Upload results.json
Browse files- results.json +582 -0
results.json
ADDED
@@ -0,0 +1,582 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"syntheticDocQA_artificial_intelligence_test": {
|
3 |
+
"ndcg_at_1": 0.97,
|
4 |
+
"ndcg_at_3": 0.98893,
|
5 |
+
"ndcg_at_5": 0.98893,
|
6 |
+
"ndcg_at_10": 0.98893,
|
7 |
+
"ndcg_at_20": 0.98893,
|
8 |
+
"ndcg_at_50": 0.98893,
|
9 |
+
"ndcg_at_100": 0.98893,
|
10 |
+
"map_at_1": 0.97,
|
11 |
+
"map_at_3": 0.985,
|
12 |
+
"map_at_5": 0.985,
|
13 |
+
"map_at_10": 0.985,
|
14 |
+
"map_at_20": 0.985,
|
15 |
+
"map_at_50": 0.985,
|
16 |
+
"map_at_100": 0.985,
|
17 |
+
"recall_at_1": 0.97,
|
18 |
+
"recall_at_3": 1.0,
|
19 |
+
"recall_at_5": 1.0,
|
20 |
+
"recall_at_10": 1.0,
|
21 |
+
"recall_at_20": 1.0,
|
22 |
+
"recall_at_50": 1.0,
|
23 |
+
"recall_at_100": 1.0,
|
24 |
+
"precision_at_1": 0.97,
|
25 |
+
"precision_at_3": 0.33333,
|
26 |
+
"precision_at_5": 0.2,
|
27 |
+
"precision_at_10": 0.1,
|
28 |
+
"precision_at_20": 0.05,
|
29 |
+
"precision_at_50": 0.02,
|
30 |
+
"precision_at_100": 0.01,
|
31 |
+
"mrr_at_1": 0.98,
|
32 |
+
"mrr_at_3": 0.99,
|
33 |
+
"mrr_at_5": 0.99,
|
34 |
+
"mrr_at_10": 0.99,
|
35 |
+
"mrr_at_20": 0.99,
|
36 |
+
"mrr_at_50": 0.99,
|
37 |
+
"mrr_at_100": 0.99,
|
38 |
+
"naucs_at_1_max": 0.24696545284780627,
|
39 |
+
"naucs_at_1_std": 0.24696545284780627,
|
40 |
+
"naucs_at_1_diff1": 1.0,
|
41 |
+
"naucs_at_3_max": 1.0,
|
42 |
+
"naucs_at_3_std": 1.0,
|
43 |
+
"naucs_at_3_diff1": 1.0,
|
44 |
+
"naucs_at_5_max": 1.0,
|
45 |
+
"naucs_at_5_std": 1.0,
|
46 |
+
"naucs_at_5_diff1": 1.0,
|
47 |
+
"naucs_at_10_max": 1.0,
|
48 |
+
"naucs_at_10_std": 1.0,
|
49 |
+
"naucs_at_10_diff1": 1.0,
|
50 |
+
"naucs_at_20_max": 1.0,
|
51 |
+
"naucs_at_20_std": 1.0,
|
52 |
+
"naucs_at_20_diff1": 1.0,
|
53 |
+
"naucs_at_50_max": null,
|
54 |
+
"naucs_at_50_std": null,
|
55 |
+
"naucs_at_50_diff1": null,
|
56 |
+
"naucs_at_100_max": null,
|
57 |
+
"naucs_at_100_std": null,
|
58 |
+
"naucs_at_100_diff1": null
|
59 |
+
},
|
60 |
+
"tabfquad_test_subsampled": {
|
61 |
+
"ndcg_at_1": 0.88571,
|
62 |
+
"ndcg_at_3": 0.93567,
|
63 |
+
"ndcg_at_5": 0.93875,
|
64 |
+
"ndcg_at_10": 0.94242,
|
65 |
+
"ndcg_at_20": 0.94338,
|
66 |
+
"ndcg_at_50": 0.94556,
|
67 |
+
"ndcg_at_100": 0.94556,
|
68 |
+
"map_at_1": 0.88571,
|
69 |
+
"map_at_3": 0.9244,
|
70 |
+
"map_at_5": 0.92619,
|
71 |
+
"map_at_10": 0.92783,
|
72 |
+
"map_at_20": 0.92812,
|
73 |
+
"map_at_50": 0.92849,
|
74 |
+
"map_at_100": 0.92849,
|
75 |
+
"recall_at_1": 0.88571,
|
76 |
+
"recall_at_3": 0.96786,
|
77 |
+
"recall_at_5": 0.975,
|
78 |
+
"recall_at_10": 0.98571,
|
79 |
+
"recall_at_20": 0.98929,
|
80 |
+
"recall_at_50": 1.0,
|
81 |
+
"recall_at_100": 1.0,
|
82 |
+
"precision_at_1": 0.88571,
|
83 |
+
"precision_at_3": 0.32262,
|
84 |
+
"precision_at_5": 0.195,
|
85 |
+
"precision_at_10": 0.09857,
|
86 |
+
"precision_at_20": 0.04946,
|
87 |
+
"precision_at_50": 0.02,
|
88 |
+
"precision_at_100": 0.01,
|
89 |
+
"mrr_at_1": 0.8857142857142857,
|
90 |
+
"mrr_at_3": 0.9255952380952379,
|
91 |
+
"mrr_at_5": 0.9280952380952381,
|
92 |
+
"mrr_at_10": 0.9291369047619047,
|
93 |
+
"mrr_at_20": 0.9294345238095238,
|
94 |
+
"mrr_at_50": 0.9298080357142857,
|
95 |
+
"mrr_at_100": 0.9298080357142857,
|
96 |
+
"naucs_at_1_max": 0.6126156858092077,
|
97 |
+
"naucs_at_1_std": 0.33993830090175703,
|
98 |
+
"naucs_at_1_diff1": 0.9092311343141914,
|
99 |
+
"naucs_at_3_max": 0.919597468617075,
|
100 |
+
"naucs_at_3_std": 0.8003423591658857,
|
101 |
+
"naucs_at_3_diff1": 0.9854756717501797,
|
102 |
+
"naucs_at_5_max": 0.9603174603174579,
|
103 |
+
"naucs_at_5_std": 0.9603174603174579,
|
104 |
+
"naucs_at_5_diff1": 0.981325863678801,
|
105 |
+
"naucs_at_10_max": 1.0,
|
106 |
+
"naucs_at_10_std": 1.0,
|
107 |
+
"naucs_at_10_diff1": 1.0,
|
108 |
+
"naucs_at_20_max": 1.0,
|
109 |
+
"naucs_at_20_std": 1.0,
|
110 |
+
"naucs_at_20_diff1": 1.0,
|
111 |
+
"naucs_at_50_max": 1.0,
|
112 |
+
"naucs_at_50_std": 1.0,
|
113 |
+
"naucs_at_50_diff1": 1.0,
|
114 |
+
"naucs_at_100_max": 1.0,
|
115 |
+
"naucs_at_100_std": 1.0,
|
116 |
+
"naucs_at_100_diff1": 1.0
|
117 |
+
},
|
118 |
+
"shiftproject_test": {
|
119 |
+
"ndcg_at_1": 0.79,
|
120 |
+
"ndcg_at_3": 0.88309,
|
121 |
+
"ndcg_at_5": 0.89127,
|
122 |
+
"ndcg_at_10": 0.89416,
|
123 |
+
"ndcg_at_20": 0.89416,
|
124 |
+
"ndcg_at_50": 0.89828,
|
125 |
+
"ndcg_at_100": 0.89828,
|
126 |
+
"map_at_1": 0.79,
|
127 |
+
"map_at_3": 0.86,
|
128 |
+
"map_at_5": 0.8645,
|
129 |
+
"map_at_10": 0.8655,
|
130 |
+
"map_at_20": 0.8655,
|
131 |
+
"map_at_50": 0.86622,
|
132 |
+
"map_at_100": 0.86622,
|
133 |
+
"recall_at_1": 0.79,
|
134 |
+
"recall_at_3": 0.95,
|
135 |
+
"recall_at_5": 0.97,
|
136 |
+
"recall_at_10": 0.98,
|
137 |
+
"recall_at_20": 0.98,
|
138 |
+
"recall_at_50": 1.0,
|
139 |
+
"recall_at_100": 1.0,
|
140 |
+
"precision_at_1": 0.79,
|
141 |
+
"precision_at_3": 0.31667,
|
142 |
+
"precision_at_5": 0.194,
|
143 |
+
"precision_at_10": 0.098,
|
144 |
+
"precision_at_20": 0.049,
|
145 |
+
"precision_at_50": 0.02,
|
146 |
+
"precision_at_100": 0.01,
|
147 |
+
"mrr_at_1": 0.8,
|
148 |
+
"mrr_at_3": 0.8683333333333333,
|
149 |
+
"mrr_at_5": 0.8728333333333333,
|
150 |
+
"mrr_at_10": 0.8728333333333333,
|
151 |
+
"mrr_at_20": 0.8737424242424242,
|
152 |
+
"mrr_at_50": 0.8745417972831766,
|
153 |
+
"mrr_at_100": 0.8745417972831766,
|
154 |
+
"naucs_at_1_max": 0.057974847909202674,
|
155 |
+
"naucs_at_1_std": -0.42724889989660236,
|
156 |
+
"naucs_at_1_diff1": 0.8040493423425586,
|
157 |
+
"naucs_at_3_max": 0.09589169000933911,
|
158 |
+
"naucs_at_3_std": -0.5948646125116669,
|
159 |
+
"naucs_at_3_diff1": 0.9477124183006521,
|
160 |
+
"naucs_at_5_max": -0.0004668534080290478,
|
161 |
+
"naucs_at_5_std": -0.35434173669467856,
|
162 |
+
"naucs_at_5_diff1": 0.9564270152505424,
|
163 |
+
"naucs_at_10_max": -0.43534080298785716,
|
164 |
+
"naucs_at_10_std": -0.5929038281979383,
|
165 |
+
"naucs_at_10_diff1": 1.0,
|
166 |
+
"naucs_at_20_max": -0.43534080298785716,
|
167 |
+
"naucs_at_20_std": -0.5929038281979383,
|
168 |
+
"naucs_at_20_diff1": 1.0,
|
169 |
+
"naucs_at_50_max": null,
|
170 |
+
"naucs_at_50_std": null,
|
171 |
+
"naucs_at_50_diff1": null,
|
172 |
+
"naucs_at_100_max": null,
|
173 |
+
"naucs_at_100_std": null,
|
174 |
+
"naucs_at_100_diff1": null
|
175 |
+
},
|
176 |
+
"syntheticDocQA_government_reports_test": {
|
177 |
+
"ndcg_at_1": 0.9,
|
178 |
+
"ndcg_at_3": 0.96178,
|
179 |
+
"ndcg_at_5": 0.96178,
|
180 |
+
"ndcg_at_10": 0.96178,
|
181 |
+
"ndcg_at_20": 0.96178,
|
182 |
+
"ndcg_at_50": 0.96178,
|
183 |
+
"ndcg_at_100": 0.96178,
|
184 |
+
"map_at_1": 0.9,
|
185 |
+
"map_at_3": 0.94833,
|
186 |
+
"map_at_5": 0.94833,
|
187 |
+
"map_at_10": 0.94833,
|
188 |
+
"map_at_20": 0.94833,
|
189 |
+
"map_at_50": 0.94833,
|
190 |
+
"map_at_100": 0.94833,
|
191 |
+
"recall_at_1": 0.9,
|
192 |
+
"recall_at_3": 1.0,
|
193 |
+
"recall_at_5": 1.0,
|
194 |
+
"recall_at_10": 1.0,
|
195 |
+
"recall_at_20": 1.0,
|
196 |
+
"recall_at_50": 1.0,
|
197 |
+
"recall_at_100": 1.0,
|
198 |
+
"precision_at_1": 0.9,
|
199 |
+
"precision_at_3": 0.33333,
|
200 |
+
"precision_at_5": 0.2,
|
201 |
+
"precision_at_10": 0.1,
|
202 |
+
"precision_at_20": 0.05,
|
203 |
+
"precision_at_50": 0.02,
|
204 |
+
"precision_at_100": 0.01,
|
205 |
+
"mrr_at_1": 0.94,
|
206 |
+
"mrr_at_3": 0.9683333333333333,
|
207 |
+
"mrr_at_5": 0.9683333333333333,
|
208 |
+
"mrr_at_10": 0.9683333333333333,
|
209 |
+
"mrr_at_20": 0.9683333333333333,
|
210 |
+
"mrr_at_50": 0.9683333333333333,
|
211 |
+
"mrr_at_100": 0.9683333333333333,
|
212 |
+
"naucs_at_1_max": 0.709710550887022,
|
213 |
+
"naucs_at_1_std": 0.3939775910364137,
|
214 |
+
"naucs_at_1_diff1": 0.9738562091503267,
|
215 |
+
"naucs_at_3_max": 1.0,
|
216 |
+
"naucs_at_3_std": 1.0,
|
217 |
+
"naucs_at_3_diff1": 1.0,
|
218 |
+
"naucs_at_5_max": 1.0,
|
219 |
+
"naucs_at_5_std": 1.0,
|
220 |
+
"naucs_at_5_diff1": 1.0,
|
221 |
+
"naucs_at_10_max": 1.0,
|
222 |
+
"naucs_at_10_std": 1.0,
|
223 |
+
"naucs_at_10_diff1": 1.0,
|
224 |
+
"naucs_at_20_max": 1.0,
|
225 |
+
"naucs_at_20_std": 1.0,
|
226 |
+
"naucs_at_20_diff1": 1.0,
|
227 |
+
"naucs_at_50_max": null,
|
228 |
+
"naucs_at_50_std": null,
|
229 |
+
"naucs_at_50_diff1": null,
|
230 |
+
"naucs_at_100_max": null,
|
231 |
+
"naucs_at_100_std": null,
|
232 |
+
"naucs_at_100_diff1": null
|
233 |
+
},
|
234 |
+
"infovqa_test_subsampled": {
|
235 |
+
"ndcg_at_1": 0.89271,
|
236 |
+
"ndcg_at_3": 0.9279,
|
237 |
+
"ndcg_at_5": 0.93548,
|
238 |
+
"ndcg_at_10": 0.93812,
|
239 |
+
"ndcg_at_20": 0.93968,
|
240 |
+
"ndcg_at_50": 0.94205,
|
241 |
+
"ndcg_at_100": 0.94241,
|
242 |
+
"map_at_1": 0.89271,
|
243 |
+
"map_at_3": 0.9197,
|
244 |
+
"map_at_5": 0.92395,
|
245 |
+
"map_at_10": 0.92506,
|
246 |
+
"map_at_20": 0.9255,
|
247 |
+
"map_at_50": 0.92586,
|
248 |
+
"map_at_100": 0.9259,
|
249 |
+
"recall_at_1": 0.89271,
|
250 |
+
"recall_at_3": 0.95142,
|
251 |
+
"recall_at_5": 0.96964,
|
252 |
+
"recall_at_10": 0.97773,
|
253 |
+
"recall_at_20": 0.98381,
|
254 |
+
"recall_at_50": 0.99595,
|
255 |
+
"recall_at_100": 0.99798,
|
256 |
+
"precision_at_1": 0.89271,
|
257 |
+
"precision_at_3": 0.31714,
|
258 |
+
"precision_at_5": 0.19393,
|
259 |
+
"precision_at_10": 0.09777,
|
260 |
+
"precision_at_20": 0.04919,
|
261 |
+
"precision_at_50": 0.01992,
|
262 |
+
"precision_at_100": 0.00998,
|
263 |
+
"mrr_at_1": 0.8967611336032388,
|
264 |
+
"mrr_at_3": 0.9220647773279351,
|
265 |
+
"mrr_at_5": 0.9258097165991901,
|
266 |
+
"mrr_at_10": 0.9269503887924939,
|
267 |
+
"mrr_at_20": 0.9273423944476574,
|
268 |
+
"mrr_at_50": 0.9277128849497269,
|
269 |
+
"mrr_at_100": 0.9277518136323802,
|
270 |
+
"naucs_at_1_max": 0.7069555250969274,
|
271 |
+
"naucs_at_1_std": 0.03146819531411467,
|
272 |
+
"naucs_at_1_diff1": 0.948883682523629,
|
273 |
+
"naucs_at_3_max": 0.7542194764049448,
|
274 |
+
"naucs_at_3_std": 0.14233724807946155,
|
275 |
+
"naucs_at_3_diff1": 0.9448939012384912,
|
276 |
+
"naucs_at_5_max": 0.7638778110599751,
|
277 |
+
"naucs_at_5_std": 0.11081212928246655,
|
278 |
+
"naucs_at_5_diff1": 0.9292437691902227,
|
279 |
+
"naucs_at_10_max": 0.8654947821504146,
|
280 |
+
"naucs_at_10_std": 0.427910709539122,
|
281 |
+
"naucs_at_10_diff1": 0.927259949634811,
|
282 |
+
"naucs_at_20_max": 0.8707684274521482,
|
283 |
+
"naucs_at_20_std": 0.6120449232560383,
|
284 |
+
"naucs_at_20_diff1": 0.9163076125059596,
|
285 |
+
"naucs_at_50_max": 0.9346992729675874,
|
286 |
+
"naucs_at_50_std": 0.9346992729675874,
|
287 |
+
"naucs_at_50_diff1": 0.9346992729675874,
|
288 |
+
"naucs_at_100_max": 0.8693985459351681,
|
289 |
+
"naucs_at_100_std": 0.8693985459351681,
|
290 |
+
"naucs_at_100_diff1": 1.0
|
291 |
+
},
|
292 |
+
"syntheticDocQA_healthcare_industry_test": {
|
293 |
+
"ndcg_at_1": 0.96,
|
294 |
+
"ndcg_at_3": 0.98524,
|
295 |
+
"ndcg_at_5": 0.98524,
|
296 |
+
"ndcg_at_10": 0.98524,
|
297 |
+
"ndcg_at_20": 0.98524,
|
298 |
+
"ndcg_at_50": 0.98524,
|
299 |
+
"ndcg_at_100": 0.98524,
|
300 |
+
"map_at_1": 0.96,
|
301 |
+
"map_at_3": 0.98,
|
302 |
+
"map_at_5": 0.98,
|
303 |
+
"map_at_10": 0.98,
|
304 |
+
"map_at_20": 0.98,
|
305 |
+
"map_at_50": 0.98,
|
306 |
+
"map_at_100": 0.98,
|
307 |
+
"recall_at_1": 0.96,
|
308 |
+
"recall_at_3": 1.0,
|
309 |
+
"recall_at_5": 1.0,
|
310 |
+
"recall_at_10": 1.0,
|
311 |
+
"recall_at_20": 1.0,
|
312 |
+
"recall_at_50": 1.0,
|
313 |
+
"recall_at_100": 1.0,
|
314 |
+
"precision_at_1": 0.96,
|
315 |
+
"precision_at_3": 0.33333,
|
316 |
+
"precision_at_5": 0.2,
|
317 |
+
"precision_at_10": 0.1,
|
318 |
+
"precision_at_20": 0.05,
|
319 |
+
"precision_at_50": 0.02,
|
320 |
+
"precision_at_100": 0.01,
|
321 |
+
"mrr_at_1": 0.96,
|
322 |
+
"mrr_at_3": 0.98,
|
323 |
+
"mrr_at_5": 0.98,
|
324 |
+
"mrr_at_10": 0.98,
|
325 |
+
"mrr_at_20": 0.98,
|
326 |
+
"mrr_at_50": 0.98,
|
327 |
+
"mrr_at_100": 0.98,
|
328 |
+
"naucs_at_1_max": 0.8231792717086849,
|
329 |
+
"naucs_at_1_std": -0.7742763772175525,
|
330 |
+
"naucs_at_1_diff1": 0.96732026143791,
|
331 |
+
"naucs_at_3_max": 1.0,
|
332 |
+
"naucs_at_3_std": 1.0,
|
333 |
+
"naucs_at_3_diff1": 1.0,
|
334 |
+
"naucs_at_5_max": 1.0,
|
335 |
+
"naucs_at_5_std": 1.0,
|
336 |
+
"naucs_at_5_diff1": 1.0,
|
337 |
+
"naucs_at_10_max": 1.0,
|
338 |
+
"naucs_at_10_std": 1.0,
|
339 |
+
"naucs_at_10_diff1": 1.0,
|
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 |
+
"syntheticDocQA_energy_test": {
|
351 |
+
"ndcg_at_1": 0.92,
|
352 |
+
"ndcg_at_3": 0.95155,
|
353 |
+
"ndcg_at_5": 0.95585,
|
354 |
+
"ndcg_at_10": 0.95874,
|
355 |
+
"ndcg_at_20": 0.95874,
|
356 |
+
"ndcg_at_50": 0.96073,
|
357 |
+
"ndcg_at_100": 0.96073,
|
358 |
+
"map_at_1": 0.92,
|
359 |
+
"map_at_3": 0.945,
|
360 |
+
"map_at_5": 0.9475,
|
361 |
+
"map_at_10": 0.9485,
|
362 |
+
"map_at_20": 0.9485,
|
363 |
+
"map_at_50": 0.94881,
|
364 |
+
"map_at_100": 0.94881,
|
365 |
+
"recall_at_1": 0.92,
|
366 |
+
"recall_at_3": 0.97,
|
367 |
+
"recall_at_5": 0.98,
|
368 |
+
"recall_at_10": 0.99,
|
369 |
+
"recall_at_20": 0.99,
|
370 |
+
"recall_at_50": 1.0,
|
371 |
+
"recall_at_100": 1.0,
|
372 |
+
"precision_at_1": 0.92,
|
373 |
+
"precision_at_3": 0.32333,
|
374 |
+
"precision_at_5": 0.196,
|
375 |
+
"precision_at_10": 0.099,
|
376 |
+
"precision_at_20": 0.0495,
|
377 |
+
"precision_at_50": 0.02,
|
378 |
+
"precision_at_100": 0.01,
|
379 |
+
"mrr_at_1": 0.93,
|
380 |
+
"mrr_at_3": 0.95,
|
381 |
+
"mrr_at_5": 0.9525,
|
382 |
+
"mrr_at_10": 0.9536111111111112,
|
383 |
+
"mrr_at_20": 0.9536111111111112,
|
384 |
+
"mrr_at_50": 0.9539444444444445,
|
385 |
+
"mrr_at_100": 0.9539444444444445,
|
386 |
+
"naucs_at_1_max": 0.2832049486461252,
|
387 |
+
"naucs_at_1_std": -0.673611111111113,
|
388 |
+
"naucs_at_1_diff1": 0.983660130718955,
|
389 |
+
"naucs_at_3_max": 0.6498599439775861,
|
390 |
+
"naucs_at_3_std": -1.3478057889822568,
|
391 |
+
"naucs_at_3_diff1": 1.0,
|
392 |
+
"naucs_at_5_max": 0.540149393090577,
|
393 |
+
"naucs_at_5_std": -1.7399626517273414,
|
394 |
+
"naucs_at_5_diff1": 1.0,
|
395 |
+
"naucs_at_10_max": 0.7222222222222276,
|
396 |
+
"naucs_at_10_std": -1.7399626517273863,
|
397 |
+
"naucs_at_10_diff1": 1.0,
|
398 |
+
"naucs_at_20_max": 0.7222222222222276,
|
399 |
+
"naucs_at_20_std": -1.7399626517273863,
|
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 |
+
"arxivqa_test_subsampled": {
|
409 |
+
"ndcg_at_1": 0.866,
|
410 |
+
"ndcg_at_3": 0.90455,
|
411 |
+
"ndcg_at_5": 0.91117,
|
412 |
+
"ndcg_at_10": 0.91638,
|
413 |
+
"ndcg_at_20": 0.92041,
|
414 |
+
"ndcg_at_50": 0.92254,
|
415 |
+
"ndcg_at_100": 0.92416,
|
416 |
+
"map_at_1": 0.866,
|
417 |
+
"map_at_3": 0.89567,
|
418 |
+
"map_at_5": 0.89937,
|
419 |
+
"map_at_10": 0.90153,
|
420 |
+
"map_at_20": 0.90263,
|
421 |
+
"map_at_50": 0.90303,
|
422 |
+
"map_at_100": 0.90317,
|
423 |
+
"recall_at_1": 0.866,
|
424 |
+
"recall_at_3": 0.93,
|
425 |
+
"recall_at_5": 0.946,
|
426 |
+
"recall_at_10": 0.962,
|
427 |
+
"recall_at_20": 0.978,
|
428 |
+
"recall_at_50": 0.988,
|
429 |
+
"recall_at_100": 0.998,
|
430 |
+
"precision_at_1": 0.866,
|
431 |
+
"precision_at_3": 0.31,
|
432 |
+
"precision_at_5": 0.1892,
|
433 |
+
"precision_at_10": 0.0962,
|
434 |
+
"precision_at_20": 0.0489,
|
435 |
+
"precision_at_50": 0.01976,
|
436 |
+
"precision_at_100": 0.00998,
|
437 |
+
"mrr_at_1": 0.86,
|
438 |
+
"mrr_at_3": 0.8926666666666666,
|
439 |
+
"mrr_at_5": 0.8968666666666667,
|
440 |
+
"mrr_at_10": 0.8986880952380951,
|
441 |
+
"mrr_at_20": 0.8999191844103607,
|
442 |
+
"mrr_at_50": 0.9002436444330966,
|
443 |
+
"mrr_at_100": 0.9003898348214776,
|
444 |
+
"naucs_at_1_max": 0.8161638583392195,
|
445 |
+
"naucs_at_1_std": -0.018111189587326895,
|
446 |
+
"naucs_at_1_diff1": 0.9326505902532544,
|
447 |
+
"naucs_at_3_max": 0.8620114712551726,
|
448 |
+
"naucs_at_3_std": 0.06083766840069296,
|
449 |
+
"naucs_at_3_diff1": 0.9197012138188607,
|
450 |
+
"naucs_at_5_max": 0.8768025728810052,
|
451 |
+
"naucs_at_5_std": 0.2530345471521926,
|
452 |
+
"naucs_at_5_diff1": 0.9255628177196795,
|
453 |
+
"naucs_at_10_max": 0.8913951545530463,
|
454 |
+
"naucs_at_10_std": 0.26278932625681417,
|
455 |
+
"naucs_at_10_diff1": 0.9226006191950457,
|
456 |
+
"naucs_at_20_max": 0.9272133095662477,
|
457 |
+
"naucs_at_20_std": 0.3346490111195921,
|
458 |
+
"naucs_at_20_diff1": 0.9390968508615575,
|
459 |
+
"naucs_at_50_max": 0.931917211328972,
|
460 |
+
"naucs_at_50_std": 0.6713352007469628,
|
461 |
+
"naucs_at_50_diff1": 0.9564270152505482,
|
462 |
+
"naucs_at_100_max": 1.0,
|
463 |
+
"naucs_at_100_std": 1.0,
|
464 |
+
"naucs_at_100_diff1": 1.0
|
465 |
+
},
|
466 |
+
"tatdqa_test": {
|
467 |
+
"ndcg_at_1": 0.71264,
|
468 |
+
"ndcg_at_3": 0.8028,
|
469 |
+
"ndcg_at_5": 0.81922,
|
470 |
+
"ndcg_at_10": 0.83059,
|
471 |
+
"ndcg_at_20": 0.83583,
|
472 |
+
"ndcg_at_50": 0.83979,
|
473 |
+
"ndcg_at_100": 0.84207,
|
474 |
+
"map_at_1": 0.71264,
|
475 |
+
"map_at_3": 0.78119,
|
476 |
+
"map_at_5": 0.79039,
|
477 |
+
"map_at_10": 0.79529,
|
478 |
+
"map_at_20": 0.79682,
|
479 |
+
"map_at_50": 0.7975,
|
480 |
+
"map_at_100": 0.79771,
|
481 |
+
"recall_at_1": 0.71264,
|
482 |
+
"recall_at_3": 0.86513,
|
483 |
+
"recall_at_5": 0.90462,
|
484 |
+
"recall_at_10": 0.93864,
|
485 |
+
"recall_at_20": 0.95869,
|
486 |
+
"recall_at_50": 0.97813,
|
487 |
+
"recall_at_100": 0.9921,
|
488 |
+
"precision_at_1": 0.71264,
|
489 |
+
"precision_at_3": 0.28838,
|
490 |
+
"precision_at_5": 0.18092,
|
491 |
+
"precision_at_10": 0.09386,
|
492 |
+
"precision_at_20": 0.04793,
|
493 |
+
"precision_at_50": 0.01956,
|
494 |
+
"precision_at_100": 0.00992,
|
495 |
+
"mrr_at_1": 0.707168894289186,
|
496 |
+
"mrr_at_3": 0.7789590927501013,
|
497 |
+
"mrr_at_5": 0.7882543539894699,
|
498 |
+
"mrr_at_10": 0.7929583984261994,
|
499 |
+
"mrr_at_20": 0.7944539276081832,
|
500 |
+
"mrr_at_50": 0.7951441370914628,
|
501 |
+
"mrr_at_100": 0.7953321522389292,
|
502 |
+
"naucs_at_1_max": 0.267865154809863,
|
503 |
+
"naucs_at_1_std": -0.09367553525202181,
|
504 |
+
"naucs_at_1_diff1": 0.8523551929013733,
|
505 |
+
"naucs_at_3_max": 0.3637086940124698,
|
506 |
+
"naucs_at_3_std": 0.040842164765542366,
|
507 |
+
"naucs_at_3_diff1": 0.7686370221763869,
|
508 |
+
"naucs_at_5_max": 0.3777878526600295,
|
509 |
+
"naucs_at_5_std": 0.07406870671570945,
|
510 |
+
"naucs_at_5_diff1": 0.7558439662904856,
|
511 |
+
"naucs_at_10_max": 0.4896273289198233,
|
512 |
+
"naucs_at_10_std": 0.22965450771547347,
|
513 |
+
"naucs_at_10_diff1": 0.7505849146020235,
|
514 |
+
"naucs_at_20_max": 0.49880423324612594,
|
515 |
+
"naucs_at_20_std": 0.3289229815026192,
|
516 |
+
"naucs_at_20_diff1": 0.7088085588102754,
|
517 |
+
"naucs_at_50_max": 0.6671001388202468,
|
518 |
+
"naucs_at_50_std": 0.5531687668519774,
|
519 |
+
"naucs_at_50_diff1": 0.79460370844467,
|
520 |
+
"naucs_at_100_max": 0.7515505724064554,
|
521 |
+
"naucs_at_100_std": 0.5897764215843185,
|
522 |
+
"naucs_at_100_diff1": 0.7754412395814483
|
523 |
+
},
|
524 |
+
"docvqa_test_subsampled": {
|
525 |
+
"ndcg_at_1": 0.54989,
|
526 |
+
"ndcg_at_3": 0.6135,
|
527 |
+
"ndcg_at_5": 0.63058,
|
528 |
+
"ndcg_at_10": 0.65304,
|
529 |
+
"ndcg_at_20": 0.665,
|
530 |
+
"ndcg_at_50": 0.67275,
|
531 |
+
"ndcg_at_100": 0.67814,
|
532 |
+
"map_at_1": 0.54989,
|
533 |
+
"map_at_3": 0.59793,
|
534 |
+
"map_at_5": 0.60724,
|
535 |
+
"map_at_10": 0.61622,
|
536 |
+
"map_at_20": 0.6196,
|
537 |
+
"map_at_50": 0.62077,
|
538 |
+
"map_at_100": 0.62124,
|
539 |
+
"recall_at_1": 0.54989,
|
540 |
+
"recall_at_3": 0.65854,
|
541 |
+
"recall_at_5": 0.70067,
|
542 |
+
"recall_at_10": 0.77162,
|
543 |
+
"recall_at_20": 0.81818,
|
544 |
+
"recall_at_50": 0.85809,
|
545 |
+
"recall_at_100": 0.89135,
|
546 |
+
"precision_at_1": 0.54989,
|
547 |
+
"precision_at_3": 0.21951,
|
548 |
+
"precision_at_5": 0.14013,
|
549 |
+
"precision_at_10": 0.07716,
|
550 |
+
"precision_at_20": 0.04091,
|
551 |
+
"precision_at_50": 0.01716,
|
552 |
+
"precision_at_100": 0.00891,
|
553 |
+
"mrr_at_1": 0.5521064301552107,
|
554 |
+
"mrr_at_3": 0.5931263858093129,
|
555 |
+
"mrr_at_5": 0.6059866962305985,
|
556 |
+
"mrr_at_10": 0.6145892725161016,
|
557 |
+
"mrr_at_20": 0.6172970783835527,
|
558 |
+
"mrr_at_50": 0.6190029838259105,
|
559 |
+
"mrr_at_100": 0.6194633017577265,
|
560 |
+
"naucs_at_1_max": 0.3120684712170286,
|
561 |
+
"naucs_at_1_std": 0.7079281345869217,
|
562 |
+
"naucs_at_1_diff1": 0.917948356572515,
|
563 |
+
"naucs_at_3_max": 0.24008650595118855,
|
564 |
+
"naucs_at_3_std": 0.8128519605964449,
|
565 |
+
"naucs_at_3_diff1": 0.8473099212945505,
|
566 |
+
"naucs_at_5_max": 0.16205532036953102,
|
567 |
+
"naucs_at_5_std": 0.8560263843379905,
|
568 |
+
"naucs_at_5_diff1": 0.824925647993079,
|
569 |
+
"naucs_at_10_max": 0.012769751585812625,
|
570 |
+
"naucs_at_10_std": 0.9065613989192631,
|
571 |
+
"naucs_at_10_diff1": 0.8065057384718499,
|
572 |
+
"naucs_at_20_max": -0.06721876143851727,
|
573 |
+
"naucs_at_20_std": 0.9197324080389992,
|
574 |
+
"naucs_at_20_diff1": 0.7911368704615722,
|
575 |
+
"naucs_at_50_max": -0.17369534057340794,
|
576 |
+
"naucs_at_50_std": 0.9264211427158648,
|
577 |
+
"naucs_at_50_diff1": 0.7869124563082568,
|
578 |
+
"naucs_at_100_max": -0.22153475665071373,
|
579 |
+
"naucs_at_100_std": 0.9125411363750677,
|
580 |
+
"naucs_at_100_diff1": 0.7666876762968439
|
581 |
+
}
|
582 |
+
}
|