Rewrite _EvalKing as a linear ring-scan and promote its terms to DNA-tunable constants; retune via mate-mining regression, ElasticNet/Ridge, and logistic-vs-material refits.

Splits _EvalKing's own king-location table from CountKingSafetyDefects' search-gate copy so future eval retunes can't silently perturb extension/reduction gate frequency. Bumps KING_BACK_FLIGHT_BONUS (+1 -> +3) and reorders/nudges the ring-scan sub-terms (minor/pawn/xray/undefended) to match relative rankings that replicated across three independent calibration methods, while leaving KING_QUEEN_PROXIMITY_DANGER and KING_MISSING_ONE_CASTLE_OPTION untouched pending further discussion.

Self-play (640 games) is roughly even (score 0.509, llr=+0.17, far from either SPRT bound) but consistently faster (nps candidate=1362140 vs head=1333682) at equal average depth -- landing as a wash/speed-neutral checkpoint, not a confirmed tactical improvement, for further tuning to build on.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

1 files changed, 40 insertions, 6 deletions

diff --git a/src/eval_tune/test_vs_head.sh b/src/eval_tune/test_vs_head.sh
index 871b801..29c050f 100755
--- a/src/eval_tune/test_vs_head.sh
+++ b/src/eval_tune/test_vs_head.sh
@@ -1,11 +1,45 @@
 #!/usr/bin/env bash
+#
+# Gated self-play match against a baseline binary. Historically this
+# always compared the live working-tree build against head_reference/
+# -- generalized (2026-09-14) to take both binary paths as args so two
+# arbitrary builds (e.g. a file-storm-only worktree build vs. the
+# current working tree, to isolate one change at a time when several
+# have landed together -- see king_safety_data/HANDOFF.md's session
+# notes on not measuring two eval changes in one match) can be compared
+# without hand-rolling a match_play.py invocation each time.
+#
+# Usage: test_vs_head.sh [head_binary] [candidate_binary] [label]
+#
+#   head_binary       Baseline engine. Defaults to head_reference/typhoon
+#                      (the usual "is this better than last checkpoint"
+#                      question).
+#   candidate_binary   Candidate engine. Defaults to a fresh copy of the
+#                      live working-tree build (../typhoon) into
+#                      /tmp/typhoon/typhoon_match_play_candidate -- pass
+#                      an explicit path (already built) to skip that
+#                      copy/freeze step entirely, e.g. when comparing
+#                      two prebuilt worktree binaries.
+#   label              Distinguishes scratch dir/log/pgn-out so multiple
+#                      matches can run concurrently without colliding.
+#                      Defaults to "match".
+#
+# Examples:
+#   test_vs_head.sh                                                    # old default behavior
+#   test_vs_head.sh /tmp/typhoon/filestorm_only /tmp/typhoon/candidate queenprox_backflight
 
 set -e
 
-CANDIDATE=/tmp/typhoon/typhoon_match_play_candidate
-HEAD=../../head_reference/typhoon
+HEAD="${1:-../../head_reference/typhoon}"
+LABEL="${3:-match}"
+
+if [ -n "$2" ]; then
+    CANDIDATE="$2"
+else
+    CANDIDATE=/tmp/typhoon/typhoon_match_play_candidate
+    cp -f ../typhoon ${CANDIDATE}
+fi
 
-cp -f ../typhoon ${CANDIDATE}
 python3 ./match_play.py \
         ${HEAD} \
         ${CANDIDATE} \
@@ -14,6 +48,6 @@ python3 ./match_play.py \
         --workers 12 \
         --st 1 \
         --sprt --elo0 0 --elo1 5 \
-        --scratch /usr/local/tmp/typhoon_match_overnight \
-        --log overnight_match.log \
-        --pgn-out ../self_play_games.pgn
+        --scratch /usr/local/tmp/typhoon_match_${LABEL} \
+        --log ${LABEL}.log \
+        --pgn-out ../${LABEL}_games.pgn