Seat-swap comparisons
4 of 32 matched pair(s), paired on
instance_id, seed, arm and selected by largest-effect. 32 episode(s) left, 32 right, 32 shared key(s). The primary/USW/worst-off columns are DELTAS (right minus left), not levels.| page | model | arm | visibility | instance | difficulty | parameter tags | seed | outcome | primary | dist NBS | USW | worst-off | fabricated | hazards | score Δ | total regret |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| scorable_negotiation-L0-eddb2da273 seed 1 · moves_chat · swapped Avery | Qwen3-8B vs advocate_mixed | moves_chat | PRIVATE | scorable_negotiation-L0-eddb2da273 | — | — | 1.000 | no deal | -1.000 | — | -44.0 | -6.000 | 0% | 1 no-ballot budget 32768 | -1.000 | — |
| scorable_negotiation-L0-119dfa1112 seed 0 · moves_chat · swapped Avery | Qwen3-8B vs advocate_mixed | moves_chat | PRIVATE | scorable_negotiation-L0-119dfa1112 | — | — | 0.000 | no deal | -1.000 | — | -54.5 | -19.5 | 0% | budget 32768 | -1.000 | — |
| scorable_negotiation-L0-90316f9784 seed 0 · moves_chat · swapped Avery | Qwen3-8B vs advocate_mixed | moves_chat | PRIVATE | scorable_negotiation-L0-90316f9784 | — | — | 0.000 | no deal | -1.000 | — | -48.5 | -2.500 | 0% | budget 32768 | -1.000 | — |
| scorable_negotiation-L0-5646c8be3d seed 0 · moves_chat · swapped Avery | Qwen3-8B vs advocate_mixed | moves_chat | PRIVATE | scorable_negotiation-L0-5646c8be3d | — | — | 0.000 | deal | 1.000 | — | 53.4 | 13.4 | 0% | budget 32768 | 1.000 | — |
Click a column header to sort; / focuses the filter, Enter opens the first row that survives it.