Distributional disagreement (sym-KL) on AMES (id-test)
-1.11Delta Sym-KL
Twin-bootstrap
Updated 20d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | -1.11 | - | -99 | |
2026.05 | -0.96 | - | -86 | |
2026.05 | -0.63 | - | -56 | |
2026.05 | -0.26 | - | -23 | |
2026.05 | -0.25 | - | -23 | |
2026.05 | - | 1.12 | - |