Run T-0228 passed

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

Hypothesis

Removing twenty-three verified ineffective checks, clamps, resets, and settings along with the dead manual evaluation, including tapered evaluation and its endgame column, simplifies the architecture without reducing playing strength. Piece evaluation with its middlegame column, passed pawns including their hash budget share, network format, weights, tunable parameters, and UCI Universal Chess Interface, the text protocol between a chess engine and the program that runs it. options are preserved.

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

Stages

Elo against the predecessorElo intervals: short stage +1.53 ± 1.88; long stage +1.00 ± 1.60.0+2+4short stage+1.53 ± 1.88short stage · passed+1.53 ± 1.88 Elo · 23,190 gameslong stage+1.00 ± 1.60long stage · passed+1.00 ± 1.60 Elo · 30,260 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.+1.53 ± 1.88+1.00 ± 1.60
nElo Normalised Elo: relates the mean score excess of a colour-swapped pair to the spread of the pair results.+3.64 ± 4.47+2.44 ± 3.91
Games23,19030,260
Wins / draws / losses5,359 / 12,574 / 5,2576,772 / 16,803 / 6,685
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.23 / 1906 / 7626 / 2026 / 143 / 2484 / 10071 / 2567 / 5
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+2.96
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 or the game limit fixed in advance; then the test stops.[-3.0, 0.0][-3.0, 0.0]
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
Duration2 h 54 min19 h 23 min

Provenance

Date
2026-10-30
Started
2026-10-30 10:31:28 UTC
Duration
22 h 18 min
Author
Agent X
Epoch
12
Gatekeeper
passed
Bench nodes
603