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, 24 insertions, 51 deletions

diff --git a/src/search.c b/src/search.c
index dc0fdc0..395a301 100644
--- a/src/search.c
+++ b/src/search.c
@@ -116,14 +116,12 @@ extern FLAG g_fCanSplit[MAX_PLY_PER_SEARCH];
 // purely to minimize the original diff against HEAD's LMR. The move
 // loop below now just calls GetLMRReduction once and uses its result.
 //
-// EstimateHangingMaterialCp/HangCpBucket/GapCpBucket/MoveNumBucket/
-// DepthBucket moved there too but are no longer file-static -- the
-// measurement/collection block further below (gated on
-// fMoveIsPruneReduceEligible alone, independent of the LMR decision -- this
-// is what's still generating the next round of g_uJointFHThousandths
-// data) still needs them, so they're declared in chess.h and called
-// from here unchanged in behavior, just by their new (un-underscored)
-// public names.
+// EstimateHangingMaterialCp moved there too but is no longer
+// file-static. 2026-10-25: the bucket helpers mentioned above
+// (HangCpBucket/GapCpBucket/MoveNumBucket/DepthBucket) and the
+// data.c-table lookups they fed are gone entirely -- see
+// docs/REGRESSION.md -- replaced by fhmodel.c's quantized logistic
+// regressions.
 
 
 #ifdef JOINT_EXTRA_VERIFY
@@ -449,7 +447,6 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
     BITBOARD bbMinorAttacksSnapshot[2];
     BITBOARD bbRookAttacksSnapshot[2];
     FLAG fMoveIsPruneReduceEligible = FALSE;
-    ULONG uRawDepthB;
 #ifdef MP
     FLAG fNodeSplitEligible;
 #endif
@@ -637,7 +634,6 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
     {
         iImprovement = (iEval - ctx->sPlyInfo[ctx->uPly - 2].iEval);
     }
-    ULONG uRawImproveB = ImproveBucket(iImprovement);
     SCORE iEnemyImprovement = 0;
     if (ctx->uPly > 2)
     {
@@ -670,8 +666,7 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
                                               iBeta,
                                               uDepth,
                                               iImprovement,
-                                              iEnemyImprovement,
-                                              uRawImproveB);
+                                              iEnemyImprovement);
 
     // One call, regardless of which (or neither) of the iEval>iBeta /
     // iEval<=iAlpha branches below ends up applying -- FhCollectNodeEntry
@@ -694,7 +689,6 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
                        ((pos->uNonPawnMaterial[WHITE] - VALUE_KING) +
                         (pos->uNonPawnMaterial[BLACK] - VALUE_KING)));
 
-#ifdef FH_USE_REGRESSION_MODEL
     // HOISTED node-level precompute:
     FHM_NODE_BASE sFhAlphaNodeBase = (iEval <= iAlpha) ?
         FhModelAlphaNodeBaseQ16(iEval,
@@ -706,7 +700,6 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
                                         (pos->uNonPawnMaterial[BLACK] - VALUE_KING)),
                                 eNodeTypeGuessParent) :
         (FHM_NODE_BASE)FHM_MATE_GATED;
-#endif
 
     // If the Eval call above was a full eval (i.e. not lazy or super
     // lazy), there are usable attack bitboards.  We'll consult them
@@ -819,44 +812,32 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
             INC(ctx->sCounters.tree.u64QuickNullMoves);
 #ifndef FH_REGRESSION_COLLECTION
             // A collection build must NOT take this shortcut -- it
-            // would skip the real move loop based on the CURRENTLY
-            // LOADED (soon-to-be-replaced) data.c table, censoring
-            // exactly the population FhCollectNodeEntry/NodeExit
-            // (above/below) are trying to measure. Same reasoning as
+            // would skip the real move loop before FhCollectNodeEntry/
+            // NodeExit (above/below) get a chance to log the
+            // population they're trying to measure. Same reasoning as
             // the LMP disable in searchsup.c. uNodeLocalFH was already
             // computed above by _RefineNodeTypeGuess via this exact
-            // same _BetaTablePredictedFHThousandths lookup (same
-            // depth/gap/improve bucket inputs, gated by the same
-            // iEval > iBeta branch) -- reuse it instead of consulting
-            // the table again.
-#ifdef FH_USE_REGRESSION_MODEL
+            // same fhmodel.c beta-regression call (same iEval > iBeta
+            // branch) -- reuse it instead of consulting the model
+            // again.
+            //
+            // 99000 is the confirmed default (docs/REGRESSION.md's
+            // trust-audit section): a direct 200-game sweep against a
+            // looser 96000 threshold settled this decisively
+            // (LOWER95=0.79, +291 Elo) -- 96000 fires this shortcut
+            // ~2x as often as the old table did on real search trees
+            // (calibration is honest at both; this was a firing-
+            // frequency gap, not an accuracy one) and cost real
+            // strength. A 99500 follow-up sweep against 99000 came
+            // back inconclusive, so there's no case yet for moving
+            // off 99000.
             static ULONG uBetaSkipThreshold = 0;
             if (0 == uBetaSkipThreshold)
             {
                 CHAR *pszThresh = getenv("FH_BETA_SKIP_THRESHOLD");
-                // 2026-10-24: provisional default, NOT yet confirmed by
-                // match-play -- see docs/REGRESSION.md's "Static-nullmove
-                // shortcut firing-rate" section. 96000 (matching the old
-                // table's nominal threshold) empirically fires the
-                // shortcut ~2x as often as the table did on real search
-                // trees (calibration is honest at both; this is a
-                // firing-frequency gap, not an accuracy one) and costs a
-                // large chunk of ECM solve rate. 99000 recovers ECM
-                // parity. Per DEEPER_PRUNING.md's Category A/B framework,
-                // ECM is the WRONG instrument to pick this value with --
-                // this is a Category B (deliberately-unsound,
-                // cluster-tested) pruning decision, and only
-                // match_play.py's LOWER95 gate can say whether the more
-                // aggressive 96000 is actually a net real-game win
-                // despite losing ECM solves. That sweep has not been run
-                // yet. 99000 is chosen here only as the closest-to-known-
-                // safe (table-matched) stand-in until it is.
                 uBetaSkipThreshold = (pszThresh && atol(pszThresh) > 0) ?
                     (ULONG)atol(pszThresh) : 99000;
             }
-#else
-            #define uBetaSkipThreshold 96000
-#endif
             ULONG uBetaPredictedFHThousandths = uNodeLocalFH;
             if ((uBetaPredictedFHThousandths != 0xFFFF) &&
                 (uBetaPredictedFHThousandths > uBetaSkipThreshold))
@@ -868,9 +849,6 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
                 iBestScore = iBeta;
                 goto end;
             }
-#ifndef FH_USE_REGRESSION_MODEL
-            #undef uBetaSkipThreshold
-#endif
 #endif
         }
         else if (iEval <= iAlpha)
@@ -1041,7 +1019,6 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
                     }
                 }
                 uStage++;
-                uRawDepthB = DepthBucket(uDepth / ONE_PLY);
 #ifdef MP
                 // See fNodeSplitEligible's declaration comment -- same
                 // four conditions the move loop used to re-check on
@@ -1231,13 +1208,9 @@ Search(IN SEARCHER_THREAD_CONTEXT *ctx,
                                           fIsLeftoverMove,
                                           fThreat,
                                           (iBestScore == -INFINITY_SCORE),
-                                          uRawDepthB,
-                                          uRawImproveB,
                                           bbMinorAttacksSnapshot,
                                           bbRookAttacksSnapshot,
-#ifdef FH_USE_REGRESSION_MODEL
                                           sFhAlphaNodeBase,
-#endif
 #ifdef MOVE_ORDERING_EVIDENCE_COLLECTION
                                           fThisMoveIsCountermoveMatch,
                                           uCMEvidenceBucket,