Update results.json
Browse files- results.json +465 -0
results.json
CHANGED
@@ -4,6 +4,471 @@
|
|
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,
|
|
|
4 |
"vidore_benchmark_version": "4.0.3.dev20+g2d72668"
|
5 |
},
|
6 |
"metrics": {
|
7 |
+
"vidore/restaurant_esg_reports_beir": {"ndcg_at_1": 0.64103, "ndcg_at_3": 0.67538, "ndcg_at_5": 0.68397, "ndcg_at_10": 0.71199, "ndcg_at_20": 0.73099, "ndcg_at_50": 0.75581, "ndcg_at_100": 0.76163, "map_at_1": 0.43942, "map_at_3": 0.58034, "map_at_5": 0.6105, "map_at_10": 0.63715, "map_at_20": 0.64674, "map_at_50": 0.65463, "map_at_100": 0.65653, "recall_at_1": 0.43942, "recall_at_3": 0.6766, "recall_at_5": 0.73558, "recall_at_10": 0.81426, "recall_at_20": 0.87567, "recall_at_50": 0.95485, "recall_at_100": 0.981, "precision_at_1": 0.65385, "precision_at_3": 0.39744, "precision_at_5": 0.27692, "precision_at_10": 0.16538, "precision_at_20": 0.09423, "precision_at_50": 0.04346, "precision_at_100": 0.02308, "mrr_at_1": 0.6730769230769231, "mrr_at_3": 0.7467948717948718, "mrr_at_5": 0.7592948717948718, "mrr_at_10": 0.7647893772893772, "mrr_at_20": 0.7647893772893772, "mrr_at_50": 0.76724122651542, "mrr_at_100": 0.76724122651542, "naucs_at_1_max": 0.10629249714250551, "naucs_at_1_std": 0.03656703481974433, "naucs_at_1_diff1": 0.6471348946136236, "naucs_at_3_max": -0.04531273341377843, "naucs_at_3_std": 0.00041838369923711004, "naucs_at_3_diff1": -0.10904002079315368, "naucs_at_5_max": -0.11437346877355879, "naucs_at_5_std": -0.03247506128676773, "naucs_at_5_diff1": -0.23163739837531055, "naucs_at_10_max": -0.17966299098993738, "naucs_at_10_std": -0.08845607083585832, "naucs_at_10_diff1": -0.3668906677620788, "naucs_at_20_max": -0.1623997659302278, "naucs_at_20_std": -0.05328921373458377, "naucs_at_20_diff1": -0.4139154609733948, "naucs_at_50_max": -0.15835976853630981, "naucs_at_50_std": -0.042923187520787366, "naucs_at_50_diff1": -0.45626822378009313, "naucs_at_100_max": -0.14433851613678755, "naucs_at_100_std": -0.03148299510892002, "naucs_at_100_diff1": -0.44576138476398025},
|
8 |
+
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
|
9 |
+
"ndcg_at_1": 0.60345,
|
10 |
+
"ndcg_at_3": 0.59658,
|
11 |
+
"ndcg_at_5": 0.56521,
|
12 |
+
"ndcg_at_10": 0.55055,
|
13 |
+
"ndcg_at_20": 0.57899,
|
14 |
+
"ndcg_at_50": 0.65246,
|
15 |
+
"ndcg_at_100": 0.68858,
|
16 |
+
"map_at_1": 0.08192,
|
17 |
+
"map_at_3": 0.18869,
|
18 |
+
"map_at_5": 0.23861,
|
19 |
+
"map_at_10": 0.30685,
|
20 |
+
"map_at_20": 0.36485,
|
21 |
+
"map_at_50": 0.42784,
|
22 |
+
"map_at_100": 0.45362,
|
23 |
+
"recall_at_1": 0.08192,
|
24 |
+
"recall_at_3": 0.23525,
|
25 |
+
"recall_at_5": 0.31079,
|
26 |
+
"recall_at_10": 0.43833,
|
27 |
+
"recall_at_20": 0.58306,
|
28 |
+
"recall_at_50": 0.78859,
|
29 |
+
"recall_at_100": 0.90965,
|
30 |
+
"precision_at_1": 0.60345,
|
31 |
+
"precision_at_3": 0.5546,
|
32 |
+
"precision_at_5": 0.49138,
|
33 |
+
"precision_at_10": 0.39914,
|
34 |
+
"precision_at_20": 0.30539,
|
35 |
+
"precision_at_50": 0.1981,
|
36 |
+
"precision_at_100": 0.12647,
|
37 |
+
"mrr_at_1": 0.5948275862068966,
|
38 |
+
"mrr_at_3": 0.7140804597701149,
|
39 |
+
"mrr_at_5": 0.7311063218390805,
|
40 |
+
"mrr_at_10": 0.7372383004926109,
|
41 |
+
"mrr_at_20": 0.7380691285134744,
|
42 |
+
"mrr_at_50": 0.738889335917265,
|
43 |
+
"mrr_at_100": 0.738889335917265,
|
44 |
+
"naucs_at_1_max": 0.009301400086149124,
|
45 |
+
"naucs_at_1_std": -0.018176205759631064,
|
46 |
+
"naucs_at_1_diff1": 0.06589141538556753,
|
47 |
+
"naucs_at_3_max": 0.03608007053002765,
|
48 |
+
"naucs_at_3_std": 0.045332981794521165,
|
49 |
+
"naucs_at_3_diff1": 0.0027274204838523214,
|
50 |
+
"naucs_at_5_max": 0.06351874275538175,
|
51 |
+
"naucs_at_5_std": 0.09161670694703962,
|
52 |
+
"naucs_at_5_diff1": 0.030104357247264922,
|
53 |
+
"naucs_at_10_max": 0.09045732284339944,
|
54 |
+
"naucs_at_10_std": 0.11937912992266166,
|
55 |
+
"naucs_at_10_diff1": -0.007723827231040398,
|
56 |
+
"naucs_at_20_max": 0.04097490582062997,
|
57 |
+
"naucs_at_20_std": 0.11121740670187244,
|
58 |
+
"naucs_at_20_diff1": -0.04080919911505186,
|
59 |
+
"naucs_at_50_max": -0.04431654376754045,
|
60 |
+
"naucs_at_50_std": 0.1075378398002067,
|
61 |
+
"naucs_at_50_diff1": -0.0408768243788732,
|
62 |
+
"naucs_at_100_max": -0.08194156783211,
|
63 |
+
"naucs_at_100_std": 0.08152221906964778,
|
64 |
+
"naucs_at_100_diff1": -0.002462405639259035
|
65 |
+
},
|
66 |
+
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
67 |
+
"ndcg_at_1": 0.44444,
|
68 |
+
"ndcg_at_3": 0.52927,
|
69 |
+
"ndcg_at_5": 0.53193,
|
70 |
+
"ndcg_at_10": 0.55273,
|
71 |
+
"ndcg_at_20": 0.57791,
|
72 |
+
"ndcg_at_50": 0.62959,
|
73 |
+
"ndcg_at_100": 0.64947,
|
74 |
+
"map_at_1": 0.19923,
|
75 |
+
"map_at_3": 0.31897,
|
76 |
+
"map_at_5": 0.3681,
|
77 |
+
"map_at_10": 0.4284,
|
78 |
+
"map_at_20": 0.45565,
|
79 |
+
"map_at_50": 0.47849,
|
80 |
+
"map_at_100": 0.48445,
|
81 |
+
"recall_at_1": 0.19923,
|
82 |
+
"recall_at_3": 0.43016,
|
83 |
+
"recall_at_5": 0.51283,
|
84 |
+
"recall_at_10": 0.63101,
|
85 |
+
"recall_at_20": 0.7193,
|
86 |
+
"recall_at_50": 0.86749,
|
87 |
+
"recall_at_100": 0.93786,
|
88 |
+
"precision_at_1": 0.44444,
|
89 |
+
"precision_at_3": 0.39815,
|
90 |
+
"precision_at_5": 0.33611,
|
91 |
+
"precision_at_10": 0.25,
|
92 |
+
"precision_at_20": 0.15347,
|
93 |
+
"precision_at_50": 0.08167,
|
94 |
+
"precision_at_100": 0.04556,
|
95 |
+
"mrr_at_1": 0.4444444444444444,
|
96 |
+
"mrr_at_3": 0.6041666666666666,
|
97 |
+
"mrr_at_5": 0.6111111111111112,
|
98 |
+
"mrr_at_10": 0.6134259259259259,
|
99 |
+
"mrr_at_20": 0.6134259259259259,
|
100 |
+
"mrr_at_50": 0.6156871267846877,
|
101 |
+
"mrr_at_100": 0.6160388005738615,
|
102 |
+
"naucs_at_1_max": -0.007676494689249098,
|
103 |
+
"naucs_at_1_std": 0.15632886231764911,
|
104 |
+
"naucs_at_1_diff1": 0.3454147669831923,
|
105 |
+
"naucs_at_3_max": -0.21520431732796824,
|
106 |
+
"naucs_at_3_std": -0.039307896873910286,
|
107 |
+
"naucs_at_3_diff1": 0.07075823324379214,
|
108 |
+
"naucs_at_5_max": -0.23427920743418434,
|
109 |
+
"naucs_at_5_std": -0.04955213973003769,
|
110 |
+
"naucs_at_5_diff1": 0.03587555672187707,
|
111 |
+
"naucs_at_10_max": -0.32076687527735803,
|
112 |
+
"naucs_at_10_std": -0.08584531062590048,
|
113 |
+
"naucs_at_10_diff1": -0.13920437910700148,
|
114 |
+
"naucs_at_20_max": -0.3500838034005256,
|
115 |
+
"naucs_at_20_std": -0.11679539412969686,
|
116 |
+
"naucs_at_20_diff1": -0.2051894549829469,
|
117 |
+
"naucs_at_50_max": -0.4102497000902005,
|
118 |
+
"naucs_at_50_std": -0.1409315271751862,
|
119 |
+
"naucs_at_50_diff1": -0.16443764913412845,
|
120 |
+
"naucs_at_100_max": -0.43730180953377223,
|
121 |
+
"naucs_at_100_std": -0.17380745870110292,
|
122 |
+
"naucs_at_100_diff1": -0.19442949153976513
|
123 |
+
},
|
124 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
|
125 |
+
"ndcg_at_1": 0.61875,
|
126 |
+
"ndcg_at_3": 0.61406,
|
127 |
+
"ndcg_at_5": 0.63644,
|
128 |
+
"ndcg_at_10": 0.67591,
|
129 |
+
"ndcg_at_20": 0.70178,
|
130 |
+
"ndcg_at_50": 0.72212,
|
131 |
+
"ndcg_at_100": 0.7297,
|
132 |
+
"map_at_1": 0.38142,
|
133 |
+
"map_at_3": 0.50057,
|
134 |
+
"map_at_5": 0.54282,
|
135 |
+
"map_at_10": 0.58278,
|
136 |
+
"map_at_20": 0.59965,
|
137 |
+
"map_at_50": 0.60789,
|
138 |
+
"map_at_100": 0.60942,
|
139 |
+
"recall_at_1": 0.38142,
|
140 |
+
"recall_at_3": 0.55686,
|
141 |
+
"recall_at_5": 0.65567,
|
142 |
+
"recall_at_10": 0.77349,
|
143 |
+
"recall_at_20": 0.84542,
|
144 |
+
"recall_at_50": 0.902,
|
145 |
+
"recall_at_100": 0.93314,
|
146 |
+
"precision_at_1": 0.61875,
|
147 |
+
"precision_at_3": 0.38333,
|
148 |
+
"precision_at_5": 0.28875,
|
149 |
+
"precision_at_10": 0.18875,
|
150 |
+
"precision_at_20": 0.11063,
|
151 |
+
"precision_at_50": 0.052,
|
152 |
+
"precision_at_100": 0.02756,
|
153 |
+
"mrr_at_1": 0.6,
|
154 |
+
"mrr_at_3": 0.6947916666666667,
|
155 |
+
"mrr_at_5": 0.7104166666666667,
|
156 |
+
"mrr_at_10": 0.7197544642857143,
|
157 |
+
"mrr_at_20": 0.7207690746753247,
|
158 |
+
"mrr_at_50": 0.7216319385110503,
|
159 |
+
"mrr_at_100": 0.7218020773999393,
|
160 |
+
"naucs_at_1_max": 0.23570942089460648,
|
161 |
+
"naucs_at_1_std": -0.0331808109585888,
|
162 |
+
"naucs_at_1_diff1": 0.38829894385449926,
|
163 |
+
"naucs_at_3_max": -0.02996939892755872,
|
164 |
+
"naucs_at_3_std": -0.06455703309969216,
|
165 |
+
"naucs_at_3_diff1": -0.10409043693090879,
|
166 |
+
"naucs_at_5_max": -0.10452188626653831,
|
167 |
+
"naucs_at_5_std": -0.052524231286355125,
|
168 |
+
"naucs_at_5_diff1": -0.26201383842532566,
|
169 |
+
"naucs_at_10_max": -0.18753439904110775,
|
170 |
+
"naucs_at_10_std": -0.07594574430351896,
|
171 |
+
"naucs_at_10_diff1": -0.3404263646481817,
|
172 |
+
"naucs_at_20_max": -0.20945097879456231,
|
173 |
+
"naucs_at_20_std": -0.04291331785264603,
|
174 |
+
"naucs_at_20_diff1": -0.35991045256760157,
|
175 |
+
"naucs_at_50_max": -0.25078519595626036,
|
176 |
+
"naucs_at_50_std": -0.021452523948669356,
|
177 |
+
"naucs_at_50_diff1": -0.3863780246795678,
|
178 |
+
"naucs_at_100_max": -0.2723431611743009,
|
179 |
+
"naucs_at_100_std": -0.031237471793638266,
|
180 |
+
"naucs_at_100_diff1": -0.38639136112161093
|
181 |
+
},
|
182 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
|
183 |
+
"ndcg_at_1": 0.57895,
|
184 |
+
"ndcg_at_3": 0.57099,
|
185 |
+
"ndcg_at_5": 0.57396,
|
186 |
+
"ndcg_at_10": 0.6394,
|
187 |
+
"ndcg_at_20": 0.67256,
|
188 |
+
"ndcg_at_50": 0.70473,
|
189 |
+
"ndcg_at_100": 0.71518,
|
190 |
+
"map_at_1": 0.26466,
|
191 |
+
"map_at_3": 0.41771,
|
192 |
+
"map_at_5": 0.45328,
|
193 |
+
"map_at_10": 0.515,
|
194 |
+
"map_at_20": 0.53681,
|
195 |
+
"map_at_50": 0.55475,
|
196 |
+
"map_at_100": 0.55975,
|
197 |
+
"recall_at_1": 0.26466,
|
198 |
+
"recall_at_3": 0.50881,
|
199 |
+
"recall_at_5": 0.57932,
|
200 |
+
"recall_at_10": 0.77663,
|
201 |
+
"recall_at_20": 0.8768,
|
202 |
+
"recall_at_50": 0.96898,
|
203 |
+
"recall_at_100": 1.0,
|
204 |
+
"precision_at_1": 0.57895,
|
205 |
+
"precision_at_3": 0.39766,
|
206 |
+
"precision_at_5": 0.29123,
|
207 |
+
"precision_at_10": 0.21053,
|
208 |
+
"precision_at_20": 0.13246,
|
209 |
+
"precision_at_50": 0.07123,
|
210 |
+
"precision_at_100": 0.03895,
|
211 |
+
"mrr_at_1": 0.5614035087719298,
|
212 |
+
"mrr_at_3": 0.6637426900584795,
|
213 |
+
"mrr_at_5": 0.6751461988304094,
|
214 |
+
"mrr_at_10": 0.6886173767752715,
|
215 |
+
"mrr_at_20": 0.6913087643350802,
|
216 |
+
"mrr_at_50": 0.6925429103060682,
|
217 |
+
"mrr_at_100": 0.6925429103060682,
|
218 |
+
"naucs_at_1_max": -0.32399679124866293,
|
219 |
+
"naucs_at_1_std": -0.3157496852536844,
|
220 |
+
"naucs_at_1_diff1": 0.059217413521438306,
|
221 |
+
"naucs_at_3_max": -0.16317940152105928,
|
222 |
+
"naucs_at_3_std": -0.036766880845353206,
|
223 |
+
"naucs_at_3_diff1": 0.13451653330920363,
|
224 |
+
"naucs_at_5_max": -0.18872080560435078,
|
225 |
+
"naucs_at_5_std": -0.08965899629213353,
|
226 |
+
"naucs_at_5_diff1": 0.09733357617902798,
|
227 |
+
"naucs_at_10_max": -0.21096127425243222,
|
228 |
+
"naucs_at_10_std": -0.0492682492736064,
|
229 |
+
"naucs_at_10_diff1": 0.06579043413332678,
|
230 |
+
"naucs_at_20_max": -0.3151765999140926,
|
231 |
+
"naucs_at_20_std": -0.11272929289257284,
|
232 |
+
"naucs_at_20_diff1": -0.030784322032566636,
|
233 |
+
"naucs_at_50_max": -0.29489025135650376,
|
234 |
+
"naucs_at_50_std": -0.008523958191869246,
|
235 |
+
"naucs_at_50_diff1": -0.11796822928434904,
|
236 |
+
"naucs_at_100_max": -0.2661970083875134,
|
237 |
+
"naucs_at_100_std": 0.05555820249689567,
|
238 |
+
"naucs_at_100_diff1": -0.1271611921091859
|
239 |
+
},
|
240 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
|
241 |
+
"ndcg_at_1": 0.55702,
|
242 |
+
"ndcg_at_3": 0.5542,
|
243 |
+
"ndcg_at_5": 0.5738,
|
244 |
+
"ndcg_at_10": 0.62953,
|
245 |
+
"ndcg_at_20": 0.67065,
|
246 |
+
"ndcg_at_50": 0.6964,
|
247 |
+
"ndcg_at_100": 0.70872,
|
248 |
+
"map_at_1": 0.25589,
|
249 |
+
"map_at_3": 0.40701,
|
250 |
+
"map_at_5": 0.45304,
|
251 |
+
"map_at_10": 0.5087,
|
252 |
+
"map_at_20": 0.53389,
|
253 |
+
"map_at_50": 0.5501,
|
254 |
+
"map_at_100": 0.55542,
|
255 |
+
"recall_at_1": 0.25589,
|
256 |
+
"recall_at_3": 0.49373,
|
257 |
+
"recall_at_5": 0.59174,
|
258 |
+
"recall_at_10": 0.76938,
|
259 |
+
"recall_at_20": 0.89178,
|
260 |
+
"recall_at_50": 0.9594,
|
261 |
+
"recall_at_100": 1.0,
|
262 |
+
"precision_at_1": 0.55702,
|
263 |
+
"precision_at_3": 0.3845,
|
264 |
+
"precision_at_5": 0.29649,
|
265 |
+
"precision_at_10": 0.20746,
|
266 |
+
"precision_at_20": 0.13487,
|
267 |
+
"precision_at_50": 0.0707,
|
268 |
+
"precision_at_100": 0.03895,
|
269 |
+
"mrr_at_1": 0.5570175438596491,
|
270 |
+
"mrr_at_3": 0.6571637426900585,
|
271 |
+
"mrr_at_5": 0.6698830409356724,
|
272 |
+
"mrr_at_10": 0.683766708437761,
|
273 |
+
"mrr_at_20": 0.687599964534949,
|
274 |
+
"mrr_at_50": 0.6879085010276961,
|
275 |
+
"mrr_at_100": 0.6880572205275953,
|
276 |
+
"naucs_at_1_max": -0.17166276074798967,
|
277 |
+
"naucs_at_1_std": -0.20325235499471186,
|
278 |
+
"naucs_at_1_diff1": 0.33001833715444423,
|
279 |
+
"naucs_at_3_max": -0.04474887443402487,
|
280 |
+
"naucs_at_3_std": -0.008560331928141176,
|
281 |
+
"naucs_at_3_diff1": 0.1746255699902219,
|
282 |
+
"naucs_at_5_max": -0.08458531884834858,
|
283 |
+
"naucs_at_5_std": -0.06118868392476525,
|
284 |
+
"naucs_at_5_diff1": 0.13235525060593817,
|
285 |
+
"naucs_at_10_max": -0.12880215182381638,
|
286 |
+
"naucs_at_10_std": -0.08311726109553826,
|
287 |
+
"naucs_at_10_diff1": 0.11900519462159719,
|
288 |
+
"naucs_at_20_max": -0.18439650375622735,
|
289 |
+
"naucs_at_20_std": -0.051821500134533655,
|
290 |
+
"naucs_at_20_diff1": -0.015123572562768748,
|
291 |
+
"naucs_at_50_max": -0.20702547660326365,
|
292 |
+
"naucs_at_50_std": 0.02211997502899773,
|
293 |
+
"naucs_at_50_diff1": -0.1539679823951051,
|
294 |
+
"naucs_at_100_max": -0.1731060459048004,
|
295 |
+
"naucs_at_100_std": 0.1019715434458989,
|
296 |
+
"naucs_at_100_diff1": -0.1841288831466728
|
297 |
+
},
|
298 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
|
299 |
+
"ndcg_at_1": 0.57812,
|
300 |
+
"ndcg_at_3": 0.58744,
|
301 |
+
"ndcg_at_5": 0.61127,
|
302 |
+
"ndcg_at_10": 0.64614,
|
303 |
+
"ndcg_at_20": 0.67298,
|
304 |
+
"ndcg_at_50": 0.6947,
|
305 |
+
"ndcg_at_100": 0.70357,
|
306 |
+
"map_at_1": 0.35834,
|
307 |
+
"map_at_3": 0.47597,
|
308 |
+
"map_at_5": 0.51819,
|
309 |
+
"map_at_10": 0.55455,
|
310 |
+
"map_at_20": 0.57016,
|
311 |
+
"map_at_50": 0.5782,
|
312 |
+
"map_at_100": 0.58034,
|
313 |
+
"recall_at_1": 0.35834,
|
314 |
+
"recall_at_3": 0.54214,
|
315 |
+
"recall_at_5": 0.63727,
|
316 |
+
"recall_at_10": 0.74383,
|
317 |
+
"recall_at_20": 0.82133,
|
318 |
+
"recall_at_50": 0.88659,
|
319 |
+
"recall_at_100": 0.91866,
|
320 |
+
"precision_at_1": 0.57812,
|
321 |
+
"precision_at_3": 0.3651,
|
322 |
+
"precision_at_5": 0.28,
|
323 |
+
"precision_at_10": 0.18,
|
324 |
+
"precision_at_20": 0.10617,
|
325 |
+
"precision_at_50": 0.05,
|
326 |
+
"precision_at_100": 0.02695,
|
327 |
+
"mrr_at_1": 0.5671875,
|
328 |
+
"mrr_at_3": 0.6708333333333333,
|
329 |
+
"mrr_at_5": 0.6866145833333334,
|
330 |
+
"mrr_at_10": 0.6939360119047618,
|
331 |
+
"mrr_at_20": 0.6963204666729361,
|
332 |
+
"mrr_at_50": 0.6971792252566347,
|
333 |
+
"mrr_at_100": 0.6973040137004454,
|
334 |
+
"naucs_at_1_max": 0.22350385772789982,
|
335 |
+
"naucs_at_1_std": -0.014236260379664127,
|
336 |
+
"naucs_at_1_diff1": 0.415396972645202,
|
337 |
+
"naucs_at_3_max": 0.05168321374193644,
|
338 |
+
"naucs_at_3_std": -0.05262932689279111,
|
339 |
+
"naucs_at_3_diff1": -0.046426105116023936,
|
340 |
+
"naucs_at_5_max": -0.019935793098795593,
|
341 |
+
"naucs_at_5_std": -0.07180552504536146,
|
342 |
+
"naucs_at_5_diff1": -0.15736139387093928,
|
343 |
+
"naucs_at_10_max": -0.1020058048777736,
|
344 |
+
"naucs_at_10_std": -0.09370704449884888,
|
345 |
+
"naucs_at_10_diff1": -0.23614803376814614,
|
346 |
+
"naucs_at_20_max": -0.13810591303119216,
|
347 |
+
"naucs_at_20_std": -0.0692107572861515,
|
348 |
+
"naucs_at_20_diff1": -0.28493482904408224,
|
349 |
+
"naucs_at_50_max": -0.17286447176352046,
|
350 |
+
"naucs_at_50_std": -0.04984221651971845,
|
351 |
+
"naucs_at_50_diff1": -0.317010129235068,
|
352 |
+
"naucs_at_100_max": -0.18980306870058375,
|
353 |
+
"naucs_at_100_std": -0.048954124365436114,
|
354 |
+
"naucs_at_100_diff1": -0.3281886367637723
|
355 |
+
},
|
356 |
+
"vidore/synthetic_axa_filtered_v1.0": {
|
357 |
+
"ndcg_at_1": 0.44444,
|
358 |
+
"ndcg_at_3": 0.55779,
|
359 |
+
"ndcg_at_5": 0.60297,
|
360 |
+
"ndcg_at_10": 0.63112,
|
361 |
+
"ndcg_at_20": 0.65055,
|
362 |
+
"ndcg_at_50": 0.69129,
|
363 |
+
"ndcg_at_100": 0.70318,
|
364 |
+
"map_at_1": 0.22361,
|
365 |
+
"map_at_3": 0.34019,
|
366 |
+
"map_at_5": 0.42558,
|
367 |
+
"map_at_10": 0.50246,
|
368 |
+
"map_at_20": 0.53023,
|
369 |
+
"map_at_50": 0.54858,
|
370 |
+
"map_at_100": 0.55304,
|
371 |
+
"recall_at_1": 0.22361,
|
372 |
+
"recall_at_3": 0.43907,
|
373 |
+
"recall_at_5": 0.59758,
|
374 |
+
"recall_at_10": 0.75267,
|
375 |
+
"recall_at_20": 0.82791,
|
376 |
+
"recall_at_50": 0.94587,
|
377 |
+
"recall_at_100": 0.9784,
|
378 |
+
"precision_at_1": 0.44444,
|
379 |
+
"precision_at_3": 0.42593,
|
380 |
+
"precision_at_5": 0.4,
|
381 |
+
"precision_at_10": 0.29444,
|
382 |
+
"precision_at_20": 0.175,
|
383 |
+
"precision_at_50": 0.08556,
|
384 |
+
"precision_at_100": 0.04611,
|
385 |
+
"mrr_at_1": 0.4444444444444444,
|
386 |
+
"mrr_at_3": 0.6111111111111112,
|
387 |
+
"mrr_at_5": 0.625,
|
388 |
+
"mrr_at_10": 0.6342592592592592,
|
389 |
+
"mrr_at_20": 0.6342592592592592,
|
390 |
+
"mrr_at_50": 0.6367845117845118,
|
391 |
+
"mrr_at_100": 0.6367845117845118,
|
392 |
+
"naucs_at_1_max": 0.27180734937990775,
|
393 |
+
"naucs_at_1_std": 0.1460001284215161,
|
394 |
+
"naucs_at_1_diff1": 0.52680845013576,
|
395 |
+
"naucs_at_3_max": -0.4472601618035251,
|
396 |
+
"naucs_at_3_std": -0.35334842300017605,
|
397 |
+
"naucs_at_3_diff1": -0.022038941836526545,
|
398 |
+
"naucs_at_5_max": -0.5746685319786979,
|
399 |
+
"naucs_at_5_std": -0.45581287349947885,
|
400 |
+
"naucs_at_5_diff1": -0.02909625842935311,
|
401 |
+
"naucs_at_10_max": -0.6670105211539744,
|
402 |
+
"naucs_at_10_std": -0.4579454710599414,
|
403 |
+
"naucs_at_10_diff1": -0.291350928264914,
|
404 |
+
"naucs_at_20_max": -0.7088454526103415,
|
405 |
+
"naucs_at_20_std": -0.45884776633256535,
|
406 |
+
"naucs_at_20_diff1": -0.39562206735708155,
|
407 |
+
"naucs_at_50_max": -0.7078100142972502,
|
408 |
+
"naucs_at_50_std": -0.4315828703198929,
|
409 |
+
"naucs_at_50_diff1": -0.37094602463897214,
|
410 |
+
"naucs_at_100_max": -0.7059796119743438,
|
411 |
+
"naucs_at_100_std": -0.400631653419931,
|
412 |
+
"naucs_at_100_diff1": -0.33114628268848284
|
413 |
+
},
|
414 |
+
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
|
415 |
+
"ndcg_at_1": 0.67241,
|
416 |
+
"ndcg_at_3": 0.64169,
|
417 |
+
"ndcg_at_5": 0.5978,
|
418 |
+
"ndcg_at_10": 0.58577,
|
419 |
+
"ndcg_at_20": 0.61496,
|
420 |
+
"ndcg_at_50": 0.6772,
|
421 |
+
"ndcg_at_100": 0.71432,
|
422 |
+
"map_at_1": 0.08152,
|
423 |
+
"map_at_3": 0.20404,
|
424 |
+
"map_at_5": 0.2537,
|
425 |
+
"map_at_10": 0.32889,
|
426 |
+
"map_at_20": 0.39447,
|
427 |
+
"map_at_50": 0.4536,
|
428 |
+
"map_at_100": 0.48141,
|
429 |
+
"recall_at_1": 0.08152,
|
430 |
+
"recall_at_3": 0.2494,
|
431 |
+
"recall_at_5": 0.32267,
|
432 |
+
"recall_at_10": 0.45814,
|
433 |
+
"recall_at_20": 0.61677,
|
434 |
+
"recall_at_50": 0.80189,
|
435 |
+
"recall_at_100": 0.92313,
|
436 |
+
"precision_at_1": 0.67241,
|
437 |
+
"precision_at_3": 0.59195,
|
438 |
+
"precision_at_5": 0.51379,
|
439 |
+
"precision_at_10": 0.42586,
|
440 |
+
"precision_at_20": 0.325,
|
441 |
+
"precision_at_50": 0.20138,
|
442 |
+
"precision_at_100": 0.12983,
|
443 |
+
"mrr_at_1": 0.6724137931034483,
|
444 |
+
"mrr_at_3": 0.7729885057471265,
|
445 |
+
"mrr_at_5": 0.7807471264367816,
|
446 |
+
"mrr_at_10": 0.7857758620689655,
|
447 |
+
"mrr_at_20": 0.7868534482758621,
|
448 |
+
"mrr_at_50": 0.7876030734632684,
|
449 |
+
"mrr_at_100": 0.7876030734632684,
|
450 |
+
"naucs_at_1_max": 0.34454681161877004,
|
451 |
+
"naucs_at_1_std": 0.5235431895381841,
|
452 |
+
"naucs_at_1_diff1": -0.08387631081097016,
|
453 |
+
"naucs_at_3_max": 0.08884531420395679,
|
454 |
+
"naucs_at_3_std": 0.2382734233882671,
|
455 |
+
"naucs_at_3_diff1": -0.1871866677817215,
|
456 |
+
"naucs_at_5_max": 0.01311909348957855,
|
457 |
+
"naucs_at_5_std": 0.2167381673457986,
|
458 |
+
"naucs_at_5_diff1": -0.14497179289018872,
|
459 |
+
"naucs_at_10_max": 0.14293369671235354,
|
460 |
+
"naucs_at_10_std": 0.22265260242487017,
|
461 |
+
"naucs_at_10_diff1": -0.09048933555139305,
|
462 |
+
"naucs_at_20_max": 0.08115085333286959,
|
463 |
+
"naucs_at_20_std": 0.20688202040577058,
|
464 |
+
"naucs_at_20_diff1": -0.15069532949644948,
|
465 |
+
"naucs_at_50_max": -0.010126566692404412,
|
466 |
+
"naucs_at_50_std": 0.24164336672801914,
|
467 |
+
"naucs_at_50_diff1": -0.10468292902065172,
|
468 |
+
"naucs_at_100_max": -0.04114659355878923,
|
469 |
+
"naucs_at_100_std": 0.2129831852026439,
|
470 |
+
"naucs_at_100_diff1": -0.03795755522744344
|
471 |
+
},
|
472 |
"data_dir/eval_vidore/arxivqa_test_subsampled": {
|
473 |
"ndcg_at_1": 0.856,
|
474 |
"ndcg_at_3": 0.88745,
|