Make the FH% regression model the default; remove data.c's retired tables

Flips FH_USE_REGRESSION_MODEL from an opt-in safety toggle to the only
behavior: fhmodel.c's quantized logistic regressions are now always
used, with no build-time choice left between them and the old
histogram tables. Removes g_uJointFHThousandths/g_uBetaFHThousandths
and their _NNUE counterparts from data.c (4085 lines), their extern
declarations from chess.h, and the now-dead
_JointTablePredictedFHThousandths/_BetaTablePredictedFHThousandths
lookup functions and their supporting bucket helpers
(HangCpBucket/GapCpBucket/MoveNumBucket/DepthBucket/ImproveBucket/
GapBetaBucket/_ShipDepthBucket/_ShipLateBucket) from searchsup.c, along
with the uRawDepthB/uRawImproveB plumbing that only existed to feed
them (search.c, split.c, SearchOneMove's parameter list).

Also drops the beta-side static-nullmove skip threshold's provisional-
96000 #else branch -- 99000 is now simply the default, confirmed (not
provisional) by docs/REGRESSION.md's trust-audit sweep (+291 Elo over
96000 at 200 games, LOWER95=0.79).

Verified: clean release build, clean DEBUG=1 TEST=1 self-test run (no
asserts), and a fresh head_reference/ checkpoint
(head-reference-20261025 -> 874ef04's regression-model binary) with
sd10/sn5000000 solve counts on the three curated suites essentially
matching the previous table-based checkpoint (70/191 vs 71/191 sd10,
93/191 vs 96/191 sn5M).

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

1 files changed, 13 insertions, 77 deletions

diff --git a/src/chess.h b/src/chess.h
index 0d5a4a1..85b4bd7 100755
--- a/src/chess.h
+++ b/src/chess.h
@@ -3975,40 +3975,13 @@ extern BITBOARD g_KingAttacksBB[128];
 // search.c -- phase 2 (LMR replacement) is a separate, later step.
 //
 // 2026-10-21: late axis widened 16 -> 17. Shipped late bucket 0 is now
-// dedicated SOLELY to the whole-node sample (raw late == 0, "will
-// something at this node fail high" -- no specific move), not shared
-// with the real first-leftover-move curve the way the old 16-bucket
-// shape coincidentally did. See searchsup.c's _ShipLateBucket and
-// dual_table_run_nnue/README.md's "whole-node alpha sample" section.
-// g_uJointFHThousandths (HCE) carries a PLACEHOLDER in that bucket,
-// duplicated from g_uJointFHThousandths_NNUE's real measurement, since
-// this table's own collection build predates the whole-node
-// instrumentation -- see data.c's header comment on this array, and
-// dual_table_run/README.md, for how/when that gets replaced with a
-// real HCE-side measurement.
-extern USHORT g_uJointFHThousandths[12][11][11][17][11];
-
-// 2026-10-21: NNUE-eval counterpart of g_uJointFHThousandths above --
-// same shape, collected against the NNUE evaluator instead of HCE
-// (see ../dual_table_run_nnue/). Both tables are compiled in; which
-// one a lookup reads is chosen at runtime by
-// _JointTablePredictedFHThousandths (searchsup.c) based on
-// (g_fUseNnueEval && g_fNnueWeightsLoaded) -- NOT a build-time
-// #ifdef, since NNUE is itself already a runtime switch in this
-// binary (see eval.c, command.c's "nnue on"/"nnue off").
-extern USHORT g_uJointFHThousandths_NNUE[12][11][11][17][11];
-
-// 2026-10-10: beta-side (static-null-move) 4D FH% table -- see data.c's
-// header. [depth][gapBeta][ownImprove][enemyImprove]. Cell stores the
-// GAP TO 100% FH rate (thousandths of a percentage point), not FH%
-// itself -- see _BetaTablePredictedFHThousandths's comment for why.
-extern USHORT g_uBetaFHThousandths[12][21][11][11];
-
-// 2026-10-21: NNUE-eval counterpart of g_uBetaFHThousandths above --
-// same shape/encoding, collected against the NNUE evaluator. Runtime-
-// selected the same way as g_uJointFHThousandths_NNUE above (see
-// _BetaTablePredictedFHThousandths, searchsup.c).
-extern USHORT g_uBetaFHThousandths_NNUE[12][21][11][11];
+// 2026-10-25: the data.c FH%-prediction histogram tables
+// (g_uJointFHThousandths/g_uBetaFHThousandths and their _NNUE
+// counterparts) are retired -- replaced by the quantized logistic
+// regressions in fhmodel.c/fhmodel_weights.h (see docs/REGRESSION.md
+// for the full design/validation trail). This is now the only FH%-
+// prediction mechanism; there's no build-time choice between it and
+// a table anymore.
 
 // 2026-09-15: king-ring bitboard split for _EvalKing's linear-SCORE
 // rewrite -- front/back mirror EmptyAttackedSquare's old color-dependent
@@ -4614,50 +4587,18 @@ EstimateHangingMaterialCp(IN SEARCHER_THREAD_CONTEXT *ctx,
                           IN BITBOARD bbRookAttacksSnapshot[2]);
 
 ULONG
-HangCpBucket(SCORE iHangCp);
-
-ULONG
-GapCpBucket(SCORE iGapCp);
-
-ULONG
-MoveNumBucket(ULONG uMoveNum);
-
-ULONG
-DepthBucket(ULONG uCandDepth);
-
-ULONG
-ImproveBucket(SCORE iImprovement);
-
-ULONG
-GapBetaBucket(SCORE iGapBeta);
-
-USHORT
-_JointTablePredictedFHThousandths(IN ULONG uRawDepthBucket,
-                                   IN ULONG uRawDumbBucket,
-                                   IN ULONG uRawGapBucket,
-                                   IN ULONG uRawLateBucket,
-                                   IN ULONG uRawImproveBucket);
-
-ULONG
-_BetaTablePredictedFHThousandths(IN ULONG uRawDepthBucket,
-                                  IN ULONG uGapBetaBucket,
-                                  IN ULONG uOwnImproveBucket,
-                                  IN ULONG uEnemyImproveBucket);
-
-ULONG
 _RefineNodeTypeGuess(IN SEARCHER_THREAD_CONTEXT *ctx,
                      IN SCORE iEval,
                      IN SCORE iAlpha,
                      IN SCORE iBeta,
                      IN ULONG uDepth,
                      IN SCORE iImprovement,
-                     IN SCORE iEnemyImprovement,
-                     IN ULONG uRawImproveB);
+                     IN SCORE iEnemyImprovement);
 
 // fhmodel.c -- production inference for the FH% logistic-regression
-// models (FH_USE_REGRESSION_MODEL), see docs/REGRESSION.md. No
-// separate header -- matches fhcollect.c's own convention of
-// declaring everything here rather than a per-module header.
+// models, see docs/REGRESSION.md. No separate header -- matches
+// fhcollect.c's own convention of declaring everything here rather
+// than a per-module header.
 //
 // Fully quantized fixed-point integer arithmetic -- no floats, no
 // runtime log()/exp() calls.
@@ -4825,16 +4766,11 @@ SearchOneMove(IN SEARCHER_THREAD_CONTEXT *ctx,
                                         // matters once HelpSearch() also calls
                                         // this: its first move off the shared
                                         // pool is never the node's first move)
-              IN ULONG uRawDepthB,      // node-level hoists, loop-invariant --
-              IN ULONG uRawImproveB,    // caller computes once, not per-move
               IN BITBOARD bbMinorAttacksSnapshot[2],
               IN BITBOARD bbRookAttacksSnapshot[2],
-#ifdef FH_USE_REGRESSION_MODEL
               IN FHM_NODE_BASE sFhAlphaNodeBase,  // hoisted node-level
-                                        // precompute, same loop-invariant
-                                        // convention as uRawDepthB/
-                                        // uRawImproveB above
-#endif
+                                        // precompute, loop-invariant --
+                                        // caller computes once, not per-move
 #ifdef MOVE_ORDERING_EVIDENCE_COLLECTION
               IN FLAG fThisMoveIsCountermoveMatch,
               IN ULONG uCMEvidenceBucket,