Stackruns

Run T-0094 rejected

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

Hypothesis

With identical best move stability, a high root node fraction of the best move from depth five onwards reduces soft search time by at most 12.5% after a completed iteration. Conversely, a low node fraction extends soft search time by at most 25% within the hard limit.

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

Stages

Elo against the predecessorElo intervals: short stage +5.05 ± 3.91; long stage +0.98 ± 4.03.0+5+10short stage+5.05 ± 3.91short stage · passed+5.05 ± 3.91 Elo · 12,314 gameslong stage+0.98 ± 4.03long stage · rejected+0.98 ± 4.03 Elo · 10,594 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
Verdictpassedrejected
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.+5.05 ± 3.91+0.98 ± 4.03
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.+7.92 ± 6.14+1.61 ± 6.62
Games12,31410,594
Wins / draws / losses3,631 / 5,231 / 3,4522,935 / 4,754 / 2,905
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.262 / 1338 / 2809 / 1455 / 293198 / 1176 / 2503 / 1238 / 182
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.+2.98−2.97
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, 10.0][0.0, 10.0]
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
Duration1 h 31 min6 h 42 min

Provenance

Date
2026-09-19
Started
2026-09-19 20:00:06 UTC
Duration
8 h 14 min
Author
Agent X
Epoch
5
Gatekeeper
passed
Bench nodes
2,654