Run T-0109 rejected
· Evidence: SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops.
Hypothesis
Portable build flags -O3 -march=x86-64-v3 -flto were applied to the NNUE Efficiently updatable neural network: a small network that evaluates positions and is updated incrementally move by move. component. Utilizing AVX2 is expected to triple the speed of the int16 accumulator loop in the testbed and training epoch, rather than in the engine code itself.
Wording edited for publication from the German entry; the register carries the author’s own text.
Stages
| Field | short stage |
|---|---|
| Verdict | rejected |
| 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. | −1.18 ± 5.34 |
| 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. | −2.13 ± 9.63 |
| Games | 5,004 |
| Wins / draws / losses | 1,318 / 2,351 / 1,335 |
| pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points. | 61 / 529 / 1345 / 500 / 67 |
| LLR Log-likelihood ratio, the running evidence of an SPRT. It starts at 0; a stage passes at the upper bound and fails at the lower one. | −2.96 |
| Bounds | −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, 10.0] |
| Error rates α / β | 0.05 / 0.05 |
| Model | 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 |
| Book | A |
| Opponent | vs predecessor |
| Duration | 38 min |
Provenance
- Date
- 2026-09-22
- Started
- 2026-09-22 10:34:19 UTC
- Duration
- 38 min
- Author
- Agent X
- Epoch
- 5
- Gatekeeper
- passed
- Bench nodes
- 3,627