Run T-0144 passed

2026-09-30 · Evidence: SPRT Sequential probability ratio test. Games are played until the accumulated evidence reaches one of two bounds; then the test stops.

Hypothesis

Using the multi-layer neural network SKML768V7J (16/32 structure, four king buckets with a symmetric board and mirror bit, horizontal king mirroring, trained on v7j data for 16 epochs) increases the engine's playing strength against main with network KM768V6 under timed conditions.

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

Stages

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	long stage
Verdict	passed	passed
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.	+26.67 ± 9.79	+35.15 ± 10.95
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.	+45.73 ± 16.72	+63.56 ± 19.66
Games	1,658	1,200
Wins / draws / losses	520 / 745 / 393	362 / 597 / 241
pentanomial Games are played in pairs with swapped colours; the five counts are the pairs scoring 0, ½, 1, 1½ and 2 points.	`9 / 166 / 377 / 243 / 34`	`3 / 110 / 265 / 207 / 15`
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.	+2.94	+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 / β	0.05 / 0.05	0.05 / 0.05
Model	normalized	normalized
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	40+0.4
Book	A	B
Opponent	vs predecessor	vs predecessor
Duration	13 min	51 min

Provenance

Date: 2026-09-30
Started: 2026-09-30 14:32:21 UTC
Duration: 1 h 04 min
Author: Agent X
Epoch: 6
Gatekeeper: passed
Bench nodes: 4,293

Playing strength carried forward

3527 ± 54

An estimate, not a measured Elo. This build has not played a single listed opponent — anchored is 0.1.118 alone, and this figure is carried on from there. The chain is measured against our own predecessors, at a different time control and a different book, and an SPRT that stops at its upper bound reports a gain that is biased upward. The figure is therefore more likely too high than too low. Only the anchoring itself is a measurement.

How it is worked out

The anchoring measures Coherent 0.1.118, the build of run T-0135: 3455 ± 52, transferred over foreign engines with a published rating at 120+1.
The register carries the passed long stages after T-0135: +6.82 (T-0138) +10.32 (T-0141) +7.12 (T-0142) +12.96 (T-0143) +35.15 (T-0144), together +72.37, each measured against its own predecessor at 40+0.4.
3455, plus +72.37, gives 3527. The half-widths are combined in quadrature — the root of the sum of the squares: ± 52 and ± 15.12 make ± 54.