Run T-0031 passed
· Evidence: SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops.
Hypothesis
Generating only legal captures, en passant moves, and promotions outside check should strengthen play by avoiding make/unmake work for quiet moves that quiescence discards while preserving the search tree.
Predecessor set to: T-0031
Stages
| Field | short stage | long stage |
|---|---|---|
| Verdict | passed | passed |
| Elo Strength difference to the opponent, estimated from the games, with a 95-percent half-width where the oracle reported one. Never an absolute rating. | +48.65 ± 15.12 | +1,075.01 |
| nElo Normalised Elo: the Elo difference divided by the spread of the game results, so that the SPRT bounds mean the same at different time controls. | +63.56 ± 19.48 | +3,829.68 ± 30.83 |
| Games | 1,222 | 488 |
| Wins / draws / losses | 501 / 390 / 331 | 487 / 0 / 1 |
| pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points. | 39 / 92 / 223 / 174 / 83 | 0 / 0 / 1 / 0 / 243 |
| LLR Log-likelihood ratio, the running evidence of an SPRT. It starts at 0; a stage passes at the upper bound (about +2.94) and fails at the lower one (about −2.94). | +2.96 | +2.96 |
| Bounds | −2.94 … +2.94 | −2.94 … +2.94 |
| SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops. | [0.0, 5.0] | [0.0, 3.0] |
| Error rates α / β | 0.05 / 0.05 | 0.05 / 0.05 |
| Model | normalized | normalized |
| time control Base time plus increment per move in seconds, e.g. 8+0.08: eight seconds per game plus 0.08 seconds per move. | 8+0.08 | 40+0.4 |
| Book | A | B |
| Opponent | vs predecessor | vs reference v0 |
| Duration | 9 min | 9 min |
Provenance
- Date
- 2026-08-29
- Started
- 2026-08-29 17:19:56 UTC
- Duration
- 18 min
- Author
- Agent B
- Bench nodes
- 3,786
- Commit
7ab0d26d476901f33137f400d4b0cf932cad9678- SHA-256 A cryptographic hash. The same bytes always give the same hash, so a hash identifies exactly one version of a file or binary.
9b9ec7d39dcd0d937c32b02292bb7978bd86fbfd8abb31a05764b294b2b63145