,
|
143 |
"recall_at_50": 1.0,
|
144 |
"recall_at_100": 1.0,
|
145 |
+
"precision_at_1": 0.93,
|
146 |
+
"precision_at_3": 0.32667,
|
147 |
+
"precision_at_5": 0.196,
|
148 |
"precision_at_10": 0.098,
|
149 |
"precision_at_20": 0.0495,
|
150 |
"precision_at_50": 0.02,
|
151 |
"precision_at_100": 0.01,
|
152 |
+
"mrr_at_1": 0.93,
|
153 |
+
"mrr_at_3": 0.9516666666666667,
|
154 |
+
"mrr_at_5": 0.9516666666666667,
|
155 |
+
"mrr_at_10": 0.9516666666666667,
|
156 |
+
"mrr_at_20": 0.9525757575757575,
|
157 |
+
"mrr_at_50": 0.9529205851619644,
|
158 |
+
"mrr_at_100": 0.9529205851619644,
|
159 |
+
"naucs_at_1_max": 0.39482459650526885,
|
160 |
+
"naucs_at_1_std": -0.31419234360410914,
|
161 |
+
"naucs_at_1_diff1": 1.0,
|
162 |
+
"naucs_at_3_max": 0.6790382819794457,
|
163 |
+
"naucs_at_3_std": -0.9556489262371661,
|
164 |
+
"naucs_at_3_diff1": 1.0,
|
165 |
+
"naucs_at_5_max": 0.6790382819794609,
|
166 |
+
"naucs_at_5_std": -0.9556489262371534,
|
167 |
+
"naucs_at_5_diff1": 1.0,
|
168 |
+
"naucs_at_10_max": 0.6790382819794609,
|
169 |
+
"naucs_at_10_std": -0.9556489262371534,
|
170 |
+
"naucs_at_10_diff1": 1.0,
|
171 |
+
"naucs_at_20_max": 1.0,
|
172 |
+
"naucs_at_20_std": -0.1713352007469681,
|
173 |
"naucs_at_20_diff1": 1.0,
|
174 |
"naucs_at_50_max": null,
|
175 |
"naucs_at_50_std": null,
|
|
|
178 |
"naucs_at_100_std": null,
|
179 |
"naucs_at_100_diff1": null
|
180 |
},
|
181 |
+
"data_dir/eval_vidore/tatdqa_test": {
|
182 |
+
"ndcg_at_1": 0.69927,
|
183 |
+
"ndcg_at_3": 0.79372,
|
184 |
+
"ndcg_at_5": 0.81105,
|
185 |
+
"ndcg_at_10": 0.82459,
|
186 |
+
"ndcg_at_20": 0.82878,
|
187 |
+
"ndcg_at_50": 0.83303,
|
188 |
+
"ndcg_at_100": 0.83442,
|
189 |
+
"map_at_1": 0.69927,
|
190 |
+
"map_at_3": 0.77106,
|
191 |
+
"map_at_5": 0.78072,
|
192 |
+
"map_at_10": 0.78653,
|
193 |
+
"map_at_20": 0.7877,
|
194 |
+
"map_at_50": 0.78839,
|
195 |
+
"map_at_100": 0.78852,
|
196 |
+
"recall_at_1": 0.69927,
|
197 |
+
"recall_at_3": 0.85905,
|
198 |
+
"recall_at_5": 0.90097,
|
199 |
+
"recall_at_10": 0.94168,
|
200 |
+
"recall_at_20": 0.95808,
|
201 |
+
"recall_at_50": 0.97934,
|
202 |
+
"recall_at_100": 0.98785,
|
203 |
+
"precision_at_1": 0.69927,
|
204 |
+
"precision_at_3": 0.28635,
|
205 |
+
"precision_at_5": 0.18019,
|
206 |
+
"precision_at_10": 0.09417,
|
207 |
+
"precision_at_20": 0.0479,
|
208 |
+
"precision_at_50": 0.01959,
|
209 |
"precision_at_100": 0.00988,
|
210 |
+
"mrr_at_1": 0.7004860267314702,
|
211 |
+
"mrr_at_3": 0.7722762251923856,
|
212 |
+
"mrr_at_5": 0.7813284730660186,
|
213 |
+
"mrr_at_10": 0.7874199598835079,
|
214 |
+
"mrr_at_20": 0.7885261582425689,
|
215 |
+
"mrr_at_50": 0.7892193634018624,
|
216 |
+
"mrr_at_100": 0.7893291443742743,
|
217 |
+
"naucs_at_1_max": 0.2682416909968819,
|
218 |
+
"naucs_at_1_std": -0.1346098281401034,
|
219 |
+
"naucs_at_1_diff1": 0.8296403667835969,
|
220 |
+
"naucs_at_3_max": 0.36050493227494845,
|
221 |
+
"naucs_at_3_std": -0.01834048113954263,
|
222 |
+
"naucs_at_3_diff1": 0.7445505884597561,
|
223 |
+
"naucs_at_5_max": 0.36523716935916267,
|
224 |
+
"naucs_at_5_std": 0.06489405058952001,
|
225 |
+
"naucs_at_5_diff1": 0.7142046612217674,
|
226 |
+
"naucs_at_10_max": 0.4293315802144752,
|
227 |
+
"naucs_at_10_std": 0.2564808038730297,
|
228 |
+
"naucs_at_10_diff1": 0.6873136665710184,
|
229 |
+
"naucs_at_20_max": 0.4688188620078513,
|
230 |
+
"naucs_at_20_std": 0.26917226500908054,
|
231 |
+
"naucs_at_20_diff1": 0.6720615167289586,
|
232 |
+
"naucs_at_50_max": 0.5671944664000176,
|
233 |
+
"naucs_at_50_std": 0.4964253483275758,
|
234 |
+
"naucs_at_50_diff1": 0.722603370462453,
|
235 |
+
"naucs_at_100_max": 0.6585255212623138,
|
236 |
+
"naucs_at_100_std": 0.5978336814194427,
|
237 |
+
"naucs_at_100_diff1": 0.8138609714332596
|
238 |
},
|
239 |
+
"data_dir/eval_vidore/infovqa_test_subsampled": {
|
240 |
+
"ndcg_at_1": 0.88462,
|
241 |
+
"ndcg_at_3": 0.91698,
|
242 |
+
"ndcg_at_5": 0.92378,
|
243 |
+
"ndcg_at_10": 0.92838,
|
244 |
+
"ndcg_at_20": 0.93146,
|
245 |
+
"ndcg_at_50": 0.93263,
|
246 |
+
"ndcg_at_100": 0.93362,
|
247 |
+
"map_at_1": 0.88462,
|
248 |
+
"map_at_3": 0.90924,
|
249 |
+
"map_at_5": 0.91309,
|
250 |
+
"map_at_10": 0.91501,
|
251 |
+
"map_at_20": 0.91585,
|
252 |
+
"map_at_50": 0.91603,
|
253 |
+
"map_at_100": 0.91612,
|
254 |
+
"recall_at_1": 0.88462,
|
255 |
"recall_at_3": 0.93927,
|
256 |
"recall_at_5": 0.95547,
|
257 |
+
"recall_at_10": 0.96964,
|
258 |
+
"recall_at_20": 0.98178,
|
259 |
"recall_at_50": 0.98785,
|
260 |
+
"recall_at_100": 0.99393,
|
261 |
+
"precision_at_1": 0.88462,
|
262 |
"precision_at_3": 0.31309,
|
263 |
"precision_at_5": 0.19109,
|
264 |
+
"precision_at_10": 0.09696,
|
265 |
+
"precision_at_20": 0.04909,
|
266 |
"precision_at_50": 0.01976,
|
267 |
+
"precision_at_100": 0.00994,
|
268 |
"mrr_at_1": 0.8846153846153846,
|
269 |
"mrr_at_3": 0.9092442645074225,
|
270 |
+
"mrr_at_5": 0.9129892037786774,
|
271 |
+
"mrr_at_10": 0.9147717049032839,
|
272 |
+
"mrr_at_20": 0.9154333931688503,
|
273 |
+
"mrr_at_50": 0.9156112743493511,
|
274 |
+
"mrr_at_100": 0.915698522470477,
|
275 |
+
"naucs_at_1_max": 0.6002033777762705,
|
276 |
+
"naucs_at_1_std": -0.07102965572007143,
|
277 |
+
"naucs_at_1_diff1": 0.9544715151522033,
|
278 |
+
"naucs_at_3_max": 0.8025453360230541,
|
279 |
+
"naucs_at_3_std": 0.19885112605813188,
|
280 |
+
"naucs_at_3_diff1": 0.960819563780572,
|
281 |
+
"naucs_at_5_max": 0.9121856227472513,
|
282 |
+
"naucs_at_5_std": 0.3583912666662475,
|
283 |
+
"naucs_at_5_diff1": 0.9584449918884831,
|
284 |
+
"naucs_at_10_max": 0.9368484108193146,
|
285 |
+
"naucs_at_10_std": 0.44097650713388975,
|
286 |
+
"naucs_at_10_diff1": 0.9651729455827266,
|
287 |
+
"naucs_at_20_max": 0.9709774546522766,
|
288 |
+
"naucs_at_20_std": 0.6007213904253922,
|
289 |
+
"naucs_at_20_diff1": 0.9854887273261383,
|
290 |
+
"naucs_at_50_max": 0.9782330909892136,
|
291 |
+
"naucs_at_50_std": 0.7577252323561762,
|
292 |
+
"naucs_at_50_diff1": 0.9782330909892136,
|
293 |
+
"naucs_at_100_max": 1.0,
|
294 |
+
"naucs_at_100_std": 0.7075525547215259,
|
295 |
+
"naucs_at_100_diff1": 0.9564661819784259
|
296 |
},
|
297 |
+
"data_dir/eval_vidore/syntheticDocQA_healthcare_industry_test": {
|
298 |
+
"ndcg_at_1": 0.95,
|
299 |
+
"ndcg_at_3": 0.97893,
|
300 |
+
"ndcg_at_5": 0.97893,
|
301 |
+
"ndcg_at_10": 0.97893,
|
302 |
+
"ndcg_at_20": 0.97893,
|
303 |
+
"ndcg_at_50": 0.97893,
|
304 |
+
"ndcg_at_100": 0.97893,
|
305 |
+
"map_at_1": 0.95,
|
306 |
+
"map_at_3": 0.97167,
|
307 |
+
"map_at_5": 0.97167,
|
308 |
+
"map_at_10": 0.97167,
|
309 |
+
"map_at_20": 0.97167,
|
310 |
+
"map_at_50": 0.97167,
|
311 |
+
"map_at_100": 0.97167,
|
312 |
+
"recall_at_1": 0.95,
|
313 |
"recall_at_3": 1.0,
|
314 |
"recall_at_5": 1.0,
|
315 |
"recall_at_10": 1.0,
|
316 |
"recall_at_20": 1.0,
|
317 |
"recall_at_50": 1.0,
|
318 |
"recall_at_100": 1.0,
|
319 |
+
"precision_at_1": 0.95,
|
320 |
"precision_at_3": 0.33333,
|
321 |
"precision_at_5": 0.2,
|
322 |
"precision_at_10": 0.1,
|
323 |
"precision_at_20": 0.05,
|
324 |
"precision_at_50": 0.02,
|
325 |
"precision_at_100": 0.01,
|
326 |
+
"mrr_at_1": 0.96,
|
327 |
+
"mrr_at_3": 0.9783333333333333,
|
328 |
+
"mrr_at_5": 0.9783333333333333,
|
329 |
+
"mrr_at_10": 0.9783333333333333,
|
330 |
+
"mrr_at_20": 0.9783333333333333,
|
331 |
+
"mrr_at_50": 0.9783333333333333,
|
332 |
+
"mrr_at_100": 0.9783333333333333,
|
333 |
+
"naucs_at_1_max": 0.7605042016806716,
|
334 |
+
"naucs_at_1_std": -0.35732959850606716,
|
335 |
+
"naucs_at_1_diff1": 0.9738562091503253,
|
336 |
"naucs_at_3_max": 1.0,
|
337 |
"naucs_at_3_std": 1.0,
|
338 |
"naucs_at_3_diff1": 1.0,
|
|
|
352 |
"naucs_at_100_std": null,
|
353 |
"naucs_at_100_diff1": null
|
354 |
},
|
355 |
+
"data_dir/eval_vidore/tabfquad_test_subsampled": {
|
356 |
+
"ndcg_at_1": 0.85714,
|
357 |
+
"ndcg_at_3": 0.90523,
|
358 |
+
"ndcg_at_5": 0.91122,
|
359 |
+
"ndcg_at_10": 0.91807,
|
360 |
+
"ndcg_at_20": 0.92163,
|
361 |
+
"ndcg_at_50": 0.92385,
|
362 |
+
"ndcg_at_100": 0.92385,
|
363 |
+
"map_at_1": 0.85714,
|
364 |
+
"map_at_3": 0.89345,
|
365 |
+
"map_at_5": 0.89685,
|
366 |
+
"map_at_10": 0.89962,
|
367 |
+
"map_at_20": 0.90057,
|
368 |
+
"map_at_50": 0.90097,
|
369 |
+
"map_at_100": 0.90097,
|
370 |
+
"recall_at_1": 0.85714,
|
371 |
+
"recall_at_3": 0.93929,
|
372 |
+
"recall_at_5": 0.95357,
|
373 |
+
"recall_at_10": 0.975,
|
374 |
"recall_at_20": 0.98929,
|
375 |
"recall_at_50": 1.0,
|
376 |
"recall_at_100": 1.0,
|
377 |
+
"precision_at_1": 0.85714,
|
378 |
+
"precision_at_3": 0.3131,
|
379 |
+
"precision_at_5": 0.19071,
|
380 |
+
"precision_at_10": 0.0975,
|
381 |
"precision_at_20": 0.04946,
|
382 |
"precision_at_50": 0.02,
|
383 |
"precision_at_100": 0.01,
|
384 |
+
"mrr_at_1": 0.8571428571428571,
|
385 |
+
"mrr_at_3": 0.8928571428571429,
|
386 |
+
"mrr_at_5": 0.8955357142857143,
|
387 |
+
"mrr_at_10": 0.8989866780045351,
|
388 |
+
"mrr_at_20": 0.8999608080411652,
|
389 |
+
"mrr_at_50": 0.9003545809349381,
|
390 |
+
"mrr_at_100": 0.9003545809349381,
|
391 |
+
"naucs_at_1_max": 0.44880952380952394,
|
392 |
+
"naucs_at_1_std": 0.06635082604470473,
|
393 |
+
"naucs_at_1_diff1": 0.9110301263362479,
|
394 |
+
"naucs_at_3_max": 0.7531443950129105,
|
395 |
+
"naucs_at_3_std": 0.4460647003899606,
|
396 |
+
"naucs_at_3_diff1": 0.9288735101883916,
|
397 |
+
"naucs_at_5_max": 0.8075127486892179,
|
398 |
+
"naucs_at_5_std": 0.529124470300943,
|
399 |
+
"naucs_at_5_diff1": 0.917043740573152,
|
400 |
+
"naucs_at_10_max": 0.7902494331065706,
|
401 |
+
"naucs_at_10_std": 0.6329198346005056,
|
402 |
+
"naucs_at_10_diff1": 0.9626517273576021,
|
403 |
+
"naucs_at_20_max": 0.9564270152505505,
|
404 |
+
"naucs_at_20_std": 0.8638344226579515,
|
405 |
"naucs_at_20_diff1": 0.9564270152505505,
|
406 |
"naucs_at_50_max": 1.0,
|
407 |
"naucs_at_50_std": 1.0,
|
|
|
410 |
"naucs_at_100_std": 1.0,
|
411 |
"naucs_at_100_diff1": 1.0
|
412 |
},
|
413 |
+
"data_dir/eval_vidore/syntheticDocQA_government_reports_test": {
|
414 |
+
"ndcg_at_1": 0.92,
|
415 |
+
"ndcg_at_3": 0.96417,
|
416 |
+
"ndcg_at_5": 0.96417,
|
417 |
+
"ndcg_at_10": 0.9675,
|
418 |
+
"ndcg_at_20": 0.9675,
|
419 |
+
"ndcg_at_50": 0.9675,
|
420 |
+
"ndcg_at_100": 0.9675,
|
421 |
+
"map_at_1": 0.92,
|
422 |
+
"map_at_3": 0.955,
|
423 |
+
"map_at_5": 0.955,
|
424 |
+
"map_at_10": 0.95643,
|
425 |
+
"map_at_20": 0.95643,
|
426 |
+
"map_at_50": 0.95643,
|
427 |
+
"map_at_100": 0.95643,
|
428 |
+
"recall_at_1": 0.92,
|
429 |
+
"recall_at_3": 0.99,
|
430 |
"recall_at_5": 0.99,
|
431 |
"recall_at_10": 1.0,
|
432 |
"recall_at_20": 1.0,
|
433 |
"recall_at_50": 1.0,
|
434 |
"recall_at_100": 1.0,
|
435 |
+
"precision_at_1": 0.92,
|
436 |
+
"precision_at_3": 0.33,
|
437 |
"precision_at_5": 0.198,
|
438 |
"precision_at_10": 0.1,
|
439 |
"precision_at_20": 0.05,
|
440 |
"precision_at_50": 0.02,
|
441 |
"precision_at_100": 0.01,
|
442 |
+
"mrr_at_1": 0.92,
|
443 |
+
"mrr_at_3": 0.955,
|
444 |
+
"mrr_at_5": 0.955,
|
445 |
+
"mrr_at_10": 0.9564285714285714,
|
446 |
+
"mrr_at_20": 0.9564285714285714,
|
447 |
+
"mrr_at_50": 0.9564285714285714,
|
448 |
+
"mrr_at_100": 0.9564285714285714,
|
449 |
+
"naucs_at_1_max": 0.8768674136321195,
|
450 |
+
"naucs_at_1_std": 0.41940943043884304,
|
451 |
+
"naucs_at_1_diff1": 0.9673202614379083,
|
452 |
+
"naucs_at_3_max": 1.0,
|
453 |
+
"naucs_at_3_std": 0.8692810457516356,
|
454 |
+
"naucs_at_3_diff1": 1.0,
|
455 |
+
"naucs_at_5_max": 1.0,
|
456 |
+
"naucs_at_5_std": 0.8692810457516413,
|
457 |
"naucs_at_5_diff1": 1.0,
|
458 |
"naucs_at_10_max": 1.0,
|
459 |
"naucs_at_10_std": 1.0,
|
|
|
468 |
"naucs_at_100_std": null,
|
469 |
"naucs_at_100_diff1": null
|
470 |
},
|
471 |
+
"data_dir/eval_vidore/shiftproject_test": {
|
472 |
+
"ndcg_at_1": 0.78,
|
473 |
+
"ndcg_at_3": 0.8644,
|
474 |
+
"ndcg_at_5": 0.87302,
|
475 |
+
"ndcg_at_10": 0.8828,
|
476 |
+
"ndcg_at_20": 0.88795,
|
477 |
+
"ndcg_at_50": 0.88997,
|
478 |
+
"ndcg_at_100": 0.88997,
|
479 |
+
"map_at_1": 0.78,
|
480 |
+
"map_at_3": 0.845,
|
481 |
+
"map_at_5": 0.85,
|
482 |
+
"map_at_10": 0.8541,
|
483 |
+
"map_at_20": 0.85555,
|
484 |
+
"map_at_50": 0.85589,
|
485 |
+
"map_at_100": 0.85589,
|
486 |
+
"recall_at_1": 0.78,
|
487 |
+
"recall_at_3": 0.92,
|
488 |
"recall_at_5": 0.94,
|
489 |
+
"recall_at_10": 0.97,
|
490 |
+
"recall_at_20": 0.99,
|
491 |
"recall_at_50": 1.0,
|
492 |
"recall_at_100": 1.0,
|
493 |
+
"precision_at_1": 0.78,
|
494 |
+
"precision_at_3": 0.30667,
|
495 |
"precision_at_5": 0.188,
|
496 |
+
"precision_at_10": 0.097,
|
497 |
+
"precision_at_20": 0.0495,
|
498 |
"precision_at_50": 0.02,
|
499 |
"precision_at_100": 0.01,
|
500 |
+
"mrr_at_1": 0.81,
|
501 |
+
"mrr_at_3": 0.8633333333333333,
|
502 |
+
"mrr_at_5": 0.8658333333333332,
|
503 |
+
"mrr_at_10": 0.8699285714285715,
|
504 |
+
"mrr_at_20": 0.871412087912088,
|
505 |
+
"mrr_at_50": 0.8717454212454213,
|
506 |
+
"mrr_at_100": 0.8717454212454213,
|
507 |
+
"naucs_at_1_max": -0.24755413363008374,
|
508 |
+
"naucs_at_1_std": -0.6164510594890337,
|
509 |
+
"naucs_at_1_diff1": 0.8162006769601703,
|
510 |
+
"naucs_at_3_max": 0.2243814192343627,
|
511 |
+
"naucs_at_3_std": -0.23225957049486393,
|
512 |
+
"naucs_at_3_diff1": 0.8544000933706815,
|
513 |
+
"naucs_at_5_max": -0.012371615312794324,
|
514 |
+
"naucs_at_5_std": -0.5504201680672273,
|
515 |
+
"naucs_at_5_diff1": 0.9128540305010897,
|
516 |
+
"naucs_at_10_max": -0.049486461251166146,
|
517 |
+
"naucs_at_10_std": -0.27591036414565706,
|
518 |
+
"naucs_at_10_diff1": 0.9128540305010848,
|
519 |
+
"naucs_at_20_max": 0.7222222222222276,
|
520 |
+
"naucs_at_20_std": 0.5541549953314738,
|
521 |
+
"naucs_at_20_diff1": 0.8692810457516413,
|
522 |
"naucs_at_50_max": null,
|
523 |
"naucs_at_50_std": null,
|
524 |
"naucs_at_50_diff1": null,
|
|
|
526 |
"naucs_at_100_std": null,
|
527 |
"naucs_at_100_diff1": null
|
528 |
},
|
529 |
+
"data_dir/eval_vidore/syntheticDocQA_artificial_intelligence_test": {
|
530 |
+
"ndcg_at_1": 0.99,
|
531 |
+
"ndcg_at_3": 0.99631,
|
532 |
+
"ndcg_at_5": 0.99631,
|
533 |
+
"ndcg_at_10": 0.99631,
|
534 |
+
"ndcg_at_20": 0.99631,
|
535 |
+
"ndcg_at_50": 0.99631,
|
536 |
+
"ndcg_at_100": 0.99631,
|
537 |
+
"map_at_1": 0.99,
|
538 |
+
"map_at_3": 0.995,
|
539 |
+
"map_at_5": 0.995,
|
540 |
+
"map_at_10": 0.995,
|
541 |
+
"map_at_20": 0.995,
|
542 |
+
"map_at_50": 0.995,
|
543 |
+
"map_at_100": 0.995,
|
544 |
+
"recall_at_1": 0.99,
|
545 |
"recall_at_3": 1.0,
|
546 |
"recall_at_5": 1.0,
|
547 |
"recall_at_10": 1.0,
|
548 |
"recall_at_20": 1.0,
|
549 |
"recall_at_50": 1.0,
|
550 |
"recall_at_100": 1.0,
|
551 |
+
"precision_at_1": 0.99,
|
552 |
"precision_at_3": 0.33333,
|
553 |
"precision_at_5": 0.2,
|
554 |
"precision_at_10": 0.1,
|
555 |
"precision_at_20": 0.05,
|
556 |
"precision_at_50": 0.02,
|
557 |
"precision_at_100": 0.01,
|
558 |
+
"mrr_at_1": 0.99,
|
559 |
+
"mrr_at_3": 0.995,
|
560 |
+
"mrr_at_5": 0.995,
|
561 |
+
"mrr_at_10": 0.995,
|
562 |
+
"mrr_at_20": 0.995,
|
563 |
+
"mrr_at_50": 0.995,
|
564 |
+
"mrr_at_100": 0.995,
|
565 |
+
"naucs_at_1_max": 0.8692810457516276,
|
566 |
+
"naucs_at_1_std": -0.5634920634920657,
|
567 |
"naucs_at_1_diff1": 1.0,
|
568 |
"naucs_at_3_max": 1.0,
|
569 |
"naucs_at_3_std": 1.0,
|