Run T-0076 passed
· Evidence: SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops.
Hypothesis
A network additionally trained on campaign data plays stronger than the production network trained solely on the legacy data set.
Wording edited for publication from the German entry; the register carries the author’s own text.
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. | +143.17 ± 26.61 | +172.05 ± 27.97 |
| 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. | +185.04 ± 30.70 | +230.62 ± 31.89 |
| Games | 492 | 456 |
| Wins / draws / losses | 272 / 140 / 80 | 266 / 133 / 57 |
| pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points. | 3 / 25 / 72 / 69 / 77 | 5 / 14 / 47 / 91 / 71 |
| 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 | +2.95 |
| 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, 5.0] |
| 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 predecessor |
| Duration | 3 min | 18 min |
Provenance
- Date
- 2026-09-14
- Started
- 2026-09-14 13:44:01 UTC
- Duration
- 22 min
- Author
- Agent X
- Epoch
- 4
- Gatekeeper
- passed
- Bench nodes
- 3,242