Run T-0075 passed

· Evidence: SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops.

Hypothesis

The network evaluation updates the feature accumulators for both perspectives incrementally with every piece change on the board, instead of re-accumulating them from all pieces during each evaluation call.

Wording edited for publication from the German entry; the register carries the author’s own text.

Stages

Elo against the predecessorElo intervals: short stage +3.01 ± 2.38; long stage +4.50 ± 3.53.0+2+4+6+8short stage+3.01 ± 2.38short stage · passed+3.01 ± 2.38 Elo · 41,618 gameslong stage+4.50 ± 3.53long stage · passed+4.50 ± 3.53 Elo · 17,746 games
Point estimate with the reported 95-percent half-width, per stage. The dashed line is zero. Estimates from a stopped sequential test are biased by the stopping rule; the interval is nominal.
Field short stagelong stage
Verdictpassedpassed
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.+3.01 ± 2.38+4.50 ± 3.53
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.+4.21 ± 3.34+6.52 ± 5.11
Games41,61817,746
Wins / draws / losses13,374 / 15,230 / 13,0145,548 / 6,880 / 5,318
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.1482 / 4406 / 8752 / 4608 / 1561520 / 1974 / 3724 / 2066 / 589
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.+2.95+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 / β0.05 / 0.050.05 / 0.05
Modelnormalizednormalized
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+0.0840+0.4
BookAB
Opponentvs predecessorvs predecessor
Duration5 h 05 min11 h 03 min

Provenance

Date
2026-09-13
Started
2026-09-13 13:00:45 UTC
Duration
16 h 09 min
Author
Agent D
Epoch
4
Gatekeeper
passed
Bench nodes
3,406