Stackruns

Run T-0131 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 with a width of 768, trained on 3.13 billion positions over 16 epochs with a paired AVX2 head, is expected to play stronger under time controls than the baseline network of width 512.

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

Stages

Elo against the predecessorElo intervals: short stage +14.96 ± 7.24; long stage +30.48 ± 10.08.0+10+20+30+40short stage+14.96 ± 7.24short stage · passed+14.96 ± 7.24 Elo · 3,206 gameslong stage+30.48 ± 10.08long stage · passed+30.48 ± 10.08 Elo · 1,394 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.+14.96 ± 7.24+30.48 ± 10.08
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.+24.90 ± 12.03+55.49 ± 18.24
Games3,2061,394
Wins / draws / losses904 / 1,536 / 766417 / 682 / 295
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.44 / 326 / 738 / 438 / 577 / 119 / 335 / 217 / 19
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+2.97
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
Duration25 min58 min

Provenance

Date
2026-09-27
Started
2026-09-27 17:38:42 UTC
Duration
1 h 24 min
Author
Agent X
Epoch
6
Gatekeeper
passed
Bench nodes
3,521