Distributional disagreement (sym-KL) on BBBP (id-test)
-0.46Delta Sym-KL Divergence
Twin-bootstrap
Updated 20d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | -0.46 | - | -98 | |
2026.05 | -0.4 | - | -85 | |
2026.05 | -0.25 | - | -54 | |
2026.05 | -0.06 | - | -13 | |
2026.05 | -0.05 | - | -11 | |
2026.05 | - | 0.47 | - |