Upload results.json
Browse files- results.json +588 -0
results.json
ADDED
@@ -0,0 +1,588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"timestamp": "2025-01-30T14:08:26.760026",
|
4 |
+
"vidore_benchmark_version": "4.0.3.dev20+g2d72668"
|
5 |
+
},
|
6 |
+
"metrics": {
|
7 |
+
"arxivqa_test_subsampled": {
|
8 |
+
"ndcg_at_1": 0.83,
|
9 |
+
"ndcg_at_3": 0.87855,
|
10 |
+
"ndcg_at_5": 0.88517,
|
11 |
+
"ndcg_at_10": 0.8947,
|
12 |
+
"ndcg_at_20": 0.89981,
|
13 |
+
"ndcg_at_50": 0.90189,
|
14 |
+
"ndcg_at_100": 0.90285,
|
15 |
+
"map_at_1": 0.83,
|
16 |
+
"map_at_3": 0.86633,
|
17 |
+
"map_at_5": 0.87003,
|
18 |
+
"map_at_10": 0.87386,
|
19 |
+
"map_at_20": 0.87529,
|
20 |
+
"map_at_50": 0.87566,
|
21 |
+
"map_at_100": 0.87574,
|
22 |
+
"recall_at_1": 0.83,
|
23 |
+
"recall_at_3": 0.914,
|
24 |
+
"recall_at_5": 0.93,
|
25 |
+
"recall_at_10": 0.96,
|
26 |
+
"recall_at_20": 0.98,
|
27 |
+
"recall_at_50": 0.99,
|
28 |
+
"recall_at_100": 0.996,
|
29 |
+
"precision_at_1": 0.83,
|
30 |
+
"precision_at_3": 0.30467,
|
31 |
+
"precision_at_5": 0.186,
|
32 |
+
"precision_at_10": 0.096,
|
33 |
+
"precision_at_20": 0.049,
|
34 |
+
"precision_at_50": 0.0198,
|
35 |
+
"precision_at_100": 0.00996,
|
36 |
+
"mrr_at_1": 0.834,
|
37 |
+
"mrr_at_3": 0.8696666666666666,
|
38 |
+
"mrr_at_5": 0.8724666666666667,
|
39 |
+
"mrr_at_10": 0.8768738095238096,
|
40 |
+
"mrr_at_20": 0.8780439976689977,
|
41 |
+
"mrr_at_50": 0.8784954053717398,
|
42 |
+
"mrr_at_100": 0.8785747821152928,
|
43 |
+
"naucs_at_1_max": 0.7814883612933191,
|
44 |
+
"naucs_at_1_std": -0.014564346665118771,
|
45 |
+
"naucs_at_1_diff1": 0.9431415800777861,
|
46 |
+
"naucs_at_3_max": 0.7651293075369701,
|
47 |
+
"naucs_at_3_std": 0.13162008989642363,
|
48 |
+
"naucs_at_3_diff1": 0.876392417432091,
|
49 |
+
"naucs_at_5_max": 0.7719887955182062,
|
50 |
+
"naucs_at_5_std": 0.12731759370415013,
|
51 |
+
"naucs_at_5_diff1": 0.8762838468720809,
|
52 |
+
"naucs_at_10_max": 0.8234126984126983,
|
53 |
+
"naucs_at_10_std": 0.03160597572361713,
|
54 |
+
"naucs_at_10_diff1": 0.8921568627450972,
|
55 |
+
"naucs_at_20_max": 0.8225957049486448,
|
56 |
+
"naucs_at_20_std": -0.02110177404295123,
|
57 |
+
"naucs_at_20_diff1": 0.9084967320261399,
|
58 |
+
"naucs_at_50_max": 0.9738562091503188,
|
59 |
+
"naucs_at_50_std": 0.3997198879551785,
|
60 |
+
"naucs_at_50_diff1": 0.947712418300658,
|
61 |
+
"naucs_at_100_max": 1.0,
|
62 |
+
"naucs_at_100_std": 1.0,
|
63 |
+
"naucs_at_100_diff1": 0.9346405228758466
|
64 |
+
},
|
65 |
+
"docvqa_test_subsampled": {
|
66 |
+
"ndcg_at_1": 0.5255,
|
67 |
+
"ndcg_at_3": 0.59582,
|
68 |
+
"ndcg_at_5": 0.61852,
|
69 |
+
"ndcg_at_10": 0.6347,
|
70 |
+
"ndcg_at_20": 0.6492,
|
71 |
+
"ndcg_at_50": 0.65706,
|
72 |
+
"ndcg_at_100": 0.66361,
|
73 |
+
"map_at_1": 0.5255,
|
74 |
+
"map_at_3": 0.57871,
|
75 |
+
"map_at_5": 0.59124,
|
76 |
+
"map_at_10": 0.59815,
|
77 |
+
"map_at_20": 0.6021,
|
78 |
+
"map_at_50": 0.60333,
|
79 |
+
"map_at_100": 0.60394,
|
80 |
+
"recall_at_1": 0.5255,
|
81 |
+
"recall_at_3": 0.64523,
|
82 |
+
"recall_at_5": 0.70067,
|
83 |
+
"recall_at_10": 0.74945,
|
84 |
+
"recall_at_20": 0.8071,
|
85 |
+
"recall_at_50": 0.84701,
|
86 |
+
"recall_at_100": 0.88692,
|
87 |
+
"precision_at_1": 0.5255,
|
88 |
+
"precision_at_3": 0.21508,
|
89 |
+
"precision_at_5": 0.14013,
|
90 |
+
"precision_at_10": 0.07494,
|
91 |
+
"precision_at_20": 0.04035,
|
92 |
+
"precision_at_50": 0.01694,
|
93 |
+
"precision_at_100": 0.00887,
|
94 |
+
"mrr_at_1": 0.5254988913525499,
|
95 |
+
"mrr_at_3": 0.5798226164079823,
|
96 |
+
"mrr_at_5": 0.5909090909090909,
|
97 |
+
"mrr_at_10": 0.5981936085594622,
|
98 |
+
"mrr_at_20": 0.6018577072277826,
|
99 |
+
"mrr_at_50": 0.603184631365057,
|
100 |
+
"mrr_at_100": 0.6036950361798563,
|
101 |
+
"naucs_at_1_max": 0.3862474572443775,
|
102 |
+
"naucs_at_1_std": 0.6866980709008784,
|
103 |
+
"naucs_at_1_diff1": 0.908866111398327,
|
104 |
+
"naucs_at_3_max": 0.3232612877463118,
|
105 |
+
"naucs_at_3_std": 0.7754733885431401,
|
106 |
+
"naucs_at_3_diff1": 0.8488934990862631,
|
107 |
+
"naucs_at_5_max": 0.26561580627789727,
|
108 |
+
"naucs_at_5_std": 0.8294969802329596,
|
109 |
+
"naucs_at_5_diff1": 0.843549438877749,
|
110 |
+
"naucs_at_10_max": 0.21226897631460165,
|
111 |
+
"naucs_at_10_std": 0.9004830786766392,
|
112 |
+
"naucs_at_10_diff1": 0.8313389289681655,
|
113 |
+
"naucs_at_20_max": 0.1442628756616487,
|
114 |
+
"naucs_at_20_std": 0.9192991363569017,
|
115 |
+
"naucs_at_20_diff1": 0.8284091873092273,
|
116 |
+
"naucs_at_50_max": 0.04661475790032267,
|
117 |
+
"naucs_at_50_std": 0.9356118889205624,
|
118 |
+
"naucs_at_50_diff1": 0.8459735188892017,
|
119 |
+
"naucs_at_100_max": -0.014764226166713695,
|
120 |
+
"naucs_at_100_std": 0.9484296739649325,
|
121 |
+
"naucs_at_100_diff1": 0.853153345512516
|
122 |
+
},
|
123 |
+
"syntheticDocQA_energy_test": {
|
124 |
+
"ndcg_at_1": 0.95,
|
125 |
+
"ndcg_at_3": 0.96131,
|
126 |
+
"ndcg_at_5": 0.96131,
|
127 |
+
"ndcg_at_10": 0.96487,
|
128 |
+
"ndcg_at_20": 0.96757,
|
129 |
+
"ndcg_at_50": 0.96952,
|
130 |
+
"ndcg_at_100": 0.96952,
|
131 |
+
"map_at_1": 0.95,
|
132 |
+
"map_at_3": 0.95833,
|
133 |
+
"map_at_5": 0.95833,
|
134 |
+
"map_at_10": 0.96,
|
135 |
+
"map_at_20": 0.96083,
|
136 |
+
"map_at_50": 0.96113,
|
137 |
+
"map_at_100": 0.96113,
|
138 |
+
"recall_at_1": 0.95,
|
139 |
+
"recall_at_3": 0.97,
|
140 |
+
"recall_at_5": 0.97,
|
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": 0.95,
|
146 |
+
"precision_at_3": 0.32333,
|
147 |
+
"precision_at_5": 0.194,
|
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": 0.95,
|
153 |
+
"mrr_at_3": 0.9583333333333333,
|
154 |
+
"mrr_at_5": 0.9603333333333333,
|
155 |
+
"mrr_at_10": 0.9603333333333333,
|
156 |
+
"mrr_at_20": 0.9612424242424242,
|
157 |
+
"mrr_at_50": 0.9615549242424243,
|
158 |
+
"mrr_at_100": 0.9615549242424243,
|
159 |
+
"naucs_at_1_max": 0.5612511671335213,
|
160 |
+
"naucs_at_1_std": -0.8497665732959815,
|
161 |
+
"naucs_at_1_diff1": 0.9477124183006508,
|
162 |
+
"naucs_at_3_max": 0.807812013694371,
|
163 |
+
"naucs_at_3_std": -0.6484593837535022,
|
164 |
+
"naucs_at_3_diff1": 0.9564270152505466,
|
165 |
+
"naucs_at_5_max": 0.807812013694364,
|
166 |
+
"naucs_at_5_std": -0.6484593837535011,
|
167 |
+
"naucs_at_5_diff1": 0.9564270152505424,
|
168 |
+
"naucs_at_10_max": 0.9346405228758136,
|
169 |
+
"naucs_at_10_std": -0.10270774976657283,
|
170 |
+
"naucs_at_10_diff1": 0.9346405228758136,
|
171 |
+
"naucs_at_20_max": 0.8692810457516413,
|
172 |
+
"naucs_at_20_std": -0.5634920634920767,
|
173 |
+
"naucs_at_20_diff1": 1.0,
|
174 |
+
"naucs_at_50_max": null,
|
175 |
+
"naucs_at_50_std": null,
|
176 |
+
"naucs_at_50_diff1": null,
|
177 |
+
"naucs_at_100_max": null,
|
178 |
+
"naucs_at_100_std": null,
|
179 |
+
"naucs_at_100_diff1": null
|
180 |
+
},
|
181 |
+
"tatdqa_test": {
|
182 |
+
"ndcg_at_1": 0.69502,
|
183 |
+
"ndcg_at_3": 0.78919,
|
184 |
+
"ndcg_at_5": 0.80833,
|
185 |
+
"ndcg_at_10": 0.82129,
|
186 |
+
"ndcg_at_20": 0.82519,
|
187 |
+
"ndcg_at_50": 0.82963,
|
188 |
+
"ndcg_at_100": 0.83159,
|
189 |
+
"map_at_1": 0.69502,
|
190 |
+
"map_at_3": 0.76701,
|
191 |
+
"map_at_5": 0.77755,
|
192 |
+
"map_at_10": 0.78302,
|
193 |
+
"map_at_20": 0.7842,
|
194 |
+
"map_at_50": 0.78491,
|
195 |
+
"map_at_100": 0.78508,
|
196 |
+
"recall_at_1": 0.69502,
|
197 |
+
"recall_at_3": 0.85298,
|
198 |
+
"recall_at_5": 0.89976,
|
199 |
+
"recall_at_10": 0.93925,
|
200 |
+
"recall_at_20": 0.95383,
|
201 |
+
"recall_at_50": 0.97631,
|
202 |
+
"recall_at_100": 0.98846,
|
203 |
+
"precision_at_1": 0.69502,
|
204 |
+
"precision_at_3": 0.28433,
|
205 |
+
"precision_at_5": 0.17995,
|
206 |
+
"precision_at_10": 0.09392,
|
207 |
+
"precision_at_20": 0.04769,
|
208 |
+
"precision_at_50": 0.01953,
|
209 |
+
"precision_at_100": 0.00988,
|
210 |
+
"mrr_at_1": 0.6950182260024301,
|
211 |
+
"mrr_at_3": 0.7656946132037261,
|
212 |
+
"mrr_at_5": 0.7770554880518429,
|
213 |
+
"mrr_at_10": 0.7827320681208895,
|
214 |
+
"mrr_at_20": 0.783837406855329,
|
215 |
+
"mrr_at_50": 0.784510459247072,
|
216 |
+
"mrr_at_100": 0.7846961562032659,
|
217 |
+
"naucs_at_1_max": 0.2747145592665206,
|
218 |
+
"naucs_at_1_std": -0.09557716491043182,
|
219 |
+
"naucs_at_1_diff1": 0.8084384046681937,
|
220 |
+
"naucs_at_3_max": 0.3330280541363154,
|
221 |
+
"naucs_at_3_std": -0.0389562599865292,
|
222 |
+
"naucs_at_3_diff1": 0.7240601862039753,
|
223 |
+
"naucs_at_5_max": 0.352919194006459,
|
224 |
+
"naucs_at_5_std": 0.0514244344972758,
|
225 |
+
"naucs_at_5_diff1": 0.6583624352004738,
|
226 |
+
"naucs_at_10_max": 0.43229730811413347,
|
227 |
+
"naucs_at_10_std": 0.2815741957749473,
|
228 |
+
"naucs_at_10_diff1": 0.6007108794001051,
|
229 |
+
"naucs_at_20_max": 0.4241317350379727,
|
230 |
+
"naucs_at_20_std": 0.2971486230084223,
|
231 |
+
"naucs_at_20_diff1": 0.5874614197126973,
|
232 |
+
"naucs_at_50_max": 0.5140385840003181,
|
233 |
+
"naucs_at_50_std": 0.518664544400799,
|
234 |
+
"naucs_at_50_diff1": 0.5976629425860989,
|
235 |
+
"naucs_at_100_max": 0.4955447990957944,
|
236 |
+
"naucs_at_100_std": 0.5556756488737464,
|
237 |
+
"naucs_at_100_diff1": 0.6696787538618733
|
238 |
+
},
|
239 |
+
"infovqa_test_subsampled": {
|
240 |
+
"ndcg_at_1": 0.88664,
|
241 |
+
"ndcg_at_3": 0.91826,
|
242 |
+
"ndcg_at_5": 0.92479,
|
243 |
+
"ndcg_at_10": 0.93028,
|
244 |
+
"ndcg_at_20": 0.93185,
|
245 |
+
"ndcg_at_50": 0.93365,
|
246 |
+
"ndcg_at_100": 0.93435,
|
247 |
+
"map_at_1": 0.88664,
|
248 |
+
"map_at_3": 0.91093,
|
249 |
+
"map_at_5": 0.91447,
|
250 |
+
"map_at_10": 0.91689,
|
251 |
+
"map_at_20": 0.91735,
|
252 |
+
"map_at_50": 0.91756,
|
253 |
+
"map_at_100": 0.91763,
|
254 |
+
"recall_at_1": 0.88664,
|
255 |
+
"recall_at_3": 0.93927,
|
256 |
+
"recall_at_5": 0.95547,
|
257 |
+
"recall_at_10": 0.97166,
|
258 |
+
"recall_at_20": 0.97773,
|
259 |
+
"recall_at_50": 0.98785,
|
260 |
+
"recall_at_100": 0.9919,
|
261 |
+
"precision_at_1": 0.88664,
|
262 |
+
"precision_at_3": 0.31309,
|
263 |
+
"precision_at_5": 0.19109,
|
264 |
+
"precision_at_10": 0.09717,
|
265 |
+
"precision_at_20": 0.04889,
|
266 |
+
"precision_at_50": 0.01976,
|
267 |
+
"precision_at_100": 0.00992,
|
268 |
+
"mrr_at_1": 0.8846153846153846,
|
269 |
+
"mrr_at_3": 0.9092442645074225,
|
270 |
+
"mrr_at_5": 0.9127867746288799,
|
271 |
+
"mrr_at_10": 0.9150801683696421,
|
272 |
+
"mrr_at_20": 0.9155341004025214,
|
273 |
+
"mrr_at_50": 0.9157652608527469,
|
274 |
+
"mrr_at_100": 0.9158356239262059,
|
275 |
+
"naucs_at_1_max": 0.6077965938527005,
|
276 |
+
"naucs_at_1_std": -0.034859963613718514,
|
277 |
+
"naucs_at_1_diff1": 0.9382491207886892,
|
278 |
+
"naucs_at_3_max": 0.7083430308645834,
|
279 |
+
"naucs_at_3_std": 0.09173878193665044,
|
280 |
+
"naucs_at_3_diff1": 0.941058293792039,
|
281 |
+
"naucs_at_5_max": 0.828261285914772,
|
282 |
+
"naucs_at_5_std": 0.25360809635439513,
|
283 |
+
"naucs_at_5_diff1": 0.9374342352707031,
|
284 |
+
"naucs_at_10_max": 0.8969865162710334,
|
285 |
+
"naucs_at_10_std": 0.5367916133086486,
|
286 |
+
"naucs_at_10_diff1": 0.9521757785748344,
|
287 |
+
"naucs_at_20_max": 0.927259949634811,
|
288 |
+
"naucs_at_20_std": 0.6312197158498455,
|
289 |
+
"naucs_at_20_diff1": 0.9643814216187027,
|
290 |
+
"naucs_at_50_max": 0.9129323639568211,
|
291 |
+
"naucs_at_50_std": 0.5625809313845725,
|
292 |
+
"naucs_at_50_diff1": 0.9564661819783937,
|
293 |
+
"naucs_at_100_max": 0.9346992729676393,
|
294 |
+
"naucs_at_100_std": 0.7480140525249407,
|
295 |
+
"naucs_at_100_diff1": 0.9673496364838197
|
296 |
+
},
|
297 |
+
"syntheticDocQA_healthcare_industry_test": {
|
298 |
+
"ndcg_at_1": 0.97,
|
299 |
+
"ndcg_at_3": 0.98762,
|
300 |
+
"ndcg_at_5": 0.98762,
|
301 |
+
"ndcg_at_10": 0.98762,
|
302 |
+
"ndcg_at_20": 0.98762,
|
303 |
+
"ndcg_at_50": 0.98762,
|
304 |
+
"ndcg_at_100": 0.98762,
|
305 |
+
"map_at_1": 0.97,
|
306 |
+
"map_at_3": 0.98333,
|
307 |
+
"map_at_5": 0.98333,
|
308 |
+
"map_at_10": 0.98333,
|
309 |
+
"map_at_20": 0.98333,
|
310 |
+
"map_at_50": 0.98333,
|
311 |
+
"map_at_100": 0.98333,
|
312 |
+
"recall_at_1": 0.97,
|
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": 0.97,
|
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": 0.97,
|
327 |
+
"mrr_at_3": 0.9833333333333333,
|
328 |
+
"mrr_at_5": 0.9833333333333333,
|
329 |
+
"mrr_at_10": 0.9833333333333333,
|
330 |
+
"mrr_at_20": 0.9833333333333333,
|
331 |
+
"mrr_at_50": 0.9833333333333333,
|
332 |
+
"mrr_at_100": 0.9833333333333333,
|
333 |
+
"naucs_at_1_max": 0.8202614379084989,
|
334 |
+
"naucs_at_1_std": -0.2198879551820713,
|
335 |
+
"naucs_at_1_diff1": 0.9564270152505465,
|
336 |
+
"naucs_at_3_max": 1.0,
|
337 |
+
"naucs_at_3_std": 1.0,
|
338 |
+
"naucs_at_3_diff1": 1.0,
|
339 |
+
"naucs_at_5_max": 1.0,
|
340 |
+
"naucs_at_5_std": 1.0,
|
341 |
+
"naucs_at_5_diff1": 1.0,
|
342 |
+
"naucs_at_10_max": 1.0,
|
343 |
+
"naucs_at_10_std": 1.0,
|
344 |
+
"naucs_at_10_diff1": 1.0,
|
345 |
+
"naucs_at_20_max": 1.0,
|
346 |
+
"naucs_at_20_std": 1.0,
|
347 |
+
"naucs_at_20_diff1": 1.0,
|
348 |
+
"naucs_at_50_max": null,
|
349 |
+
"naucs_at_50_std": null,
|
350 |
+
"naucs_at_50_diff1": null,
|
351 |
+
"naucs_at_100_max": null,
|
352 |
+
"naucs_at_100_std": null,
|
353 |
+
"naucs_at_100_diff1": null
|
354 |
+
},
|
355 |
+
"tabfquad_test_subsampled": {
|
356 |
+
"ndcg_at_1": 0.83571,
|
357 |
+
"ndcg_at_3": 0.88699,
|
358 |
+
"ndcg_at_5": 0.89851,
|
359 |
+
"ndcg_at_10": 0.90549,
|
360 |
+
"ndcg_at_20": 0.91018,
|
361 |
+
"ndcg_at_50": 0.9125,
|
362 |
+
"ndcg_at_100": 0.9125,
|
363 |
+
"map_at_1": 0.83571,
|
364 |
+
"map_at_3": 0.875,
|
365 |
+
"map_at_5": 0.88125,
|
366 |
+
"map_at_10": 0.88416,
|
367 |
+
"map_at_20": 0.88553,
|
368 |
+
"map_at_50": 0.88598,
|
369 |
+
"map_at_100": 0.88598,
|
370 |
+
"recall_at_1": 0.83571,
|
371 |
+
"recall_at_3": 0.92143,
|
372 |
+
"recall_at_5": 0.95,
|
373 |
+
"recall_at_10": 0.97143,
|
374 |
+
"recall_at_20": 0.98929,
|
375 |
+
"recall_at_50": 1.0,
|
376 |
+
"recall_at_100": 1.0,
|
377 |
+
"precision_at_1": 0.83571,
|
378 |
+
"precision_at_3": 0.30714,
|
379 |
+
"precision_at_5": 0.19,
|
380 |
+
"precision_at_10": 0.09714,
|
381 |
+
"precision_at_20": 0.04946,
|
382 |
+
"precision_at_50": 0.02,
|
383 |
+
"precision_at_100": 0.01,
|
384 |
+
"mrr_at_1": 0.8392857142857143,
|
385 |
+
"mrr_at_3": 0.8767857142857143,
|
386 |
+
"mrr_at_5": 0.8830357142857143,
|
387 |
+
"mrr_at_10": 0.8858517573696145,
|
388 |
+
"mrr_at_20": 0.8872690305726021,
|
389 |
+
"mrr_at_50": 0.8877252707609851,
|
390 |
+
"mrr_at_100": 0.8877252707609851,
|
391 |
+
"naucs_at_1_max": 0.4880524536858767,
|
392 |
+
"naucs_at_1_std": 0.1966050571171859,
|
393 |
+
"naucs_at_1_diff1": 0.9065802421597565,
|
394 |
+
"naucs_at_3_max": 0.5683515830574649,
|
395 |
+
"naucs_at_3_std": 0.33952975129445734,
|
396 |
+
"naucs_at_3_diff1": 0.8935786435786452,
|
397 |
+
"naucs_at_5_max": 0.7507669734560504,
|
398 |
+
"naucs_at_5_std": 0.5118714152327615,
|
399 |
+
"naucs_at_5_diff1": 0.9109643857543043,
|
400 |
+
"naucs_at_10_max": 0.8150093370681609,
|
401 |
+
"naucs_at_10_std": 0.5556722689075682,
|
402 |
+
"naucs_at_10_diff1": 0.934640522875815,
|
403 |
+
"naucs_at_20_max": 0.9128540305011011,
|
404 |
+
"naucs_at_20_std": 0.807812013694365,
|
405 |
+
"naucs_at_20_diff1": 0.9564270152505505,
|
406 |
+
"naucs_at_50_max": 1.0,
|
407 |
+
"naucs_at_50_std": 1.0,
|
408 |
+
"naucs_at_50_diff1": 1.0,
|
409 |
+
"naucs_at_100_max": 1.0,
|
410 |
+
"naucs_at_100_std": 1.0,
|
411 |
+
"naucs_at_100_diff1": 1.0
|
412 |
+
},
|
413 |
+
"syntheticDocQA_government_reports_test": {
|
414 |
+
"ndcg_at_1": 0.91,
|
415 |
+
"ndcg_at_3": 0.94393,
|
416 |
+
"ndcg_at_5": 0.95254,
|
417 |
+
"ndcg_at_10": 0.9561,
|
418 |
+
"ndcg_at_20": 0.9561,
|
419 |
+
"ndcg_at_50": 0.9561,
|
420 |
+
"ndcg_at_100": 0.9561,
|
421 |
+
"map_at_1": 0.91,
|
422 |
+
"map_at_3": 0.935,
|
423 |
+
"map_at_5": 0.94,
|
424 |
+
"map_at_10": 0.94167,
|
425 |
+
"map_at_20": 0.94167,
|
426 |
+
"map_at_50": 0.94167,
|
427 |
+
"map_at_100": 0.94167,
|
428 |
+
"recall_at_1": 0.91,
|
429 |
+
"recall_at_3": 0.97,
|
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": 0.91,
|
436 |
+
"precision_at_3": 0.32333,
|
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": 0.91,
|
443 |
+
"mrr_at_3": 0.9383333333333332,
|
444 |
+
"mrr_at_5": 0.9428333333333333,
|
445 |
+
"mrr_at_10": 0.9428333333333333,
|
446 |
+
"mrr_at_20": 0.9428333333333333,
|
447 |
+
"mrr_at_50": 0.9428333333333333,
|
448 |
+
"mrr_at_100": 0.9428333333333333,
|
449 |
+
"naucs_at_1_max": 0.8246706089843343,
|
450 |
+
"naucs_at_1_std": 0.4518103537711367,
|
451 |
+
"naucs_at_1_diff1": 0.9564270152505436,
|
452 |
+
"naucs_at_3_max": 0.7027699968876487,
|
453 |
+
"naucs_at_3_std": 0.460939931528168,
|
454 |
+
"naucs_at_3_diff1": 0.9564270152505466,
|
455 |
+
"naucs_at_5_max": 0.5541549953314738,
|
456 |
+
"naucs_at_5_std": -0.1713352007469681,
|
457 |
+
"naucs_at_5_diff1": 1.0,
|
458 |
+
"naucs_at_10_max": 1.0,
|
459 |
+
"naucs_at_10_std": 1.0,
|
460 |
+
"naucs_at_10_diff1": 1.0,
|
461 |
+
"naucs_at_20_max": 1.0,
|
462 |
+
"naucs_at_20_std": 1.0,
|
463 |
+
"naucs_at_20_diff1": 1.0,
|
464 |
+
"naucs_at_50_max": null,
|
465 |
+
"naucs_at_50_std": null,
|
466 |
+
"naucs_at_50_diff1": null,
|
467 |
+
"naucs_at_100_max": null,
|
468 |
+
"naucs_at_100_std": null,
|
469 |
+
"naucs_at_100_diff1": null
|
470 |
+
},
|
471 |
+
"shiftproject_test": {
|
472 |
+
"ndcg_at_1": 0.73,
|
473 |
+
"ndcg_at_3": 0.85095,
|
474 |
+
"ndcg_at_5": 0.85526,
|
475 |
+
"ndcg_at_10": 0.86174,
|
476 |
+
"ndcg_at_20": 0.86703,
|
477 |
+
"ndcg_at_50": 0.87134,
|
478 |
+
"ndcg_at_100": 0.87134,
|
479 |
+
"map_at_1": 0.73,
|
480 |
+
"map_at_3": 0.82333,
|
481 |
+
"map_at_5": 0.82583,
|
482 |
+
"map_at_10": 0.82851,
|
483 |
+
"map_at_20": 0.83009,
|
484 |
+
"map_at_50": 0.83092,
|
485 |
+
"map_at_100": 0.83092,
|
486 |
+
"recall_at_1": 0.73,
|
487 |
+
"recall_at_3": 0.93,
|
488 |
+
"recall_at_5": 0.94,
|
489 |
+
"recall_at_10": 0.96,
|
490 |
+
"recall_at_20": 0.98,
|
491 |
+
"recall_at_50": 1.0,
|
492 |
+
"recall_at_100": 1.0,
|
493 |
+
"precision_at_1": 0.73,
|
494 |
+
"precision_at_3": 0.31,
|
495 |
+
"precision_at_5": 0.188,
|
496 |
+
"precision_at_10": 0.096,
|
497 |
+
"precision_at_20": 0.049,
|
498 |
+
"precision_at_50": 0.02,
|
499 |
+
"precision_at_100": 0.01,
|
500 |
+
"mrr_at_1": 0.75,
|
501 |
+
"mrr_at_3": 0.8316666666666667,
|
502 |
+
"mrr_at_5": 0.8341666666666667,
|
503 |
+
"mrr_at_10": 0.8380238095238096,
|
504 |
+
"mrr_at_20": 0.8386904761904762,
|
505 |
+
"mrr_at_50": 0.8395600414078674,
|
506 |
+
"mrr_at_100": 0.8395600414078674,
|
507 |
+
"naucs_at_1_max": -0.0662092826672433,
|
508 |
+
"naucs_at_1_std": -0.3356071477717276,
|
509 |
+
"naucs_at_1_diff1": 0.7686999941024986,
|
510 |
+
"naucs_at_3_max": -0.05822328931572497,
|
511 |
+
"naucs_at_3_std": -0.2665732959850601,
|
512 |
+
"naucs_at_3_diff1": 0.7789782579698524,
|
513 |
+
"naucs_at_5_max": 0.22206660441954526,
|
514 |
+
"naucs_at_5_std": -0.33146591970121353,
|
515 |
+
"naucs_at_5_diff1": 0.8883442265795238,
|
516 |
+
"naucs_at_10_max": 0.05240429505135564,
|
517 |
+
"naucs_at_10_std": -0.4458450046685252,
|
518 |
+
"naucs_at_10_diff1": 0.8651960784313721,
|
519 |
+
"naucs_at_20_max": -0.5088702147525547,
|
520 |
+
"naucs_at_20_std": -0.5929038281979383,
|
521 |
+
"naucs_at_20_diff1": 0.9346405228758136,
|
522 |
+
"naucs_at_50_max": null,
|
523 |
+
"naucs_at_50_std": null,
|
524 |
+
"naucs_at_50_diff1": null,
|
525 |
+
"naucs_at_100_max": null,
|
526 |
+
"naucs_at_100_std": null,
|
527 |
+
"naucs_at_100_diff1": null
|
528 |
+
},
|
529 |
+
"syntheticDocQA_artificial_intelligence_test": {
|
530 |
+
"ndcg_at_1": 0.98,
|
531 |
+
"ndcg_at_3": 0.99262,
|
532 |
+
"ndcg_at_5": 0.99262,
|
533 |
+
"ndcg_at_10": 0.99262,
|
534 |
+
"ndcg_at_20": 0.99262,
|
535 |
+
"ndcg_at_50": 0.99262,
|
536 |
+
"ndcg_at_100": 0.99262,
|
537 |
+
"map_at_1": 0.98,
|
538 |
+
"map_at_3": 0.99,
|
539 |
+
"map_at_5": 0.99,
|
540 |
+
"map_at_10": 0.99,
|
541 |
+
"map_at_20": 0.99,
|
542 |
+
"map_at_50": 0.99,
|
543 |
+
"map_at_100": 0.99,
|
544 |
+
"recall_at_1": 0.98,
|
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": 0.98,
|
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": 0.98,
|
559 |
+
"mrr_at_3": 0.99,
|
560 |
+
"mrr_at_5": 0.99,
|
561 |
+
"mrr_at_10": 0.99,
|
562 |
+
"mrr_at_20": 0.99,
|
563 |
+
"mrr_at_50": 0.99,
|
564 |
+
"mrr_at_100": 0.99,
|
565 |
+
"naucs_at_1_max": 0.3489729225023353,
|
566 |
+
"naucs_at_1_std": -0.2987861811391249,
|
567 |
+
"naucs_at_1_diff1": 1.0,
|
568 |
+
"naucs_at_3_max": 1.0,
|
569 |
+
"naucs_at_3_std": 1.0,
|
570 |
+
"naucs_at_3_diff1": 1.0,
|
571 |
+
"naucs_at_5_max": 1.0,
|
572 |
+
"naucs_at_5_std": 1.0,
|
573 |
+
"naucs_at_5_diff1": 1.0,
|
574 |
+
"naucs_at_10_max": 1.0,
|
575 |
+
"naucs_at_10_std": 1.0,
|
576 |
+
"naucs_at_10_diff1": 1.0,
|
577 |
+
"naucs_at_20_max": 1.0,
|
578 |
+
"naucs_at_20_std": 1.0,
|
579 |
+
"naucs_at_20_diff1": 1.0,
|
580 |
+
"naucs_at_50_max": null,
|
581 |
+
"naucs_at_50_std": null,
|
582 |
+
"naucs_at_50_diff1": null,
|
583 |
+
"naucs_at_100_max": null,
|
584 |
+
"naucs_at_100_std": null,
|
585 |
+
"naucs_at_100_diff1": null
|
586 |
+
}
|
587 |
+
}
|
588 |
+
}
|