Create results.json
Browse files- results.json +1110 -0
results.json
ADDED
|
@@ -0,0 +1,1110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"timestamp": "2025-03-29T04:54:33.560612",
|
| 4 |
+
"vidore_benchmark_version": "5.0.1.dev6+g9e0da63"
|
| 5 |
+
},
|
| 6 |
+
"metrics": {
|
| 7 |
+
"vidore/arxivqa_test_subsampled": {
|
| 8 |
+
"ndcg_at_1": 0.846,
|
| 9 |
+
"ndcg_at_3": 0.88855,
|
| 10 |
+
"ndcg_at_5": 0.89268,
|
| 11 |
+
"ndcg_at_10": 0.90254,
|
| 12 |
+
"ndcg_at_20": 0.90708,
|
| 13 |
+
"ndcg_at_50": 0.91061,
|
| 14 |
+
"ndcg_at_100": 0.91093,
|
| 15 |
+
"map_at_1": 0.846,
|
| 16 |
+
"map_at_3": 0.87833,
|
| 17 |
+
"map_at_5": 0.88063,
|
| 18 |
+
"map_at_10": 0.8848,
|
| 19 |
+
"map_at_20": 0.88604,
|
| 20 |
+
"map_at_50": 0.88659,
|
| 21 |
+
"map_at_100": 0.88661,
|
| 22 |
+
"recall_at_1": 0.846,
|
| 23 |
+
"recall_at_3": 0.918,
|
| 24 |
+
"recall_at_5": 0.928,
|
| 25 |
+
"recall_at_10": 0.958,
|
| 26 |
+
"recall_at_20": 0.976,
|
| 27 |
+
"recall_at_50": 0.994,
|
| 28 |
+
"recall_at_100": 0.996,
|
| 29 |
+
"precision_at_1": 0.846,
|
| 30 |
+
"precision_at_3": 0.306,
|
| 31 |
+
"precision_at_5": 0.1856,
|
| 32 |
+
"precision_at_10": 0.0958,
|
| 33 |
+
"precision_at_20": 0.0488,
|
| 34 |
+
"precision_at_50": 0.01988,
|
| 35 |
+
"precision_at_100": 0.00996,
|
| 36 |
+
"mrr_at_1": 0.844,
|
| 37 |
+
"mrr_at_3": 0.8759999999999999,
|
| 38 |
+
"mrr_at_5": 0.8800999999999998,
|
| 39 |
+
"mrr_at_10": 0.8837873015873016,
|
| 40 |
+
"mrr_at_20": 0.884978105752177,
|
| 41 |
+
"mrr_at_50": 0.8854220490930644,
|
| 42 |
+
"mrr_at_100": 0.8854514608577703,
|
| 43 |
+
"naucs_at_1_max": 0.8450125179508687,
|
| 44 |
+
"naucs_at_1_std": 0.12069338010090619,
|
| 45 |
+
"naucs_at_1_diff1": 0.9621919758028649,
|
| 46 |
+
"naucs_at_3_max": 0.8291088793240907,
|
| 47 |
+
"naucs_at_3_std": 0.04603630069914268,
|
| 48 |
+
"naucs_at_3_diff1": 0.9314522556990277,
|
| 49 |
+
"naucs_at_5_max": 0.8539267558875412,
|
| 50 |
+
"naucs_at_5_std": 0.008105093889405354,
|
| 51 |
+
"naucs_at_5_diff1": 0.9332788671023967,
|
| 52 |
+
"naucs_at_10_max": 0.8914010048463799,
|
| 53 |
+
"naucs_at_10_std": 0.049175225645809645,
|
| 54 |
+
"naucs_at_10_diff1": 0.9502023031434798,
|
| 55 |
+
"naucs_at_20_max": 0.9564270152505446,
|
| 56 |
+
"naucs_at_20_std": 0.01746809835045214,
|
| 57 |
+
"naucs_at_20_diff1": 0.9673202614379051,
|
| 58 |
+
"naucs_at_50_max": 0.9564270152505304,
|
| 59 |
+
"naucs_at_50_std": 0.08667911609088286,
|
| 60 |
+
"naucs_at_50_diff1": 1.0,
|
| 61 |
+
"naucs_at_100_max": 0.9346405228758466,
|
| 62 |
+
"naucs_at_100_std": -0.3699813258636757,
|
| 63 |
+
"naucs_at_100_diff1": 1.0
|
| 64 |
+
},
|
| 65 |
+
"vidore/docvqa_test_subsampled": {
|
| 66 |
+
"ndcg_at_1": 0.5255,
|
| 67 |
+
"ndcg_at_3": 0.59022,
|
| 68 |
+
"ndcg_at_5": 0.6095,
|
| 69 |
+
"ndcg_at_10": 0.62215,
|
| 70 |
+
"ndcg_at_20": 0.63179,
|
| 71 |
+
"ndcg_at_50": 0.64578,
|
| 72 |
+
"ndcg_at_100": 0.65236,
|
| 73 |
+
"map_at_1": 0.5255,
|
| 74 |
+
"map_at_3": 0.57428,
|
| 75 |
+
"map_at_5": 0.58503,
|
| 76 |
+
"map_at_10": 0.5901,
|
| 77 |
+
"map_at_20": 0.59281,
|
| 78 |
+
"map_at_50": 0.5952,
|
| 79 |
+
"map_at_100": 0.59581,
|
| 80 |
+
"recall_at_1": 0.5255,
|
| 81 |
+
"recall_at_3": 0.63636,
|
| 82 |
+
"recall_at_5": 0.68293,
|
| 83 |
+
"recall_at_10": 0.72284,
|
| 84 |
+
"recall_at_20": 0.76053,
|
| 85 |
+
"recall_at_50": 0.82927,
|
| 86 |
+
"recall_at_100": 0.86918,
|
| 87 |
+
"precision_at_1": 0.5255,
|
| 88 |
+
"precision_at_3": 0.21212,
|
| 89 |
+
"precision_at_5": 0.13659,
|
| 90 |
+
"precision_at_10": 0.07228,
|
| 91 |
+
"precision_at_20": 0.03803,
|
| 92 |
+
"precision_at_50": 0.01659,
|
| 93 |
+
"precision_at_100": 0.00869,
|
| 94 |
+
"mrr_at_1": 0.5277161862527716,
|
| 95 |
+
"mrr_at_3": 0.5705838876570585,
|
| 96 |
+
"mrr_at_5": 0.5818920916481892,
|
| 97 |
+
"mrr_at_10": 0.5882844120648999,
|
| 98 |
+
"mrr_at_20": 0.5910046981583916,
|
| 99 |
+
"mrr_at_50": 0.5934130734663197,
|
| 100 |
+
"mrr_at_100": 0.5940080973172209,
|
| 101 |
+
"naucs_at_1_max": 0.8434550008318404,
|
| 102 |
+
"naucs_at_1_std": 0.6208689692801249,
|
| 103 |
+
"naucs_at_1_diff1": 0.9385878043485472,
|
| 104 |
+
"naucs_at_3_max": 0.8863600274794795,
|
| 105 |
+
"naucs_at_3_std": 0.7125812271959884,
|
| 106 |
+
"naucs_at_3_diff1": 0.8562659960495058,
|
| 107 |
+
"naucs_at_5_max": 0.8957204704811382,
|
| 108 |
+
"naucs_at_5_std": 0.7815099852986634,
|
| 109 |
+
"naucs_at_5_diff1": 0.840615203999516,
|
| 110 |
+
"naucs_at_10_max": 0.8805933290684814,
|
| 111 |
+
"naucs_at_10_std": 0.8036536055359992,
|
| 112 |
+
"naucs_at_10_diff1": 0.8108491152172002,
|
| 113 |
+
"naucs_at_20_max": 0.8758585787087045,
|
| 114 |
+
"naucs_at_20_std": 0.8547041593366219,
|
| 115 |
+
"naucs_at_20_diff1": 0.7963142602467446,
|
| 116 |
+
"naucs_at_50_max": 0.835882926621152,
|
| 117 |
+
"naucs_at_50_std": 0.8642924736770558,
|
| 118 |
+
"naucs_at_50_diff1": 0.7550004769464399,
|
| 119 |
+
"naucs_at_100_max": 0.8387505235524102,
|
| 120 |
+
"naucs_at_100_std": 0.891890167597154,
|
| 121 |
+
"naucs_at_100_diff1": 0.7425247689508792
|
| 122 |
+
},
|
| 123 |
+
"vidore/infovqa_test_subsampled": {
|
| 124 |
+
"ndcg_at_1": 0.90283,
|
| 125 |
+
"ndcg_at_3": 0.92647,
|
| 126 |
+
"ndcg_at_5": 0.93144,
|
| 127 |
+
"ndcg_at_10": 0.93484,
|
| 128 |
+
"ndcg_at_20": 0.93781,
|
| 129 |
+
"ndcg_at_50": 0.93953,
|
| 130 |
+
"ndcg_at_100": 0.94056,
|
| 131 |
+
"map_at_1": 0.90283,
|
| 132 |
+
"map_at_3": 0.92004,
|
| 133 |
+
"map_at_5": 0.92277,
|
| 134 |
+
"map_at_10": 0.92425,
|
| 135 |
+
"map_at_20": 0.92501,
|
| 136 |
+
"map_at_50": 0.92533,
|
| 137 |
+
"map_at_100": 0.92544,
|
| 138 |
+
"recall_at_1": 0.90283,
|
| 139 |
+
"recall_at_3": 0.94534,
|
| 140 |
+
"recall_at_5": 0.95749,
|
| 141 |
+
"recall_at_10": 0.96761,
|
| 142 |
+
"recall_at_20": 0.97976,
|
| 143 |
+
"recall_at_50": 0.98785,
|
| 144 |
+
"recall_at_100": 0.99393,
|
| 145 |
+
"precision_at_1": 0.90283,
|
| 146 |
+
"precision_at_3": 0.31511,
|
| 147 |
+
"precision_at_5": 0.1915,
|
| 148 |
+
"precision_at_10": 0.09676,
|
| 149 |
+
"precision_at_20": 0.04899,
|
| 150 |
+
"precision_at_50": 0.01976,
|
| 151 |
+
"precision_at_100": 0.00994,
|
| 152 |
+
"mrr_at_1": 0.902834008097166,
|
| 153 |
+
"mrr_at_3": 0.9193657219973007,
|
| 154 |
+
"mrr_at_5": 0.922098515519568,
|
| 155 |
+
"mrr_at_10": 0.9235404215667373,
|
| 156 |
+
"mrr_at_20": 0.924306062896783,
|
| 157 |
+
"mrr_at_50": 0.9246081217189239,
|
| 158 |
+
"mrr_at_100": 0.9247108914770626,
|
| 159 |
+
"naucs_at_1_max": 0.7209924833135752,
|
| 160 |
+
"naucs_at_1_std": 0.12016074691763526,
|
| 161 |
+
"naucs_at_1_diff1": 0.9700705001101573,
|
| 162 |
+
"naucs_at_3_max": 0.7991816729164284,
|
| 163 |
+
"naucs_at_3_std": 0.3632744107706446,
|
| 164 |
+
"naucs_at_3_diff1": 0.9806516364348475,
|
| 165 |
+
"naucs_at_5_max": 0.7968086782065312,
|
| 166 |
+
"naucs_at_5_std": 0.420630802871265,
|
| 167 |
+
"naucs_at_5_diff1": 0.9751235325590942,
|
| 168 |
+
"naucs_at_10_max": 0.921101425024486,
|
| 169 |
+
"naucs_at_10_std": 0.6268094022259476,
|
| 170 |
+
"naucs_at_10_diff1": 0.9755122273628534,
|
| 171 |
+
"naucs_at_20_max": 0.9461062354112437,
|
| 172 |
+
"naucs_at_20_std": 0.8385150814353919,
|
| 173 |
+
"naucs_at_20_diff1": 0.9869398545935244,
|
| 174 |
+
"naucs_at_50_max": 0.9319439680295378,
|
| 175 |
+
"naucs_at_50_std": 0.8051426050527639,
|
| 176 |
+
"naucs_at_50_diff1": 0.9782330909892136,
|
| 177 |
+
"naucs_at_100_max": 0.9074217540806789,
|
| 178 |
+
"naucs_at_100_std": 0.7588534820930969,
|
| 179 |
+
"naucs_at_100_diff1": 0.9564661819784259
|
| 180 |
+
},
|
| 181 |
+
"vidore/tabfquad_test_subsampled": {
|
| 182 |
+
"ndcg_at_1": 0.90714,
|
| 183 |
+
"ndcg_at_3": 0.9463,
|
| 184 |
+
"ndcg_at_5": 0.9506,
|
| 185 |
+
"ndcg_at_10": 0.95517,
|
| 186 |
+
"ndcg_at_20": 0.95606,
|
| 187 |
+
"ndcg_at_50": 0.95606,
|
| 188 |
+
"ndcg_at_100": 0.95606,
|
| 189 |
+
"map_at_1": 0.90714,
|
| 190 |
+
"map_at_3": 0.9375,
|
| 191 |
+
"map_at_5": 0.93982,
|
| 192 |
+
"map_at_10": 0.94168,
|
| 193 |
+
"map_at_20": 0.94192,
|
| 194 |
+
"map_at_50": 0.94192,
|
| 195 |
+
"map_at_100": 0.94192,
|
| 196 |
+
"recall_at_1": 0.90714,
|
| 197 |
+
"recall_at_3": 0.97143,
|
| 198 |
+
"recall_at_5": 0.98214,
|
| 199 |
+
"recall_at_10": 0.99643,
|
| 200 |
+
"recall_at_20": 1.0,
|
| 201 |
+
"recall_at_50": 1.0,
|
| 202 |
+
"recall_at_100": 1.0,
|
| 203 |
+
"precision_at_1": 0.90714,
|
| 204 |
+
"precision_at_3": 0.32381,
|
| 205 |
+
"precision_at_5": 0.19643,
|
| 206 |
+
"precision_at_10": 0.09964,
|
| 207 |
+
"precision_at_20": 0.05,
|
| 208 |
+
"precision_at_50": 0.02,
|
| 209 |
+
"precision_at_100": 0.01,
|
| 210 |
+
"mrr_at_1": 0.9035714285714286,
|
| 211 |
+
"mrr_at_3": 0.9363095238095239,
|
| 212 |
+
"mrr_at_5": 0.9393452380952383,
|
| 213 |
+
"mrr_at_10": 0.940609410430839,
|
| 214 |
+
"mrr_at_20": 0.9408475056689343,
|
| 215 |
+
"mrr_at_50": 0.9408475056689343,
|
| 216 |
+
"mrr_at_100": 0.9408475056689343,
|
| 217 |
+
"naucs_at_1_max": 0.4907886231415652,
|
| 218 |
+
"naucs_at_1_std": 0.07367305896717852,
|
| 219 |
+
"naucs_at_1_diff1": 0.9411226028873094,
|
| 220 |
+
"naucs_at_3_max": 0.9325980392156865,
|
| 221 |
+
"naucs_at_3_std": 0.8605275443510717,
|
| 222 |
+
"naucs_at_3_diff1": 0.9836601307189589,
|
| 223 |
+
"naucs_at_5_max": 0.9477124183006519,
|
| 224 |
+
"naucs_at_5_std": 0.8921568627451019,
|
| 225 |
+
"naucs_at_5_diff1": 1.0,
|
| 226 |
+
"naucs_at_10_max": 1.0,
|
| 227 |
+
"naucs_at_10_std": 1.0,
|
| 228 |
+
"naucs_at_10_diff1": 1.0,
|
| 229 |
+
"naucs_at_20_max": 1.0,
|
| 230 |
+
"naucs_at_20_std": 1.0,
|
| 231 |
+
"naucs_at_20_diff1": 1.0,
|
| 232 |
+
"naucs_at_50_max": 1.0,
|
| 233 |
+
"naucs_at_50_std": 1.0,
|
| 234 |
+
"naucs_at_50_diff1": 1.0,
|
| 235 |
+
"naucs_at_100_max": 1.0,
|
| 236 |
+
"naucs_at_100_std": 1.0,
|
| 237 |
+
"naucs_at_100_diff1": 1.0
|
| 238 |
+
},
|
| 239 |
+
"vidore/tatdqa_test": {
|
| 240 |
+
"ndcg_at_1": 0.71021,
|
| 241 |
+
"ndcg_at_3": 0.79884,
|
| 242 |
+
"ndcg_at_5": 0.81895,
|
| 243 |
+
"ndcg_at_10": 0.82925,
|
| 244 |
+
"ndcg_at_20": 0.83272,
|
| 245 |
+
"ndcg_at_50": 0.8365,
|
| 246 |
+
"ndcg_at_100": 0.83879,
|
| 247 |
+
"map_at_1": 0.71021,
|
| 248 |
+
"map_at_3": 0.77754,
|
| 249 |
+
"map_at_5": 0.78875,
|
| 250 |
+
"map_at_10": 0.79305,
|
| 251 |
+
"map_at_20": 0.79406,
|
| 252 |
+
"map_at_50": 0.79468,
|
| 253 |
+
"map_at_100": 0.79489,
|
| 254 |
+
"recall_at_1": 0.71021,
|
| 255 |
+
"recall_at_3": 0.86027,
|
| 256 |
+
"recall_at_5": 0.90887,
|
| 257 |
+
"recall_at_10": 0.94046,
|
| 258 |
+
"recall_at_20": 0.95383,
|
| 259 |
+
"recall_at_50": 0.97266,
|
| 260 |
+
"recall_at_100": 0.98663,
|
| 261 |
+
"precision_at_1": 0.71021,
|
| 262 |
+
"precision_at_3": 0.28676,
|
| 263 |
+
"precision_at_5": 0.18177,
|
| 264 |
+
"precision_at_10": 0.09405,
|
| 265 |
+
"precision_at_20": 0.04769,
|
| 266 |
+
"precision_at_50": 0.01945,
|
| 267 |
+
"precision_at_100": 0.00987,
|
| 268 |
+
"mrr_at_1": 0.7083839611178615,
|
| 269 |
+
"mrr_at_3": 0.7776427703523693,
|
| 270 |
+
"mrr_at_5": 0.7884568651275823,
|
| 271 |
+
"mrr_at_10": 0.7926182279311078,
|
| 272 |
+
"mrr_at_20": 0.7938033556784707,
|
| 273 |
+
"mrr_at_50": 0.7943286181934197,
|
| 274 |
+
"mrr_at_100": 0.794528350656401,
|
| 275 |
+
"naucs_at_1_max": 0.32793936285585046,
|
| 276 |
+
"naucs_at_1_std": 0.08355391640281296,
|
| 277 |
+
"naucs_at_1_diff1": 0.8694893936676271,
|
| 278 |
+
"naucs_at_3_max": 0.34310764558519663,
|
| 279 |
+
"naucs_at_3_std": 0.18112933511633622,
|
| 280 |
+
"naucs_at_3_diff1": 0.7842219442406141,
|
| 281 |
+
"naucs_at_5_max": 0.390411682837578,
|
| 282 |
+
"naucs_at_5_std": 0.22111733749024254,
|
| 283 |
+
"naucs_at_5_diff1": 0.7610946297461103,
|
| 284 |
+
"naucs_at_10_max": 0.4254863651763087,
|
| 285 |
+
"naucs_at_10_std": 0.3546779556060681,
|
| 286 |
+
"naucs_at_10_diff1": 0.741877974565238,
|
| 287 |
+
"naucs_at_20_max": 0.4767731303920113,
|
| 288 |
+
"naucs_at_20_std": 0.43791968327264075,
|
| 289 |
+
"naucs_at_20_diff1": 0.752451856406408,
|
| 290 |
+
"naucs_at_50_max": 0.4552115757814973,
|
| 291 |
+
"naucs_at_50_std": 0.4781223784163035,
|
| 292 |
+
"naucs_at_50_diff1": 0.7823468200671793,
|
| 293 |
+
"naucs_at_100_max": 0.4328728795889847,
|
| 294 |
+
"naucs_at_100_std": 0.6143216368426023,
|
| 295 |
+
"naucs_at_100_diff1": 0.7683765100159515
|
| 296 |
+
},
|
| 297 |
+
"vidore/shiftproject_test": {
|
| 298 |
+
"ndcg_at_1": 0.83,
|
| 299 |
+
"ndcg_at_3": 0.90809,
|
| 300 |
+
"ndcg_at_5": 0.91671,
|
| 301 |
+
"ndcg_at_10": 0.91986,
|
| 302 |
+
"ndcg_at_20": 0.91986,
|
| 303 |
+
"ndcg_at_50": 0.92166,
|
| 304 |
+
"ndcg_at_100": 0.92166,
|
| 305 |
+
"map_at_1": 0.83,
|
| 306 |
+
"map_at_3": 0.89,
|
| 307 |
+
"map_at_5": 0.895,
|
| 308 |
+
"map_at_10": 0.89625,
|
| 309 |
+
"map_at_20": 0.89625,
|
| 310 |
+
"map_at_50": 0.89647,
|
| 311 |
+
"map_at_100": 0.89647,
|
| 312 |
+
"recall_at_1": 0.83,
|
| 313 |
+
"recall_at_3": 0.96,
|
| 314 |
+
"recall_at_5": 0.98,
|
| 315 |
+
"recall_at_10": 0.99,
|
| 316 |
+
"recall_at_20": 0.99,
|
| 317 |
+
"recall_at_50": 1.0,
|
| 318 |
+
"recall_at_100": 1.0,
|
| 319 |
+
"precision_at_1": 0.83,
|
| 320 |
+
"precision_at_3": 0.32,
|
| 321 |
+
"precision_at_5": 0.196,
|
| 322 |
+
"precision_at_10": 0.099,
|
| 323 |
+
"precision_at_20": 0.0495,
|
| 324 |
+
"precision_at_50": 0.02,
|
| 325 |
+
"precision_at_100": 0.01,
|
| 326 |
+
"mrr_at_1": 0.85,
|
| 327 |
+
"mrr_at_3": 0.9033333333333334,
|
| 328 |
+
"mrr_at_5": 0.9083333333333334,
|
| 329 |
+
"mrr_at_10": 0.9095833333333334,
|
| 330 |
+
"mrr_at_20": 0.9095833333333334,
|
| 331 |
+
"mrr_at_50": 0.909810606060606,
|
| 332 |
+
"mrr_at_100": 0.909810606060606,
|
| 333 |
+
"naucs_at_1_max": 0.007865559876938088,
|
| 334 |
+
"naucs_at_1_std": -0.25152377082486815,
|
| 335 |
+
"naucs_at_1_diff1": 0.7144308353166549,
|
| 336 |
+
"naucs_at_3_max": 0.15744631185807553,
|
| 337 |
+
"naucs_at_3_std": -0.24976657329598614,
|
| 338 |
+
"naucs_at_3_diff1": 0.7741596638655437,
|
| 339 |
+
"naucs_at_5_max": 0.45611577964519334,
|
| 340 |
+
"naucs_at_5_std": 0.09337068160597826,
|
| 341 |
+
"naucs_at_5_diff1": 0.8692810457516353,
|
| 342 |
+
"naucs_at_10_max": 0.5541549953314738,
|
| 343 |
+
"naucs_at_10_std": 0.35807656395891135,
|
| 344 |
+
"naucs_at_10_diff1": 0.8692810457516413,
|
| 345 |
+
"naucs_at_20_max": 0.5541549953314738,
|
| 346 |
+
"naucs_at_20_std": 0.35807656395891135,
|
| 347 |
+
"naucs_at_20_diff1": 0.8692810457516413,
|
| 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 |
+
"vidore/syntheticDocQA_artificial_intelligence_test": {
|
| 356 |
+
"ndcg_at_1": 0.97,
|
| 357 |
+
"ndcg_at_3": 0.98893,
|
| 358 |
+
"ndcg_at_5": 0.98893,
|
| 359 |
+
"ndcg_at_10": 0.98893,
|
| 360 |
+
"ndcg_at_20": 0.98893,
|
| 361 |
+
"ndcg_at_50": 0.98893,
|
| 362 |
+
"ndcg_at_100": 0.98893,
|
| 363 |
+
"map_at_1": 0.97,
|
| 364 |
+
"map_at_3": 0.985,
|
| 365 |
+
"map_at_5": 0.985,
|
| 366 |
+
"map_at_10": 0.985,
|
| 367 |
+
"map_at_20": 0.985,
|
| 368 |
+
"map_at_50": 0.985,
|
| 369 |
+
"map_at_100": 0.985,
|
| 370 |
+
"recall_at_1": 0.97,
|
| 371 |
+
"recall_at_3": 1.0,
|
| 372 |
+
"recall_at_5": 1.0,
|
| 373 |
+
"recall_at_10": 1.0,
|
| 374 |
+
"recall_at_20": 1.0,
|
| 375 |
+
"recall_at_50": 1.0,
|
| 376 |
+
"recall_at_100": 1.0,
|
| 377 |
+
"precision_at_1": 0.97,
|
| 378 |
+
"precision_at_3": 0.33333,
|
| 379 |
+
"precision_at_5": 0.2,
|
| 380 |
+
"precision_at_10": 0.1,
|
| 381 |
+
"precision_at_20": 0.05,
|
| 382 |
+
"precision_at_50": 0.02,
|
| 383 |
+
"precision_at_100": 0.01,
|
| 384 |
+
"mrr_at_1": 0.98,
|
| 385 |
+
"mrr_at_3": 0.99,
|
| 386 |
+
"mrr_at_5": 0.99,
|
| 387 |
+
"mrr_at_10": 0.99,
|
| 388 |
+
"mrr_at_20": 0.99,
|
| 389 |
+
"mrr_at_50": 0.99,
|
| 390 |
+
"mrr_at_100": 0.99,
|
| 391 |
+
"naucs_at_1_max": 0.47945845004668913,
|
| 392 |
+
"naucs_at_1_std": -0.8445378151260531,
|
| 393 |
+
"naucs_at_1_diff1": 1.0,
|
| 394 |
+
"naucs_at_3_max": 1.0,
|
| 395 |
+
"naucs_at_3_std": 1.0,
|
| 396 |
+
"naucs_at_3_diff1": 1.0,
|
| 397 |
+
"naucs_at_5_max": 1.0,
|
| 398 |
+
"naucs_at_5_std": 1.0,
|
| 399 |
+
"naucs_at_5_diff1": 1.0,
|
| 400 |
+
"naucs_at_10_max": 1.0,
|
| 401 |
+
"naucs_at_10_std": 1.0,
|
| 402 |
+
"naucs_at_10_diff1": 1.0,
|
| 403 |
+
"naucs_at_20_max": 1.0,
|
| 404 |
+
"naucs_at_20_std": 1.0,
|
| 405 |
+
"naucs_at_20_diff1": 1.0,
|
| 406 |
+
"naucs_at_50_max": null,
|
| 407 |
+
"naucs_at_50_std": null,
|
| 408 |
+
"naucs_at_50_diff1": null,
|
| 409 |
+
"naucs_at_100_max": null,
|
| 410 |
+
"naucs_at_100_std": null,
|
| 411 |
+
"naucs_at_100_diff1": null
|
| 412 |
+
},
|
| 413 |
+
"vidore/syntheticDocQA_energy_test": {
|
| 414 |
+
"ndcg_at_1": 0.95,
|
| 415 |
+
"ndcg_at_3": 0.95631,
|
| 416 |
+
"ndcg_at_5": 0.96448,
|
| 417 |
+
"ndcg_at_10": 0.96749,
|
| 418 |
+
"ndcg_at_20": 0.96749,
|
| 419 |
+
"ndcg_at_50": 0.96965,
|
| 420 |
+
"ndcg_at_100": 0.96965,
|
| 421 |
+
"map_at_1": 0.95,
|
| 422 |
+
"map_at_3": 0.955,
|
| 423 |
+
"map_at_5": 0.9595,
|
| 424 |
+
"map_at_10": 0.96061,
|
| 425 |
+
"map_at_20": 0.96061,
|
| 426 |
+
"map_at_50": 0.96103,
|
| 427 |
+
"map_at_100": 0.96103,
|
| 428 |
+
"recall_at_1": 0.95,
|
| 429 |
+
"recall_at_3": 0.96,
|
| 430 |
+
"recall_at_5": 0.98,
|
| 431 |
+
"recall_at_10": 0.99,
|
| 432 |
+
"recall_at_20": 0.99,
|
| 433 |
+
"recall_at_50": 1.0,
|
| 434 |
+
"recall_at_100": 1.0,
|
| 435 |
+
"precision_at_1": 0.95,
|
| 436 |
+
"precision_at_3": 0.32,
|
| 437 |
+
"precision_at_5": 0.196,
|
| 438 |
+
"precision_at_10": 0.099,
|
| 439 |
+
"precision_at_20": 0.0495,
|
| 440 |
+
"precision_at_50": 0.02,
|
| 441 |
+
"precision_at_100": 0.01,
|
| 442 |
+
"mrr_at_1": 0.95,
|
| 443 |
+
"mrr_at_3": 0.955,
|
| 444 |
+
"mrr_at_5": 0.9595,
|
| 445 |
+
"mrr_at_10": 0.9606111111111111,
|
| 446 |
+
"mrr_at_20": 0.9606111111111111,
|
| 447 |
+
"mrr_at_50": 0.9610277777777777,
|
| 448 |
+
"mrr_at_100": 0.9610277777777777,
|
| 449 |
+
"naucs_at_1_max": 0.2974789915966388,
|
| 450 |
+
"naucs_at_1_std": -0.6985060690943007,
|
| 451 |
+
"naucs_at_1_diff1": 1.0,
|
| 452 |
+
"naucs_at_3_max": 0.8068394024276336,
|
| 453 |
+
"naucs_at_3_std": -0.5852007469654534,
|
| 454 |
+
"naucs_at_3_diff1": 1.0,
|
| 455 |
+
"naucs_at_5_max": 0.9346405228758136,
|
| 456 |
+
"naucs_at_5_std": -0.661531279178339,
|
| 457 |
+
"naucs_at_5_diff1": 1.0,
|
| 458 |
+
"naucs_at_10_max": 0.8692810457516413,
|
| 459 |
+
"naucs_at_10_std": -1.1517273576097316,
|
| 460 |
+
"naucs_at_10_diff1": 1.0,
|
| 461 |
+
"naucs_at_20_max": 0.8692810457516413,
|
| 462 |
+
"naucs_at_20_std": -1.1517273576097316,
|
| 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 |
+
"vidore/syntheticDocQA_government_reports_test": {
|
| 472 |
+
"ndcg_at_1": 0.95,
|
| 473 |
+
"ndcg_at_3": 0.97131,
|
| 474 |
+
"ndcg_at_5": 0.97131,
|
| 475 |
+
"ndcg_at_10": 0.97487,
|
| 476 |
+
"ndcg_at_20": 0.97487,
|
| 477 |
+
"ndcg_at_50": 0.97487,
|
| 478 |
+
"ndcg_at_100": 0.97487,
|
| 479 |
+
"map_at_1": 0.95,
|
| 480 |
+
"map_at_3": 0.965,
|
| 481 |
+
"map_at_5": 0.965,
|
| 482 |
+
"map_at_10": 0.96667,
|
| 483 |
+
"map_at_20": 0.96667,
|
| 484 |
+
"map_at_50": 0.96667,
|
| 485 |
+
"map_at_100": 0.96667,
|
| 486 |
+
"recall_at_1": 0.95,
|
| 487 |
+
"recall_at_3": 0.99,
|
| 488 |
+
"recall_at_5": 0.99,
|
| 489 |
+
"recall_at_10": 1.0,
|
| 490 |
+
"recall_at_20": 1.0,
|
| 491 |
+
"recall_at_50": 1.0,
|
| 492 |
+
"recall_at_100": 1.0,
|
| 493 |
+
"precision_at_1": 0.95,
|
| 494 |
+
"precision_at_3": 0.33,
|
| 495 |
+
"precision_at_5": 0.198,
|
| 496 |
+
"precision_at_10": 0.1,
|
| 497 |
+
"precision_at_20": 0.05,
|
| 498 |
+
"precision_at_50": 0.02,
|
| 499 |
+
"precision_at_100": 0.01,
|
| 500 |
+
"mrr_at_1": 0.95,
|
| 501 |
+
"mrr_at_3": 0.965,
|
| 502 |
+
"mrr_at_5": 0.965,
|
| 503 |
+
"mrr_at_10": 0.9666666666666667,
|
| 504 |
+
"mrr_at_20": 0.9666666666666667,
|
| 505 |
+
"mrr_at_50": 0.9666666666666667,
|
| 506 |
+
"mrr_at_100": 0.9666666666666667,
|
| 507 |
+
"naucs_at_1_max": 0.8888888888888874,
|
| 508 |
+
"naucs_at_1_std": 0.35079365079365044,
|
| 509 |
+
"naucs_at_1_diff1": 0.9477124183006508,
|
| 510 |
+
"naucs_at_3_max": 1.0,
|
| 511 |
+
"naucs_at_3_std": 0.12278244631183229,
|
| 512 |
+
"naucs_at_3_diff1": 1.0,
|
| 513 |
+
"naucs_at_5_max": 1.0,
|
| 514 |
+
"naucs_at_5_std": 0.12278244631185926,
|
| 515 |
+
"naucs_at_5_diff1": 1.0,
|
| 516 |
+
"naucs_at_10_max": 1.0,
|
| 517 |
+
"naucs_at_10_std": 1.0,
|
| 518 |
+
"naucs_at_10_diff1": 1.0,
|
| 519 |
+
"naucs_at_20_max": 1.0,
|
| 520 |
+
"naucs_at_20_std": 1.0,
|
| 521 |
+
"naucs_at_20_diff1": 1.0,
|
| 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 |
+
"vidore/syntheticDocQA_healthcare_industry_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": 0.795751633986929,
|
| 566 |
+
"naucs_at_1_std": 0.4225023342670396,
|
| 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 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered": {
|
| 588 |
+
"ndcg_at_1": 0.66875,
|
| 589 |
+
"ndcg_at_3": 0.6417,
|
| 590 |
+
"ndcg_at_5": 0.6613,
|
| 591 |
+
"ndcg_at_10": 0.69824,
|
| 592 |
+
"ndcg_at_20": 0.72188,
|
| 593 |
+
"ndcg_at_50": 0.74328,
|
| 594 |
+
"ndcg_at_100": 0.75194,
|
| 595 |
+
"map_at_1": 0.4007,
|
| 596 |
+
"map_at_3": 0.52943,
|
| 597 |
+
"map_at_5": 0.56838,
|
| 598 |
+
"map_at_10": 0.60781,
|
| 599 |
+
"map_at_20": 0.62312,
|
| 600 |
+
"map_at_50": 0.63095,
|
| 601 |
+
"map_at_100": 0.63309,
|
| 602 |
+
"recall_at_1": 0.4007,
|
| 603 |
+
"recall_at_3": 0.5939,
|
| 604 |
+
"recall_at_5": 0.67536,
|
| 605 |
+
"recall_at_10": 0.78359,
|
| 606 |
+
"recall_at_20": 0.85117,
|
| 607 |
+
"recall_at_50": 0.91501,
|
| 608 |
+
"recall_at_100": 0.9461,
|
| 609 |
+
"precision_at_1": 0.66875,
|
| 610 |
+
"precision_at_3": 0.38542,
|
| 611 |
+
"precision_at_5": 0.29375,
|
| 612 |
+
"precision_at_10": 0.19125,
|
| 613 |
+
"precision_at_20": 0.11063,
|
| 614 |
+
"precision_at_50": 0.05187,
|
| 615 |
+
"precision_at_100": 0.02794,
|
| 616 |
+
"mrr_at_1": 0.65625,
|
| 617 |
+
"mrr_at_3": 0.7458333333333331,
|
| 618 |
+
"mrr_at_5": 0.7564583333333331,
|
| 619 |
+
"mrr_at_10": 0.7618030753968252,
|
| 620 |
+
"mrr_at_20": 0.7638654799040827,
|
| 621 |
+
"mrr_at_50": 0.7643048738434767,
|
| 622 |
+
"mrr_at_100": 0.7644090405101435,
|
| 623 |
+
"naucs_at_1_max": 0.30756403626346956,
|
| 624 |
+
"naucs_at_1_std": -0.08408354529239741,
|
| 625 |
+
"naucs_at_1_diff1": 0.4076474126922141,
|
| 626 |
+
"naucs_at_3_max": 0.07090535127918343,
|
| 627 |
+
"naucs_at_3_std": 0.07019913294946659,
|
| 628 |
+
"naucs_at_3_diff1": -0.11532493775484426,
|
| 629 |
+
"naucs_at_5_max": -0.10528352726834586,
|
| 630 |
+
"naucs_at_5_std": 0.009354154420221325,
|
| 631 |
+
"naucs_at_5_diff1": -0.24880882401264726,
|
| 632 |
+
"naucs_at_10_max": -0.14362283829712982,
|
| 633 |
+
"naucs_at_10_std": -0.00400331274744239,
|
| 634 |
+
"naucs_at_10_diff1": -0.2469913716199774,
|
| 635 |
+
"naucs_at_20_max": -0.16803539193002953,
|
| 636 |
+
"naucs_at_20_std": 0.014308541119453818,
|
| 637 |
+
"naucs_at_20_diff1": -0.2642816490417616,
|
| 638 |
+
"naucs_at_50_max": -0.2187145395937884,
|
| 639 |
+
"naucs_at_50_std": 0.06759328457586304,
|
| 640 |
+
"naucs_at_50_diff1": -0.27016007321691166,
|
| 641 |
+
"naucs_at_100_max": -0.24400788682123695,
|
| 642 |
+
"naucs_at_100_std": 0.08084279607961682,
|
| 643 |
+
"naucs_at_100_diff1": -0.2754889685246749
|
| 644 |
+
},
|
| 645 |
+
"vidore/synthetic_economics_macro_economy_2024_filtered_v1.0": {
|
| 646 |
+
"ndcg_at_1": 0.62069,
|
| 647 |
+
"ndcg_at_3": 0.6092,
|
| 648 |
+
"ndcg_at_5": 0.59592,
|
| 649 |
+
"ndcg_at_10": 0.57743,
|
| 650 |
+
"ndcg_at_20": 0.60932,
|
| 651 |
+
"ndcg_at_50": 0.67311,
|
| 652 |
+
"ndcg_at_100": 0.71364,
|
| 653 |
+
"map_at_1": 0.08389,
|
| 654 |
+
"map_at_3": 0.19085,
|
| 655 |
+
"map_at_5": 0.26062,
|
| 656 |
+
"map_at_10": 0.32998,
|
| 657 |
+
"map_at_20": 0.39499,
|
| 658 |
+
"map_at_50": 0.4528,
|
| 659 |
+
"map_at_100": 0.48214,
|
| 660 |
+
"recall_at_1": 0.08389,
|
| 661 |
+
"recall_at_3": 0.23451,
|
| 662 |
+
"recall_at_5": 0.34383,
|
| 663 |
+
"recall_at_10": 0.46383,
|
| 664 |
+
"recall_at_20": 0.61979,
|
| 665 |
+
"recall_at_50": 0.80662,
|
| 666 |
+
"recall_at_100": 0.92438,
|
| 667 |
+
"precision_at_1": 0.62069,
|
| 668 |
+
"precision_at_3": 0.57471,
|
| 669 |
+
"precision_at_5": 0.53103,
|
| 670 |
+
"precision_at_10": 0.42586,
|
| 671 |
+
"precision_at_20": 0.32328,
|
| 672 |
+
"precision_at_50": 0.19759,
|
| 673 |
+
"precision_at_100": 0.12931,
|
| 674 |
+
"mrr_at_1": 0.6206896551724138,
|
| 675 |
+
"mrr_at_3": 0.7528735632183907,
|
| 676 |
+
"mrr_at_5": 0.7683908045977013,
|
| 677 |
+
"mrr_at_10": 0.7683908045977013,
|
| 678 |
+
"mrr_at_20": 0.7696223316912972,
|
| 679 |
+
"mrr_at_50": 0.7703719568787035,
|
| 680 |
+
"mrr_at_100": 0.7703719568787035,
|
| 681 |
+
"naucs_at_1_max": 0.17281905871299316,
|
| 682 |
+
"naucs_at_1_std": 0.27905569883146514,
|
| 683 |
+
"naucs_at_1_diff1": 0.08408668436821552,
|
| 684 |
+
"naucs_at_3_max": 0.10011229417523333,
|
| 685 |
+
"naucs_at_3_std": 0.16636937514765232,
|
| 686 |
+
"naucs_at_3_diff1": -0.012050364944396099,
|
| 687 |
+
"naucs_at_5_max": 0.1464930806524891,
|
| 688 |
+
"naucs_at_5_std": 0.1745709653462463,
|
| 689 |
+
"naucs_at_5_diff1": -0.029613513564870166,
|
| 690 |
+
"naucs_at_10_max": 0.17008192605864111,
|
| 691 |
+
"naucs_at_10_std": 0.2625597911601204,
|
| 692 |
+
"naucs_at_10_diff1": -0.01001710875601573,
|
| 693 |
+
"naucs_at_20_max": 0.10235282326738067,
|
| 694 |
+
"naucs_at_20_std": 0.2133598628675844,
|
| 695 |
+
"naucs_at_20_diff1": 0.018116554485469376,
|
| 696 |
+
"naucs_at_50_max": 0.003469746317767848,
|
| 697 |
+
"naucs_at_50_std": 0.1780522203133001,
|
| 698 |
+
"naucs_at_50_diff1": -0.033424370133009036,
|
| 699 |
+
"naucs_at_100_max": -0.09027964384749197,
|
| 700 |
+
"naucs_at_100_std": 0.08216836863021816,
|
| 701 |
+
"naucs_at_100_diff1": -0.034970785400879036
|
| 702 |
+
},
|
| 703 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0": {
|
| 704 |
+
"ndcg_at_1": 0.52632,
|
| 705 |
+
"ndcg_at_3": 0.55612,
|
| 706 |
+
"ndcg_at_5": 0.58127,
|
| 707 |
+
"ndcg_at_10": 0.61632,
|
| 708 |
+
"ndcg_at_20": 0.65128,
|
| 709 |
+
"ndcg_at_50": 0.68849,
|
| 710 |
+
"ndcg_at_100": 0.69812,
|
| 711 |
+
"map_at_1": 0.26028,
|
| 712 |
+
"map_at_3": 0.40415,
|
| 713 |
+
"map_at_5": 0.45641,
|
| 714 |
+
"map_at_10": 0.49836,
|
| 715 |
+
"map_at_20": 0.51815,
|
| 716 |
+
"map_at_50": 0.5376,
|
| 717 |
+
"map_at_100": 0.54301,
|
| 718 |
+
"recall_at_1": 0.26028,
|
| 719 |
+
"recall_at_3": 0.52421,
|
| 720 |
+
"recall_at_5": 0.62776,
|
| 721 |
+
"recall_at_10": 0.73759,
|
| 722 |
+
"recall_at_20": 0.85073,
|
| 723 |
+
"recall_at_50": 0.95624,
|
| 724 |
+
"recall_at_100": 0.98026,
|
| 725 |
+
"precision_at_1": 0.52632,
|
| 726 |
+
"precision_at_3": 0.38012,
|
| 727 |
+
"precision_at_5": 0.29825,
|
| 728 |
+
"precision_at_10": 0.19825,
|
| 729 |
+
"precision_at_20": 0.12456,
|
| 730 |
+
"precision_at_50": 0.06982,
|
| 731 |
+
"precision_at_100": 0.0386,
|
| 732 |
+
"mrr_at_1": 0.47368421052631576,
|
| 733 |
+
"mrr_at_3": 0.6403508771929824,
|
| 734 |
+
"mrr_at_5": 0.6473684210526315,
|
| 735 |
+
"mrr_at_10": 0.6510721247563352,
|
| 736 |
+
"mrr_at_20": 0.65645319592688,
|
| 737 |
+
"mrr_at_50": 0.656969191798913,
|
| 738 |
+
"mrr_at_100": 0.656969191798913,
|
| 739 |
+
"naucs_at_1_max": -0.3089087067237991,
|
| 740 |
+
"naucs_at_1_std": -0.3620464461508103,
|
| 741 |
+
"naucs_at_1_diff1": 0.26950692327391307,
|
| 742 |
+
"naucs_at_3_max": -0.2207300460743008,
|
| 743 |
+
"naucs_at_3_std": -0.06741698035051424,
|
| 744 |
+
"naucs_at_3_diff1": 0.25979433023582205,
|
| 745 |
+
"naucs_at_5_max": -0.1447362086814054,
|
| 746 |
+
"naucs_at_5_std": -0.03026829152849858,
|
| 747 |
+
"naucs_at_5_diff1": 0.20242934642758445,
|
| 748 |
+
"naucs_at_10_max": -0.19458395196496367,
|
| 749 |
+
"naucs_at_10_std": 0.014281524836361133,
|
| 750 |
+
"naucs_at_10_diff1": 0.0777278953601748,
|
| 751 |
+
"naucs_at_20_max": -0.29118824877525396,
|
| 752 |
+
"naucs_at_20_std": -0.020903684805961418,
|
| 753 |
+
"naucs_at_20_diff1": -0.10611639351967059,
|
| 754 |
+
"naucs_at_50_max": -0.3569642568932217,
|
| 755 |
+
"naucs_at_50_std": -0.050538218015740266,
|
| 756 |
+
"naucs_at_50_diff1": -0.20453025213923745,
|
| 757 |
+
"naucs_at_100_max": -0.3449115539174466,
|
| 758 |
+
"naucs_at_100_std": -0.006597932224841444,
|
| 759 |
+
"naucs_at_100_diff1": -0.23912028985395903
|
| 760 |
+
},
|
| 761 |
+
"vidore/synthetic_axa_filtered_v1.0": {
|
| 762 |
+
"ndcg_at_1": 0.55556,
|
| 763 |
+
"ndcg_at_3": 0.65245,
|
| 764 |
+
"ndcg_at_5": 0.67422,
|
| 765 |
+
"ndcg_at_10": 0.69412,
|
| 766 |
+
"ndcg_at_20": 0.72356,
|
| 767 |
+
"ndcg_at_50": 0.76083,
|
| 768 |
+
"ndcg_at_100": 0.77012,
|
| 769 |
+
"map_at_1": 0.33205,
|
| 770 |
+
"map_at_3": 0.4427,
|
| 771 |
+
"map_at_5": 0.51242,
|
| 772 |
+
"map_at_10": 0.58092,
|
| 773 |
+
"map_at_20": 0.60853,
|
| 774 |
+
"map_at_50": 0.63185,
|
| 775 |
+
"map_at_100": 0.63523,
|
| 776 |
+
"recall_at_1": 0.33205,
|
| 777 |
+
"recall_at_3": 0.53629,
|
| 778 |
+
"recall_at_5": 0.63362,
|
| 779 |
+
"recall_at_10": 0.76473,
|
| 780 |
+
"recall_at_20": 0.87608,
|
| 781 |
+
"recall_at_50": 0.9613,
|
| 782 |
+
"recall_at_100": 0.98765,
|
| 783 |
+
"precision_at_1": 0.55556,
|
| 784 |
+
"precision_at_3": 0.44444,
|
| 785 |
+
"precision_at_5": 0.4,
|
| 786 |
+
"precision_at_10": 0.28889,
|
| 787 |
+
"precision_at_20": 0.17778,
|
| 788 |
+
"precision_at_50": 0.08778,
|
| 789 |
+
"precision_at_100": 0.04667,
|
| 790 |
+
"mrr_at_1": 0.5555555555555556,
|
| 791 |
+
"mrr_at_3": 0.7037037037037037,
|
| 792 |
+
"mrr_at_5": 0.7175925925925926,
|
| 793 |
+
"mrr_at_10": 0.7175925925925926,
|
| 794 |
+
"mrr_at_20": 0.7212962962962962,
|
| 795 |
+
"mrr_at_50": 0.7212962962962962,
|
| 796 |
+
"mrr_at_100": 0.7212962962962962,
|
| 797 |
+
"naucs_at_1_max": 0.273325424755173,
|
| 798 |
+
"naucs_at_1_std": 0.30910760464389075,
|
| 799 |
+
"naucs_at_1_diff1": 0.4150916518174012,
|
| 800 |
+
"naucs_at_3_max": -0.6137789179273527,
|
| 801 |
+
"naucs_at_3_std": -0.4695290775057839,
|
| 802 |
+
"naucs_at_3_diff1": -0.18728844531342823,
|
| 803 |
+
"naucs_at_5_max": -0.621465701003557,
|
| 804 |
+
"naucs_at_5_std": -0.48529226853495566,
|
| 805 |
+
"naucs_at_5_diff1": -0.2895489481138995,
|
| 806 |
+
"naucs_at_10_max": -0.6844616087512149,
|
| 807 |
+
"naucs_at_10_std": -0.5491938342713693,
|
| 808 |
+
"naucs_at_10_diff1": -0.3997842666069631,
|
| 809 |
+
"naucs_at_20_max": -0.7369836153031677,
|
| 810 |
+
"naucs_at_20_std": -0.5537041155977006,
|
| 811 |
+
"naucs_at_20_diff1": -0.4671308441713653,
|
| 812 |
+
"naucs_at_50_max": -0.7286409969333564,
|
| 813 |
+
"naucs_at_50_std": -0.5274202789653719,
|
| 814 |
+
"naucs_at_50_diff1": -0.436336242874538,
|
| 815 |
+
"naucs_at_100_max": -0.7196786978149535,
|
| 816 |
+
"naucs_at_100_std": -0.5392516201828518,
|
| 817 |
+
"naucs_at_100_diff1": -0.41765856148039054
|
| 818 |
+
},
|
| 819 |
+
"vidore/synthetic_rse_restaurant_filtered_v1.0_multilingual": {
|
| 820 |
+
"ndcg_at_1": 0.49561,
|
| 821 |
+
"ndcg_at_3": 0.52255,
|
| 822 |
+
"ndcg_at_5": 0.56941,
|
| 823 |
+
"ndcg_at_10": 0.60986,
|
| 824 |
+
"ndcg_at_20": 0.64548,
|
| 825 |
+
"ndcg_at_50": 0.67753,
|
| 826 |
+
"ndcg_at_100": 0.69032,
|
| 827 |
+
"map_at_1": 0.25293,
|
| 828 |
+
"map_at_3": 0.38225,
|
| 829 |
+
"map_at_5": 0.44555,
|
| 830 |
+
"map_at_10": 0.49002,
|
| 831 |
+
"map_at_20": 0.51143,
|
| 832 |
+
"map_at_50": 0.52918,
|
| 833 |
+
"map_at_100": 0.53512,
|
| 834 |
+
"recall_at_1": 0.25293,
|
| 835 |
+
"recall_at_3": 0.48103,
|
| 836 |
+
"recall_at_5": 0.62079,
|
| 837 |
+
"recall_at_10": 0.74725,
|
| 838 |
+
"recall_at_20": 0.86193,
|
| 839 |
+
"recall_at_50": 0.94719,
|
| 840 |
+
"recall_at_100": 0.98575,
|
| 841 |
+
"precision_at_1": 0.49561,
|
| 842 |
+
"precision_at_3": 0.35965,
|
| 843 |
+
"precision_at_5": 0.3,
|
| 844 |
+
"precision_at_10": 0.20044,
|
| 845 |
+
"precision_at_20": 0.12566,
|
| 846 |
+
"precision_at_50": 0.06921,
|
| 847 |
+
"precision_at_100": 0.03873,
|
| 848 |
+
"mrr_at_1": 0.4605263157894737,
|
| 849 |
+
"mrr_at_3": 0.600877192982456,
|
| 850 |
+
"mrr_at_5": 0.6201754385964913,
|
| 851 |
+
"mrr_at_10": 0.6277899610136451,
|
| 852 |
+
"mrr_at_20": 0.632304501054501,
|
| 853 |
+
"mrr_at_50": 0.632715568418136,
|
| 854 |
+
"mrr_at_100": 0.6328516145519891,
|
| 855 |
+
"naucs_at_1_max": -0.24080548401193705,
|
| 856 |
+
"naucs_at_1_std": -0.24229129773797134,
|
| 857 |
+
"naucs_at_1_diff1": 0.2566309953634961,
|
| 858 |
+
"naucs_at_3_max": -0.11573008196728155,
|
| 859 |
+
"naucs_at_3_std": -0.007165809143423392,
|
| 860 |
+
"naucs_at_3_diff1": 0.148079184923162,
|
| 861 |
+
"naucs_at_5_max": -0.1049432299517142,
|
| 862 |
+
"naucs_at_5_std": -0.016303988468535046,
|
| 863 |
+
"naucs_at_5_diff1": 0.09619296953820566,
|
| 864 |
+
"naucs_at_10_max": -0.12738872206780832,
|
| 865 |
+
"naucs_at_10_std": 0.0342733554094555,
|
| 866 |
+
"naucs_at_10_diff1": -0.0031293439071024384,
|
| 867 |
+
"naucs_at_20_max": -0.16828230912628597,
|
| 868 |
+
"naucs_at_20_std": 0.03349608653409504,
|
| 869 |
+
"naucs_at_20_diff1": -0.1295387505122871,
|
| 870 |
+
"naucs_at_50_max": -0.22669113877952793,
|
| 871 |
+
"naucs_at_50_std": 0.02892479553383963,
|
| 872 |
+
"naucs_at_50_diff1": -0.23893906138517593,
|
| 873 |
+
"naucs_at_100_max": -0.21963385965258986,
|
| 874 |
+
"naucs_at_100_std": 0.07333502866946137,
|
| 875 |
+
"naucs_at_100_diff1": -0.2789374899236579
|
| 876 |
+
},
|
| 877 |
+
"vidore/synthetic_axa_filtered_v1.0_multilingual": {
|
| 878 |
+
"ndcg_at_1": 0.47222,
|
| 879 |
+
"ndcg_at_3": 0.57264,
|
| 880 |
+
"ndcg_at_5": 0.59702,
|
| 881 |
+
"ndcg_at_10": 0.62186,
|
| 882 |
+
"ndcg_at_20": 0.64871,
|
| 883 |
+
"ndcg_at_50": 0.69211,
|
| 884 |
+
"ndcg_at_100": 0.70854,
|
| 885 |
+
"map_at_1": 0.26287,
|
| 886 |
+
"map_at_3": 0.38199,
|
| 887 |
+
"map_at_5": 0.44875,
|
| 888 |
+
"map_at_10": 0.50906,
|
| 889 |
+
"map_at_20": 0.53467,
|
| 890 |
+
"map_at_50": 0.55691,
|
| 891 |
+
"map_at_100": 0.56112,
|
| 892 |
+
"recall_at_1": 0.26287,
|
| 893 |
+
"recall_at_3": 0.48608,
|
| 894 |
+
"recall_at_5": 0.59926,
|
| 895 |
+
"recall_at_10": 0.72177,
|
| 896 |
+
"recall_at_20": 0.8083,
|
| 897 |
+
"recall_at_50": 0.91362,
|
| 898 |
+
"recall_at_100": 0.97557,
|
| 899 |
+
"precision_at_1": 0.47222,
|
| 900 |
+
"precision_at_3": 0.39815,
|
| 901 |
+
"precision_at_5": 0.35278,
|
| 902 |
+
"precision_at_10": 0.25417,
|
| 903 |
+
"precision_at_20": 0.15972,
|
| 904 |
+
"precision_at_50": 0.08306,
|
| 905 |
+
"precision_at_100": 0.04514,
|
| 906 |
+
"mrr_at_1": 0.4722222222222222,
|
| 907 |
+
"mrr_at_3": 0.6226851851851852,
|
| 908 |
+
"mrr_at_5": 0.6386574074074074,
|
| 909 |
+
"mrr_at_10": 0.6421296296296296,
|
| 910 |
+
"mrr_at_20": 0.6446441539578793,
|
| 911 |
+
"mrr_at_50": 0.6453055296192551,
|
| 912 |
+
"mrr_at_100": 0.6457492415868007,
|
| 913 |
+
"naucs_at_1_max": 0.2529652438308716,
|
| 914 |
+
"naucs_at_1_std": 0.2770911675122595,
|
| 915 |
+
"naucs_at_1_diff1": 0.3332157173129581,
|
| 916 |
+
"naucs_at_3_max": -0.2624572173683075,
|
| 917 |
+
"naucs_at_3_std": -0.1647564876291855,
|
| 918 |
+
"naucs_at_3_diff1": -0.23020181455626973,
|
| 919 |
+
"naucs_at_5_max": -0.3312941171013394,
|
| 920 |
+
"naucs_at_5_std": -0.22957466421975894,
|
| 921 |
+
"naucs_at_5_diff1": -0.2968823812573124,
|
| 922 |
+
"naucs_at_10_max": -0.4218539955783105,
|
| 923 |
+
"naucs_at_10_std": -0.24161976745630986,
|
| 924 |
+
"naucs_at_10_diff1": -0.35725981793366396,
|
| 925 |
+
"naucs_at_20_max": -0.46067265603833846,
|
| 926 |
+
"naucs_at_20_std": -0.21758871325930773,
|
| 927 |
+
"naucs_at_20_diff1": -0.4361139734376689,
|
| 928 |
+
"naucs_at_50_max": -0.5078470632319775,
|
| 929 |
+
"naucs_at_50_std": -0.22145210943780846,
|
| 930 |
+
"naucs_at_50_diff1": -0.4588177782881521,
|
| 931 |
+
"naucs_at_100_max": -0.5221289875651529,
|
| 932 |
+
"naucs_at_100_std": -0.2612386533865634,
|
| 933 |
+
"naucs_at_100_diff1": -0.4622709868852015
|
| 934 |
+
},
|
| 935 |
+
"vidore/synthetic_mit_biomedical_tissue_interactions_unfiltered_multilingual": {
|
| 936 |
+
"ndcg_at_1": 0.63438,
|
| 937 |
+
"ndcg_at_3": 0.62201,
|
| 938 |
+
"ndcg_at_5": 0.64286,
|
| 939 |
+
"ndcg_at_10": 0.67506,
|
| 940 |
+
"ndcg_at_20": 0.70183,
|
| 941 |
+
"ndcg_at_50": 0.72203,
|
| 942 |
+
"ndcg_at_100": 0.73249,
|
| 943 |
+
"map_at_1": 0.37943,
|
| 944 |
+
"map_at_3": 0.50859,
|
| 945 |
+
"map_at_5": 0.54911,
|
| 946 |
+
"map_at_10": 0.58498,
|
| 947 |
+
"map_at_20": 0.60163,
|
| 948 |
+
"map_at_50": 0.60896,
|
| 949 |
+
"map_at_100": 0.61143,
|
| 950 |
+
"recall_at_1": 0.37943,
|
| 951 |
+
"recall_at_3": 0.57556,
|
| 952 |
+
"recall_at_5": 0.66588,
|
| 953 |
+
"recall_at_10": 0.76488,
|
| 954 |
+
"recall_at_20": 0.83818,
|
| 955 |
+
"recall_at_50": 0.90049,
|
| 956 |
+
"recall_at_100": 0.93787,
|
| 957 |
+
"precision_at_1": 0.63438,
|
| 958 |
+
"precision_at_3": 0.38021,
|
| 959 |
+
"precision_at_5": 0.28844,
|
| 960 |
+
"precision_at_10": 0.18469,
|
| 961 |
+
"precision_at_20": 0.10945,
|
| 962 |
+
"precision_at_50": 0.05062,
|
| 963 |
+
"precision_at_100": 0.02764,
|
| 964 |
+
"mrr_at_1": 0.628125,
|
| 965 |
+
"mrr_at_3": 0.7169270833333328,
|
| 966 |
+
"mrr_at_5": 0.7309114583333327,
|
| 967 |
+
"mrr_at_10": 0.7371614583333328,
|
| 968 |
+
"mrr_at_20": 0.7390357216997715,
|
| 969 |
+
"mrr_at_50": 0.7397633603096262,
|
| 970 |
+
"mrr_at_100": 0.7398304785536334,
|
| 971 |
+
"naucs_at_1_max": 0.1453255594666248,
|
| 972 |
+
"naucs_at_1_std": -0.13075943305407295,
|
| 973 |
+
"naucs_at_1_diff1": 0.45529697520228624,
|
| 974 |
+
"naucs_at_3_max": 0.0405855928262303,
|
| 975 |
+
"naucs_at_3_std": -0.08315040203983201,
|
| 976 |
+
"naucs_at_3_diff1": -0.06475583733859824,
|
| 977 |
+
"naucs_at_5_max": -0.015242921963913872,
|
| 978 |
+
"naucs_at_5_std": -0.06714686840424429,
|
| 979 |
+
"naucs_at_5_diff1": -0.1905324708199068,
|
| 980 |
+
"naucs_at_10_max": -0.08598060050339351,
|
| 981 |
+
"naucs_at_10_std": -0.07140040506088999,
|
| 982 |
+
"naucs_at_10_diff1": -0.22563239289159312,
|
| 983 |
+
"naucs_at_20_max": -0.09063577299474389,
|
| 984 |
+
"naucs_at_20_std": -0.01558920763779827,
|
| 985 |
+
"naucs_at_20_diff1": -0.2565930359630854,
|
| 986 |
+
"naucs_at_50_max": -0.11508082629877682,
|
| 987 |
+
"naucs_at_50_std": 0.019171088523963847,
|
| 988 |
+
"naucs_at_50_diff1": -0.2618590007895247,
|
| 989 |
+
"naucs_at_100_max": -0.13214324446485648,
|
| 990 |
+
"naucs_at_100_std": 0.03196841407290063,
|
| 991 |
+
"naucs_at_100_diff1": -0.2604190397720941
|
| 992 |
+
},
|
| 993 |
+
"vidore/synthetics_economics_macro_economy_2024_filtered_v1.0_multilingual": {
|
| 994 |
+
"ndcg_at_1": 0.54741,
|
| 995 |
+
"ndcg_at_3": 0.5599,
|
| 996 |
+
"ndcg_at_5": 0.54853,
|
| 997 |
+
"ndcg_at_10": 0.545,
|
| 998 |
+
"ndcg_at_20": 0.5783,
|
| 999 |
+
"ndcg_at_50": 0.65023,
|
| 1000 |
+
"ndcg_at_100": 0.68802,
|
| 1001 |
+
"map_at_1": 0.06945,
|
| 1002 |
+
"map_at_3": 0.17107,
|
| 1003 |
+
"map_at_5": 0.22726,
|
| 1004 |
+
"map_at_10": 0.29871,
|
| 1005 |
+
"map_at_20": 0.36215,
|
| 1006 |
+
"map_at_50": 0.424,
|
| 1007 |
+
"map_at_100": 0.45027,
|
| 1008 |
+
"recall_at_1": 0.06945,
|
| 1009 |
+
"recall_at_3": 0.23305,
|
| 1010 |
+
"recall_at_5": 0.32172,
|
| 1011 |
+
"recall_at_10": 0.44954,
|
| 1012 |
+
"recall_at_20": 0.60295,
|
| 1013 |
+
"recall_at_50": 0.80472,
|
| 1014 |
+
"recall_at_100": 0.91982,
|
| 1015 |
+
"precision_at_1": 0.54741,
|
| 1016 |
+
"precision_at_3": 0.53305,
|
| 1017 |
+
"precision_at_5": 0.49397,
|
| 1018 |
+
"precision_at_10": 0.40991,
|
| 1019 |
+
"precision_at_20": 0.31358,
|
| 1020 |
+
"precision_at_50": 0.19905,
|
| 1021 |
+
"precision_at_100": 0.12728,
|
| 1022 |
+
"mrr_at_1": 0.5474137931034483,
|
| 1023 |
+
"mrr_at_3": 0.704022988505747,
|
| 1024 |
+
"mrr_at_5": 0.7195402298850573,
|
| 1025 |
+
"mrr_at_10": 0.7225933908045975,
|
| 1026 |
+
"mrr_at_20": 0.7235478243021344,
|
| 1027 |
+
"mrr_at_50": 0.7237352305989859,
|
| 1028 |
+
"mrr_at_100": 0.7237352305989859,
|
| 1029 |
+
"naucs_at_1_max": 0.00998672510834403,
|
| 1030 |
+
"naucs_at_1_std": 0.11928244010618376,
|
| 1031 |
+
"naucs_at_1_diff1": 0.18435607419736183,
|
| 1032 |
+
"naucs_at_3_max": 0.09061238892019206,
|
| 1033 |
+
"naucs_at_3_std": 0.16830880934007303,
|
| 1034 |
+
"naucs_at_3_diff1": 0.12321929418645422,
|
| 1035 |
+
"naucs_at_5_max": 0.06486164706859976,
|
| 1036 |
+
"naucs_at_5_std": 0.12775077647982017,
|
| 1037 |
+
"naucs_at_5_diff1": 0.1277592323026615,
|
| 1038 |
+
"naucs_at_10_max": 0.08518832038722114,
|
| 1039 |
+
"naucs_at_10_std": 0.16693423956201361,
|
| 1040 |
+
"naucs_at_10_diff1": 0.031238610885063946,
|
| 1041 |
+
"naucs_at_20_max": 0.09752587635034847,
|
| 1042 |
+
"naucs_at_20_std": 0.20072724900497335,
|
| 1043 |
+
"naucs_at_20_diff1": 0.018717834286324002,
|
| 1044 |
+
"naucs_at_50_max": 0.03561724408666398,
|
| 1045 |
+
"naucs_at_50_std": 0.15990917660678955,
|
| 1046 |
+
"naucs_at_50_diff1": -0.06346129978133774,
|
| 1047 |
+
"naucs_at_100_max": -0.028342706470580726,
|
| 1048 |
+
"naucs_at_100_std": 0.09244086442839103,
|
| 1049 |
+
"naucs_at_100_diff1": -0.07780688597803101
|
| 1050 |
+
},
|
| 1051 |
+
"vidore/restaurant_esg_reports_beir": {
|
| 1052 |
+
"ndcg_at_1": 0.64103,
|
| 1053 |
+
"ndcg_at_3": 0.64351,
|
| 1054 |
+
"ndcg_at_5": 0.67059,
|
| 1055 |
+
"ndcg_at_10": 0.70704,
|
| 1056 |
+
"ndcg_at_20": 0.72722,
|
| 1057 |
+
"ndcg_at_50": 0.74931,
|
| 1058 |
+
"ndcg_at_100": 0.7528,
|
| 1059 |
+
"map_at_1": 0.42885,
|
| 1060 |
+
"map_at_3": 0.56026,
|
| 1061 |
+
"map_at_5": 0.60129,
|
| 1062 |
+
"map_at_10": 0.62973,
|
| 1063 |
+
"map_at_20": 0.64241,
|
| 1064 |
+
"map_at_50": 0.64967,
|
| 1065 |
+
"map_at_100": 0.65059,
|
| 1066 |
+
"recall_at_1": 0.42885,
|
| 1067 |
+
"recall_at_3": 0.63173,
|
| 1068 |
+
"recall_at_5": 0.7295,
|
| 1069 |
+
"recall_at_10": 0.81704,
|
| 1070 |
+
"recall_at_20": 0.8714,
|
| 1071 |
+
"recall_at_50": 0.95845,
|
| 1072 |
+
"recall_at_100": 0.9711,
|
| 1073 |
+
"precision_at_1": 0.65385,
|
| 1074 |
+
"precision_at_3": 0.35897,
|
| 1075 |
+
"precision_at_5": 0.26923,
|
| 1076 |
+
"precision_at_10": 0.16346,
|
| 1077 |
+
"precision_at_20": 0.09519,
|
| 1078 |
+
"precision_at_50": 0.04346,
|
| 1079 |
+
"precision_at_100": 0.0225,
|
| 1080 |
+
"mrr_at_1": 0.6730769230769231,
|
| 1081 |
+
"mrr_at_3": 0.7339743589743589,
|
| 1082 |
+
"mrr_at_5": 0.7483974358974359,
|
| 1083 |
+
"mrr_at_10": 0.7558150183150183,
|
| 1084 |
+
"mrr_at_20": 0.7589368964368963,
|
| 1085 |
+
"mrr_at_50": 0.7600091917131535,
|
| 1086 |
+
"mrr_at_100": 0.7600091917131535,
|
| 1087 |
+
"naucs_at_1_max": 0.16031697778241094,
|
| 1088 |
+
"naucs_at_1_std": 0.03122729708497878,
|
| 1089 |
+
"naucs_at_1_diff1": 0.691822071573433,
|
| 1090 |
+
"naucs_at_3_max": 0.08627887141319174,
|
| 1091 |
+
"naucs_at_3_std": 0.016217193776361664,
|
| 1092 |
+
"naucs_at_3_diff1": -0.005764084746853097,
|
| 1093 |
+
"naucs_at_5_max": 0.12150676334655493,
|
| 1094 |
+
"naucs_at_5_std": 0.1459461309588857,
|
| 1095 |
+
"naucs_at_5_diff1": -0.11774835728053674,
|
| 1096 |
+
"naucs_at_10_max": 0.007908068459048687,
|
| 1097 |
+
"naucs_at_10_std": 0.17745560826730747,
|
| 1098 |
+
"naucs_at_10_diff1": -0.23754271742179867,
|
| 1099 |
+
"naucs_at_20_max": -0.0740960904448303,
|
| 1100 |
+
"naucs_at_20_std": 0.17166248162182116,
|
| 1101 |
+
"naucs_at_20_diff1": -0.3126851801378383,
|
| 1102 |
+
"naucs_at_50_max": -0.13339720566722635,
|
| 1103 |
+
"naucs_at_50_std": 0.13542366187464194,
|
| 1104 |
+
"naucs_at_50_diff1": -0.35317283000026634,
|
| 1105 |
+
"naucs_at_100_max": -0.16612439675549276,
|
| 1106 |
+
"naucs_at_100_std": 0.10724055764337584,
|
| 1107 |
+
"naucs_at_100_diff1": -0.35158659929056096
|
| 1108 |
+
}
|
| 1109 |
+
}
|
| 1110 |
+
}
|