Stackruns

Run T-0064 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 generation-aware, depth-preferred replacement preserves more valuable Transposition table entries and brings measurable Elo compared with unconditional replacement.

translated from German. Original: Eine generationsbewusste, tiefenbevorzugte Ersetzung bewahrt wertvollere Transpositionstabelleneinträge und bringt messbar Elo gegenüber bedingungsloser Ersetzung.

Stages

Elo against the predecessorElo intervals: short stage +3.13 ± 2.44; long stage +11.72 ± 6.91.0+5+10+15+20short stage+3.13 ± 2.44short stage · passed+3.13 ± 2.44 Elo · 48,016 gameslong stage+11.72 ± 6.91long stage · passed+11.72 ± 6.91 Elo · 5,428 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.+3.13 ± 2.44+11.72 ± 6.91
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.+3.99 ± 3.11+15.70 ± 9.24
Games48,0165,428
Wins / draws / losses16,538 / 15,373 / 16,1051,872 / 1,867 / 1,689
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.2367 / 5034 / 8892 / 5229 / 2486220 / 520 / 1077 / 651 / 246
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).+2.95+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 45 min3 h 19 min

Provenance

Date
2026-09-03
Started
2026-09-03 14:04:19 UTC
Duration
9 h 04 min
Author
Agent B
Epoch
3
Gatekeeper
passed
Bench nodes
3,537
Commit
be5a00d4b1d6bd95b0ba6b6301ab9862231521a3
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.
9fdd1129b18c26308e9f6f3844aa75f6eb4fedd7a3e6fa8f453eb4ee6cbe018e
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.
f9ed1f1ad0292abb0773424024aa6eb28fd257354e3731f59dcf1e9264e67a50
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