diff options
| author | Scott Gasch <[email protected]> | 2026-10-05 09:01:25 -0700 |
|---|---|---|
| committer | Scott Gasch <[email protected]> | 2026-10-05 09:01:25 -0700 |
| commit | 64b5d3307a7a95975f7f8c0248f3f1febedd8617 (patch) | |
| tree | 993fffd62a68bec962261caf033a8f05c6370ea9 /src/eval_tune/test_vs_head.sh | |
| parent | bbdf1bda8f410df6aa9be0a38e71b7db04982198 (diff) | |
Continue dynamic move-ordering/LMR session: SPRT-validated at 1770+ games
Gate match vs head (st4.0) shows LLR=+2.89 approaching the H1=+2.94
bound, candidate score 0.5324 (LOWER95=0.5092, ELO=+22.6+/-16.2),
candidate depth/ebf both improved (13.98 vs 13.61 avg depth, ebf 3.324
vs 3.464) with comparable nps -- consistent with real search-efficiency
gains rather than noise. match_play.py gets additional instrumentation
to report these stats; search.c/searchsup.c/generate.c/chess.h/eval.c
carry the underlying move-ordering/LMR changes from this session's
line of work.
Co-Authored-By: Claude Sonnet 5 <[email protected]>
Diffstat (limited to 'src/eval_tune/test_vs_head.sh')
| -rwxr-xr-x | src/eval_tune/test_vs_head.sh | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/eval_tune/test_vs_head.sh b/src/eval_tune/test_vs_head.sh index 592ecf1..6f37039 100755 --- a/src/eval_tune/test_vs_head.sh +++ b/src/eval_tune/test_vs_head.sh @@ -108,6 +108,7 @@ python3 ./match_play.py \ --pgn ../../pgn/twic_filtered.pgn \ --games ${GAMES} \ --workers 18 \ + --post \ ${TC_ARGS} \ ${SPRT_ARGS} \ --scratch /usr/local/tmp/typhoon_match_${LABEL} \ |