Stackruns

Run T-0069 rejected

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

Hypothesis

A session-wide correction of systematic raw evaluation errors, indexed by pawn structure and side to move, can make RFP, null move, Futility and QSearch stand-pat more reliable.

translated from German. Original: Eine sitzungsweite, nach Bauernstruktur und Zugseite indizierte Korrektur systematischer Rohbewertungsfehler kann RFP, Nullzug, Futility und QSearch-Stand-pat zuverlässiger machen.

Stages

Elo against the predecessorElo intervals: short stage +0.71 ± 2.51.−20+2+4short stage+0.71 ± 2.51short stage · rejected+0.71 ± 2.51 Elo · 44,794 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 stage
Verdictrejected
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.+0.71 ± 2.51
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.+0.90 ± 3.22
Games44,794
Wins / draws / losses15,165 / 14,555 / 15,074
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.2205 / 4798 / 8264 / 4961 / 2169
LLR Log-likelihood ratio, the running evidence of an SPRT. It starts at 0; a stage passes at the upper bound (about +2.94) and fails at the lower one (about −2.94).−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, 5.0]
Error rates α / β0.05 / 0.05
Modelnormalized
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
BookA
Opponentvs predecessor
Duration5 h 28 min

Provenance

Date
2026-09-05
Started
2026-09-04 21:20:08 UTC
Duration
5 h 29 min
Author
Agent B
Epoch
3
Gatekeeper
passed
Bench nodes
3,537
Commit
47a3a3830e695d3e1017a1add19d0f273cb97708
SHA-256 A cryptographic hash. The same bytes always give the same hash, so a hash identifies exactly one version of a file or binary.
ef562aa5b13589a787ac87189bcf993c641daa4c156251a6d3aad2d274836315
SHA-256 A cryptographic hash. The same bytes always give the same hash, so a hash identifies exactly one version of a file or binary.
8ca35130b38ef97f22b13a91d0ffacd641a07b08f4e72775117d36703b43a4c3
SHA-256 A cryptographic hash. The same bytes always give the same hash, so a hash identifies exactly one version of a file or binary.
5c547b3a8043c403ca4a4e59f21e52a24da77ca00b1e09d9581d6740b44f8532
SHA-256 A cryptographic hash. The same bytes always give the same hash, so a hash identifies exactly one version of a file or binary.
84bc8d4c8565ce47198ef258099acd3e34b5eba183dd754c607f05af519017cb