Stackruns

Run T-0080 rejected

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

Hypothesis

Das baumgleiche Geschwindigkeitsbündel K-03+K-02+K-21+K-22+K-24 (SEE Static exchange evaluation: an estimate of the material outcome of a capture sequence on one square, without searching.-Strahlmasken, Einfügesortierer, taktischer Erzeuger, Zugstruktur, toter Rang; zusammen +18,6 % E-Kern / +20,3 % P-Kern Knotenrate, bench 3406 und perft Performance test: counting all legal move sequences to a fixed depth, to check a move generator against known numbers. 5 bitgleich zur Basis) reist mit H-0208 (K-17, stetige LMR-Formel, G3b +12,3) als ein Kandidat: der Baum ist der von K-17, das Bündel ist dazu bitgleich; unter der Uhr ist das Paar mindestens so stark wie K-17 allein.

Stages

Elo against the predecessorElo intervals: short stage −118.10 ± 24.08.−150−100−500short stage−118.10 ± 24.08short stage · rejected−118.10 ± 24.08 Elo · 562 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.−118.10 ± 24.08
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.−152.30 ± 28.72
Games562
Wins / draws / losses106 / 166 / 290
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.69 / 90 / 90 / 20 / 12
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
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
Duration4 min

Provenance

Date
2026-09-14
Started
2026-09-14 14:45:00 UTC
Duration
4 min
Author
Agent A
Epoch
4
Gatekeeper
passed
Bench nodes
3,406
Metadata: commit and checksums (5)
Commit
28b1dc0b376cab05f7cd87dea9bdbaac6a819b7b
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.
b0e9d09c95056ac6a5b8b837340a2108f53dc91edeea754dbafa552c6f5e34c6
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.
39a85851063241a8c402b14b0fd43bb41a1b055bbda069f9ec8674f06d34bec6
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.
d483f6d2bfb8c0e96b442ff1371fd7c2f156ca1d0aa6c6e001088cb8c6c25ee9