Run T-0067 passed

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

Hypothesis

If a sufficiently deep non-PV Principal variation: the line of best moves the search currently expects. node without a TT Transposition table: a cache of already searched positions, keyed by a hash of the position. move is reduced by exactly one level, the worse-ordered search costs less and the saved budget can produce additional depth at more important nodes.

translated from German. Original: Wenn ein ausreichend tiefer Nicht-PV-Knoten ohne TT-Zug um genau eine Stufe reduziert wird, kostet die schlechter geordnete Suche weniger und das gesparte Budget kann an wichtigeren Knoten zusätzliche Tiefe erzeugen.

Stages

Elo against the predecessorElo intervals: short stage +7.60 ± 5.35; long stage +16.22 ± 8.31.0+10+20short stage+7.60 ± 5.35short stage · passed+7.60 ± 5.35 Elo · 9,790 gameslong stage+16.22 ± 8.31long stage · passed+16.22 ± 8.31 Elo · 3,730 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.+7.60 ± 5.35+16.22 ± 8.31
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.+9.78 ± 6.88+21.79 ± 11.15
Games9,7903,730
Wins / draws / losses3,364 / 3,276 / 3,1501,272 / 1,360 / 1,098
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.436 / 1052 / 1758 / 1160 / 489123 / 404 / 694 / 464 / 180
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+2.97
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, 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
Duration1 h 10 min2 h 16 min

Provenance

Date
2026-09-04
Started
2026-09-04 14:20:54 UTC
Duration
3 h 27 min
Author
Agent B
Epoch
3
Gatekeeper
passed
Bench nodes
3,537
Commit
a19df1d06f7f47e8a3af92d22af2c322d05d1c77
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.
d6369fa30908bc6ce8a0d70af97eded4cf63eecf4578093eea45ee8e1965e1e6
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.
8852c660e2f562afd4dfa4133ab4af59eccc7cb32d6139af673ba2d943a1add5
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