feat(alpha): Phase E.3 follow-up — C51 distributional Q + Thompson + L1-L10 depth + falsifications

C51 distributional Q-network with GPU Thompson selection borrowed
minimally from production (alpha_c51.cu: forward, project, grad,
expected_q, thompson_select kernels; ~260 lines). Uses Huber
negative-tail compression in projection per production
block_bellman_project_f. Action selection 100% GPU via mapped-pinned
i32 output + __threadfence_system + host volatile read (matches
gpu_training_guard MappedBuffer pattern).

Backtest result (2D sweep, 500 episodes per cell, 30 cells):
  cost=0    C51 +10.41 vs linear-Q -15.72  (+26pt, BEATS Phase 1d.4
                                            no-RL baseline +4.4 by 6pt)
  cost=0.125 C51 -13.81 vs -29.17  (+15pt closes half-tick gap)
Win rate at cost=0 best τ: linear-Q 0.008 → C51 0.552.

Calibration hypothesis vindicated; documented in
memory/pearl_c51_thompson_closed_phase_e3_gap.md.

Also in this commit (Phase E.3 follow-up cleanup):
- --pruned-actions falsified (2.4× worse Sharpe). Documented in
  memory/pearl_action_pruning_falsified.md.
- --real-spread falsified for ES futures (76% of bars at 1-tick floor).
- SnapshotRow bid_l/ask_l extended from [f32; 3] to [f32; 10].
  L4-L10 synthesized in this commit; real MBP-10 peek lands in E.4.A T5.
- docs/isv-slots.md updated per kernel-audit-doc hook requirement.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

crates/ml/build.rs

@@ -1615,6 +1615,12 @@ fn main() {
         // at 0.4 per pearl_wiener_alpha_floor_for_nonstationary) on the
         // observed-rate EMA at slot 545.
         "stacker_threshold_controller.cu",
+        // Phase E.3 follow-up (2026-05-15): vanilla C51 distributional
+        // Q-network kernels. Forward (logits → softmax over atoms),
+        // categorical Bellman projection, cross-entropy gradient. Fixed
+        // atom support, single network, no per-branch / Adam machinery —
+        // testing the calibration hypothesis from `pearl_action_pruning_falsified`.
+        "alpha_c51.cu",
     ];
 
     // ALL kernels get common header (BF16 types + wrappers)