84793ea46ee2f69ec99a07663ba8e27a0645d3e3
221 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
jgrusewski
|
9ad76c4dfe |
spec(crt): v3 architecture reset — collapse Phase A+B into CRT.1 unified controller
Empirical trigger: Phase A as designed in v2 failed Gate 1 catastrophically on both smoke vjmwc (commit |
||
|
jgrusewski
|
8ba8755b48 |
spec(crt): v2 amendments from critical review — 12 issues + greenfields
Self-critical review of v1 (commit
|
||
|
jgrusewski
|
0f34843253 |
spec: continuous-reasoning trader architecture (4-layer rebuild)
Integrated spec for the continuous-reasoning trader rework. Replaces
the rule-based discrete policy with a 4-layer signal-driven architecture:
Layer A: continuous control loop (every event, not every stride)
Layer B: signal-driven position management (multi-horizon fusion,
continuous sizing, conviction-degradation exit, open_trade_state
expanded 24→128 bytes)
Layer C: adaptive risk envelope (ISV-derived max_lots, threshold,
target_annual_vol)
Layer D: online weight adaptation (LoRA + EWC++, offline-batch
per-session, shadow-eval gated)
Phased gates: A unlocks B; B is where alpha lives; C amplifies B;
D amplifies whatever's working. Each gate has explicit pass criteria.
Conviction definition: ISV-weighted multi-horizon agreement.
weight_h = max(pnl_ema_win - pnl_ema_loss, 0) / (var + cost^2).
Net edge x SNR per horizon, scale-normalised, cold-start uniform fallback.
Pearl conformance: 13 existing pearls referenced and respected
(ISV-driven anchors, first-observation bootstrap, Wiener-alpha floor,
blend-with-floor, z-score normalisation, one-unbounded multiplicand,
trade-level vol bootstrap, deadline cadence, single-source-of-truth,
atomic refactor, adaptive-not-tuned).
Hardcoded boundary preserved for hardware/exchange realities (latency,
cost, annualisation, instrument bounds). Everything else adaptive.
Status: design — awaiting user review before implementation plan.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
jgrusewski
|
bf619a2e7b |
feat(ml-backtesting): max-hold + exit_px defensive + spec criteria revision
Three follow-ups from cluster smoke gp74n (trade_vol pearl validation): 1. Max-hold force-close: max_hold_ns added as per-backtest config (default 0 = disabled). Fires force-flat (3, 0) when current_ts - entry_ts >= max_hold_ns, BEFORE SL/trail check. Tested via max_hold_forces_close. Sweep YAML sets 60s cap to bound the long tail observed in gp74n (263985s pathological hold). 2. exit_px defensive sanity check: 500/1024 gp74n trades reported exit_px = ±i32::MAX/100 (float→int saturation sentinel from likely NaN segment_realized). Defensive fix in pnl_track_step: if exit_px is non-finite or diverges from entry_px by >10%, fall back to entry_px with zero realised_pnl. Root cause to be traced separately. 3. Spec §9.2 criteria revision: mean_hold<30s replaced with p95<600s + max<=max_hold_ns. The 30s threshold reflected the pre-pearl sub-cost churning bug, not a real feature criterion. p95 catches long-tail pathology while letting alpha-driven exit timing breathe. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
9b29f9fd0a |
feat(ml-backtesting): trade-vol floor replaces 2×cost literal in stop_check_isv
Replaces the Task 12 `2.0f * cost` floor (hardcoded multiplier) with trade_vol = sqrt(realised_return_var) bootstrapped from cost². Per pearl_trade_level_vol_for_stop_distance.md: microstructure ATR is the wrong time scale for trade-level stop decisions; per-horizon realised_return_var is the right one, with cost² as a structural cold- start sentinel. cost now appears exactly once — inside the sqrt as a bootstrap sentinel, never as a distance multiplier. The 2.0f literal is eliminated; controller is fully ISV-driven. var_avg accumulates realised_return_var in the same single-pass horizon loop as ema_loss/ema_win. Cold-start (var_avg=0): trade_vol = cost. Post-bootstrap: sqrt(var_avg) dominates. Test retargeted: cost_floor_prevents_sub_cost_stops → trade_vol_floor_prevents_sub_cost_stops, with boundaries straddling trade_vol=cost=0.125 instead of the prior 2*cost=0.25 (no-fire Δ=0.08, fire Δ=0.20). Spec §5, §10, §11, §12 amended. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
da6e887174 |
feat(ml-backtesting): cost-floor in stop_check_isv prevents sub-cost churning
Cluster smoke w7b4p showed 44864 closed trades in 1M events at 200ms latency — physically impossible without sub-cost churning. Root cause: sl_distance = max(pnl_ema_loss, atr) ≈ 0.05 at cold-start, but round-trip cost = 2 × 0.125 = 0.25. Every stop-out guaranteed loss > 5× distance; EMA converges sub-cost. Amendment: triple-max sl_distance = max(pnl_ema_loss, atr, 2*cost); trail_distance = max(pnl_ema_win, atr, 2*cost). cost is an ISV-discipline strategy anchor (already per-backtest from P4 — no new state slot, no tuned constants). Added cost_per_lot_per_side_per_b param to both decision kernel signatures and threaded cost_per_lot_per_side_d through both launch sites in step_decision_with_latency. Test: cost_floor_prevents_sub_cost_stops validates unrealized in (ATR, 0.25) does NOT fire SL; unrealized > 0.25 DOES fire. Spec amended (§10, §12). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
4101796ad9 |
refactor(ml-backtesting): delete StopRules + use_cold_start_stopgap atomically
- StopRules struct + sl_tp_rules field + all literals deleted; the ISV stop controller (Tasks 2-9) replaces this dead data path. - use_cold_start_stopgap propagation deleted across harness, batched_config, fxt-backtest, sweep_smoke.yaml, and 5 test files. - Q1 stopgap branch in harness.rs deleted; replaced with the original simple strategy-upload loop. - decision_floor_coldstart test retargeted: cold_start_persistent_ bullish_with_default_stops_never_closes -> ..._now_closes, asserts trades > 0 AND |pos| <= max_lots (99 trades, pos=1 on local GPU). - CBSW spec + plan prefixed with SUPERSEDED headers. Per feedback_single_source_of_truth_no_duplicates + feedback_no_partial_refactor: contract change migrates every consumer in one commit. No legacy wrappers; no version suffixes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
1ecce0d826 |
spec(ml-backtesting): critical-review pass on ISV stop controller — 9 fixes
Issues caught in self-review and fixed:
1. Encoding ambiguity: stop-fire writing (2, 0) would have silently
collapsed weak-alpha no-op semantics with force-flat. Introduced
distinct side=3 = force-flat; preserved side=2 = no-op for entry
path. Updated §3 + §5 + §7 truth table.
2. trail_hwm reset on close was implied in §4 but missing from §8's
touched-files list. Added pnl_track.cu modification (§7.1) +
added to §8 Added list.
3. __device__ helper enforcement: §3 now mandates stop_check_isv()
as a shared __device__ function called from both decision kernels,
not duplicated code.
4. Kernel arg additions enumerated explicitly in new §4.1 table —
every kernel-launch site gets named, no "thread through every kernel"
hand-wave.
5. seed_inflight_limits_batched (resting_orders.cu:439–475) named
explicitly in §1 + §7 — the actual kernel that needs the position-
target-semantics fix.
6. In-flight order summation: naive delta = target_signed - pos was
strictly worse than the original additive bug under non-zero
latency (would produce pos = pre + K·delta after fills). Fixed
§7 algorithm to compute effective_position by scanning all
active∈{1, 2} slots and summing their signed sizes. Added
position_target_not_additive_with_latency test.
7. ATR α=0.4 honest justification in §10: not strictly derived from
pearl_wiener_alpha_floor_for_nonstationary (which is about co-
adapting control loops, not passive observation); chosen as a
pragmatic project-wide constant matching isv_kelly_update_on_close.
8. CUDA Graph host-branch-free affirmation added to §3 — explicit
compatibility with P5 graph capture.
9. Cold-start symmetry caveat (§5): at n_trades_seen=0 both EMAs are
0 so sl_distance == trail_distance == atr — asymmetry only
emerges post-bootstrap. Acknowledged honestly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
jgrusewski
|
11d1279990 |
spec(ml-backtesting): ISV-driven stop controller — supersedes falsified CBSW
Replaces StopRules::default()-all-zeros (the actual cause of the cluster smoke's n_trades=0, falsifying the CBSW dilution diagnosis) with an ISV-driven SL + trail-stop controller folded into the existing decision kernel(s). Per-backtest ATR EMA on mid-price + per-horizon pnl_ema_* drive distances under max(real, floor) per pearl_blend_formulas_must_have_permanent_floor. No new kernel; single source of truth in step_decision*. Folds in the position-target semantics fix (200-event local repro showed position_lots=199 from additive-vs-target order semantics) — same commit. Removes: StopRules, sl_tp_rules, Q1 stopgap field/branch, use_cold_start_stopgap propagation. Marks CBSW spec + plan SUPERSEDED. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
566e8bcb0a |
spec(ml-backtesting): CBSW review pass — 11 fixes (perf + correctness)
Critical review surfaced 11 actionable issues in the v1 spec; 10 fixed inline (#11 — legacy-comparison test — dropped per user decision since empirical legacy behavior is already known: n_trades=0). Performance: 1. expf → piecewise-linear ramp (~5× cheaper on GPU, no transcendental in the hot path). Operationally equivalent: monotonic, saturating, midpoint at K. Side-benefit: pure max-confidence at cold-start (sq=0 instead of sigmoid's 11.9% leakage). 2. Single fused per-horizon pass replaces the two-loop sketch. 3. Tier 2 scope narrowed to decision_policy_default ONLY. The bytecode VM (decision_policy_program) stays unchanged — runs only for custom strategy experiments, never in production policy. Halves Tier 2's surface area + test cost. 4. __device__ helpers cbsw_signal_quality + cbsw_weight introduced for single source of truth. Correctness bugs (silently present in v1 sketch, would have shipped): 5. strong_h and sq_min_active initializers added (were referenced before init in the per-horizon loop). 6. Attribution mask at cold-start was setting all 5 bits because every w[h] >= floor > 1e-9; trades would pollute ALL horizons' recent_sharpe. Fix: binary split — at sq_min_active < 0.5 attribute only to strong_h; at mature, attribute per weights > floor + epsilon. 7. sq_min was "min over h", which permanently locked the aggregator into cold-start mode if any horizon never gets attributed (e.g., h6000-only-trading regime). Fix: sq_min_active = min over h with n_trades_seen > 0; cold horizons don't gate maturity. 8. Opposing-horizons case now correctly fires on the strongest single horizon at cold-start (piecewise-linear sq=0 → pure max-conf), with explicit design-choice note explaining why this conservatism trade- off favors firing. Spec hygiene: 9. Rate validation committed to a measurement gate (Q2 ev/s ≥ 95% of Q1 ev/s) instead of back-of-envelope estimate. 10. Kernel ABI explicitly stated as unchanged → feedback_no_partial_ refactor compliance is trivial at the kernel boundary. 12. Tier 1's use_cold_start_stopgap field is DROPPED in Q2 atomically (not orphaned), and DoD checklist includes a grep-zero gate for feedback_no_legacy_aliases compliance. Risks updated: removed the sigmoid-narrowing risk (irrelevant now); added register-pressure risk with the rate-gate mitigation; added explicit "cold-start may lose on noisy trades" risk with empirical escalation path (bump kelly_floor 0.20 → 0.40 if Q2 smoke shows large negative PnL). Math walk-throughs rewritten for piecewise-linear (different numbers at cold-start): cold = pure max-conf, mature = pure weighted-sharpe, clean separation at sq_min_active threshold. Awaiting review of the revised spec before writing-plans dispatch. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
1271d03931 |
spec(ml-backtesting): CBSW cold-start aggregator design
The post-trunk-grows threshold-tuning smoke (
|
||
|
jgrusewski
|
d646c1eb3c |
spec(ml-backtesting): apply 9 critical-review fixes to parallelism spec
Critical review surfaced 9 issues; all fixed inline:
1. §1 — Reframed "140× amortization" as "amortization on forward; sim
runs parallel". True win is on the ~2ms forward shared across 140
cells, not on sim work which scales linearly with n_backtests.
2. §2 — Made the 1h target vs firm bound explicit (≤1h target, ≤2h
firm). Acknowledges Graph capture realistic speedup is 1.2-1.5×,
not 2×.
3. §5 — Dropped atomicAdd. Plain `+=` under the single-writer-per-block
convention (existing pattern across sim kernels). No race.
4. §4 — Documented max-over-horizons threshold rationale (vs per-
horizon or aggregate-conviction). Flagged per-horizon as a follow-up
tweak if dilution pathway matters in the verdict.
5. §7 P5 + §10 risk — Captured-vs-uncaptured tolerance is 1e-5 relative,
NOT strict bit-identity. CUDA Graph capture can reorder reductions
harmlessly by 1 ULP; strict bit-identity would be a false-positive.
6. §8 — Made explicit that parallel_sim_equivalence + independence
tests are BOTH required. Equivalence alone is necessary but not
sufficient (a shadow-backtest[0] bug still passes equivalence).
7. §3.3 — Specified output schema: `cell_W{n}/sim_<variant_name>/`
with summary.json carrying a resolved `sim_config` block (verdict
emitter reads that, not the directory name).
8. §7 P4 — Enumerated apply_fill_to_pos call sites + added grep-verify
step before commit, so no fill path silently loses cost.
9. §9 — Tightened rate-validation gates with hard targets (P2 ≤90s,
P5 ≤60s) instead of generous minute envelopes. Added §9.1 stride=8
fallback as explicit Plan-B if Graph capture under-delivers.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
jgrusewski
|
bd35bdb6a3 |
spec(ml-backtesting): deployability-sweep parallelism + rate design
Brainstormed live with claude-opus-4-7. Targets ≤1h wall-clock per
4-quarter sweep on 1-3 L40S pods (vs ~750 GPU-hours naive). Three
multiplicative levers: per-backtest sim parameter matrix (~140×),
CUDA Graph capture (~2×), pod-level parallelism (~3×). Verified by
code-read during scoping:
- forward_only has no graph capture (X11 plan said so, X11 commit
didn't ship it)
- two host-roundtrip loops in sim.rs need GPU-ization for batching
to pay off (dispatch_latent_market_orders + close-detection)
- cost system is a literal-zero placeholder in pnl_track.cu:92
7-commit atomic ladder (P1-P7), each gated by tests + a measured rate
target. bf16 explicitly deferred to follow-up.
Awaiting review before transitioning to writing-plans for the
implementation plan.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
jgrusewski
|
da1dd92bf8 |
spec(ml-alpha): trunk-grows refactor + deployability validation (supersedes prior)
Supersedes the 2026-05-19 deployability spec (commit
|
||
|
jgrusewski
|
07d5de5048 |
spec(ml-alpha): v2 deployability — stress anchor + max-dd gate + diagnostics
User revisions to design spec from this session: 1. §2.1 — split anchor into realistic (200 ms, 1 tick) and stress (400 ms, 1.5 tick). Realistic remains the hard verdict gate; stress grades the Pass into Pass-robust vs Pass-nominal. 2. §2.2 — expand metrics from Sharpe-only to four: annualized daily Sharpe and max-drawdown are hard gates (median across windows > 1.0 and < 20% respectively); Sortino and profit factor are diagnostics. Per-window summary.json schema extended. 3. §2.6 — verdict emitter rewrites to two-anchor logic, tiered output: Pass-robust / Pass-nominal / Fail-inconclusive / Fail / Fail-degenerate. 4. §3.3 — added max-dd computation and zero-trade-window failure modes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
0809390cd5 |
spec(ml-alpha): v2 deployability validation — falsifiable LOB-backtest verdict
Closes the wiring gap between the existing real-LOB backtest system (C1–C19 on this branch) and the v2 ml-alpha model. alpha_train.rs currently never calls save_checkpoint, so the LOB harness/sweep/aggregate machinery has never been pointed at a real trained model. Design defines a single-pass falsifiable deployability gate: produce a production checkpoint (cv-n-folds=1, cv-train-window=4 → train on 2024 quarters, val on 2025-Q1, hold out 2025-Q2..2026-Q1), pre-register one threshold on the W0 val window, then evaluate median Sharpe across 4 held-out walk-forward quarters at the realistic Scaleway→IBKR anchor (200ms RTT, 1-tick all-in cost). Pass iff median > 1.0; inconclusive in [0.8, 1.0] counts as fail; smoke gate halts the full sweep on any wiring failure. Approved through brainstorming. Awaiting user spec-review before plan handoff. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
6b7920474d |
spec(ml-alpha): mark AUC-regret controller SUPERSEDED — empirically falsified
The motivating "50% saturation hit-rate" observation came from gm67g fold 0 (Option-2 config, commit |
||
|
jgrusewski
|
1fc100ae74 |
spec(ml-alpha): AUC-regret controller — replace BCE-z-score signal with per-horizon-regret
The current λ controller boosts horizons by BCE-EMA z-score, which conflates
three distinct causes of high BCE — only one of which (under-trained
horizon) benefits from boosting. The other two (intrinsically harder
horizon, calibration drift) are unaffected by gradient-magnitude lifts.
Empirical motivation (gm67g fold-0, this branch's 3-fold run):
when λ_h6000 saturated at 2.0, h6000's next-epoch AUC went UP 2/4
times and DOWN 2/4 times. 50% hit rate ⇒ the BCE saturation signal
is misaligned with the optimization objective.
This spec replaces BCE-z-score with AUC-regret:
best_auc[h] = running max of per-horizon validation AUC
regret[h] = max(0, best_auc[h] - current_auc[h])
regret_max_ema = EMA of max_h regret[h]
λ[h] = clamp(1.0, 2.0, 1 + regret[h] / regret_max_ema)
Properties:
- Aligned with the objective (AUC, not BCE)
- Naturally bounded (regret ∈ [0, 1])
- "At personal best" → λ=1.0 (no wasted boost)
- Auto-saturation by design (max-regret horizon → ceiling)
- Cold-start clean (e0: best=current, regret=0, uniform λ)
- Zero hardcoded magic beyond bootstrap epsilons
Implementation surface ~250 LOC:
- Split horizon_lambda kernel: horizon_loss_ema (per-step) +
horizon_lambda (per-epoch, AUC-regret math)
- Trainer state: drop z_max_ema, add best_auc + regret_max_ema
- Per-epoch entry point: trainer.update_lambda_from_auc()
- Extend isv snapshot log line with best_auc_h* + regret_h*
Test plan:
- Local 9/9 perception_overfit
- New synthetic-AUC unit test (controller correctness)
- Cluster 5-epoch smoke + 3-fold A/B vs Option-2 baseline (
|
||
|
jgrusewski
|
1c2ee1d7c3 |
spec(ml-alpha): v2 multi-horizon redesign (A+B+C+D+E integrated)
Integrated design spec for the post-A/B redesign: Kendall sigma BCE (A), L2 anchor on horizon tokens + shared Q (B), horizon-token K-prepend replacing per-horizon Q_h (C), regime-aware MoE gate (D), and inverted-axis attention pass (E). Bundled per pearl_no_deferrals_for_complementary_fixes — all five axes have orthogonal architectural scope and independent kill criteria. Spec drops the C21-C25 per-horizon Q_h path (falsified by sweep 2026-05-18: mean_auc -0.019 vs single-Q baseline) and migrates the existing init buffers into the new horizon-tokens prefix. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
f5632649ca |
spec(ml-alpha): per-horizon attention pool design (C20)
Captures the brainstormed "alternative attention pool variants"
follow-on from the original real-LOB integration brainstorm (Axis 1,
deferred from the LOB workstream as a separate model-side spec).
Design:
Replace shared learned query Q[HIDDEN_DIM] with per-horizon queries
Q_h[N_HORIZONS, HIDDEN_DIM]. Per-horizon softmax + context vectors
feed multi-horizon heads directly (PATH A) — each horizon attends
to a different part of the K=6000 LN_b output sequence. CfC k=0
state is initialised by the MEAN of per-horizon contexts so the
K-loop recurrence + state amplification (per
pearl_state_amplifies_short_horizon_into_long_horizon) survives.
Heads consume per-horizon context concat CfC h_K (residual) with a
default 75/25 weight split.
Falsifiable claim (§0): A/B-tested win means h6000 mean_auc lifts by
≥ +0.01 absolute OR per-horizon distribution shifts toward short
horizons (h1000, h300) with no net h6000 loss. The 3-fold variance
band on the current architecture (mean_auc 0.7749 ± 0.024) means a
+0.01 lift is within noise — a meaningful effect needs ≥ +0.024 or
qualitative distributional shift.
Two new kernels (per_horizon_attention_pool_fwd + _bwd) + signature
extension on multi_horizon_heads_{fwd,bwd}. Variant-toggle config flag
(SharedQuery vs PerHorizonQuery) keeps the existing path fully
functional; new variant is opt-in. CheckpointV1 → V2 with explicit
discriminant + optional q_h field; V1 files load as SharedQuery, new
V2 training writes the discriminant.
Three validation rings:
1. Per-(b,h) numgrad parity at K=16
2. One-epoch smoke (no NaN, loss decreases)
3. 30-epoch × 3-fold A/B (#204) — decision gate per §0 falsifiable claim
Implementation explicitly deferred. The decision to invest depends on
(a) GPU time budget (~3-6 hrs on L40S × 5 GPUs for the A/B), (b)
whether per-horizon cost-frontier sweeps (#202 follow-ups) surface
viable horizons beyond h6000 that would benefit from per-horizon
specialisation, and (c) the 3-fold variance noise floor making the
expected effect size visible.
Next step when ready: invoke superpowers:writing-plans against this
spec for the ~6-8 commit implementation plan.
Closes the "good to have" question from the recent brainstorm with a
concrete decision framework rather than ad-hoc implementation.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
bfbaea2661 |
spec(ml-backtesting): real-LOB integration design
Greenfield LOB simulator + execution policy + backtest harness inside existing ml-backtesting crate. Turns the AUC predictor into a P&L producer at IBKR+Scaleway latency profile (100ms baseline). Key design decisions: - Reuse trainer's MultiHorizonLoader, Mbp10RawInput, snap_feature_assemble cubin, CfcTrunk captured graph verbatim (zero train-vs-deploy skew). - Per-horizon ISV-Kelly + adaptive WeightedByRealizedSharpe aggregator (no static horizon mask; policy self-shifts capital). - Block-per-backtest CUDA (32 threads/warp/block), ~1.4 KB shared mem. - Three captured graphs (perception, step-event, decision); host branches only between captures. - Mapped-pinned for all CPU/GPU buffers (hard requirement per feedback_no_htod_htoh_only_mapped_pinned). - Three validation rings: N=1 bit-exact fixtures, trainer-parity check, N>1 invariant fuzz; production-day replay as Ring 3. Single binary fxt-backtest with run + aggregate subcommands. No new crates; extends existing ml-backtesting alongside barrier_backtest. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
ea1d8703b7 |
spec(perf): revise K-loop parallelization design — full critical pass
Revises all 12 issues from the self-review pass:
1. (HIGH) Soften bit-equivalence claim — single-sample helper and
batched kernel at B=1 are different CUDA kernels; FP order may
differ. Acceptance is relative_eq ≤ 1e-6, not bit-exact.
2. (HIGH) Explicit asymmetry: only cfc_step has a single-sample GPU
oracle. GRN/VSN/attn bwd rely on smoke + chain-rule preservation.
feedback_no_cpu_test_fallbacks.md forbids a CPU reference oracle.
3. (HIGH) Realistic targets — 3× floor, 5× stretch. Drops 15× claim
which was Amdahl-bounded under any reasonable assumption.
4. (MED) AdamW-after-reducer invariant stated explicitly: final grad
buffer is OVERWRITE by reducer, meaningful only after reducer ran.
5. (MED) New B=32 smoke test (stacked_trainer_loss_shrinks_at_batch_32)
actually exercises the cross-batch reduction path; existing
perception_overfit suite is all B=1.
6. (MED) Rollout commit 1 bundles reduce_axis0 + first consumer
(cfc_step refactor) to avoid feedback_wire_everything_up.md
orphan-kernel anti-pattern.
7. (LOW) Drop "merge to ml-alpha-phase-a" — user already chose direct
commits to that branch; clarify in Rollout.
8. (LOW) Add explicit scratch-sizing formula:
scratch_bytes ≈ B × Σ(param tensor sizes per kernel).
9. (LOW) Remove resolved open question (memset_zeros ordering).
10. (STRUCT) Post-refactor bottleneck analysis section — names the
next L40S floor (Mamba2 scan, launch latency, cuBLAS).
11. (STRUCT) cudaFuncSetAttribute note — refactored cfc_bwd's per-
block shared mem drops to 1 KiB; no attribute change needed.
12. (STRUCT) Explicit Rollback section — atomic-commit-per-kernel +
revert strategy; rollback baseline is the spec commit
(
|
||
|
jgrusewski
|
54aa69c108 |
spec(perf): K-loop block-per-batch parallelization design
Documents the design for fixing the single-SM bottleneck in five backward/K-loop kernels: cfc_step (fwd+bwd), GRN bwd, VSN bwd, and attention_pool bwd. All currently use grid=(1,1,1) with an internal n_batch loop — on L40S (142 SMs) with B=32 this puts <1% of the GPU to work in the K-loop critical path. Architecture: block-per-batch (grid=(B,1,1)) for the kernel body, plus per-batch grad scratch buffers reduced via a single parameterised reduce_axis0 kernel (block tree-reduce, no atomicAdd per feedback_no_atomicadd.md). Same pattern as the existing LayerNorm bwd reducer — CUDA-Graph-safe, debuggable, and consistent with foxhunt's no-cooperative-groups discipline. Target: ≥3× epoch wall speedup (stretch 8-15×). Makes 3-fold CV tractable (10.5h → 2-3h) and unblocks decision-stride / state-dim sweeps that compound the gain. Acceptance gates: (a) all 8 perception_overfit smokes still converge, (b) new B=1 bit-equivalence test asserts the refactored batched bwd kernel at B=1 matches the existing single-sample helper byte-for-byte, (c) cluster A/B vs t6z89 baseline shows AUC trajectory within ±0.005 and epoch wall ≥3× faster. Atomic refactor per kernel — one commit per kernel covering the kernel rewrite, scratch buffer alloc, reducer launch wiring, and smoke. No "_legacy" parallel kernels per feedback_no_legacy_aliases.md + feedback_no_partial_refactor.md. Open implementation-plan decisions: exact memset_zeros ordering inside the captured graph, batch-vs-per-tensor reducer launches, optimal block_dim for reduce_axis0 itself. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
ef35b10f3e |
refactor(ml-alpha): drop competitive-gate machinery — stacked is default
Per user direction "no gating, this is the new default": the stacked
Mamba2 -> CfC -> heads design is THE production architecture. There's
no competing-baseline comparison to run. Validation reduces to normal
training metrics (per-horizon val AUC, train loss curve, sanity floor
of >0.5 AUC).
Deletions:
- crates/ml-alpha/src/gate/cfc_vs_mamba2.rs (gate verdict logic)
- crates/ml-alpha/src/gate/mod.rs
- crates/ml-alpha/examples/alpha_gate.rs (gate runner binary)
Renames:
- crates/ml-alpha/src/gate/auc.rs -> crates/ml-alpha/src/eval/auc.rs
- lib.rs: pub mod gate -> pub mod eval (gate implied comparison;
eval doesn't)
Spec amendments:
- Drop the "Gate baseline strategy" amendment (committed earlier
this session)
- Reframe the stacked-architecture amendment as a "decision" not a
"gate"; production path is unambiguous
- Reframe Section 4 "Validation gate: CfC must meet Mamba2" -> just
"Validation: per-horizon val AUC" with the >0.5 sanity floor
Doc cleanups: stale "Mamba2 gate baseline" mentions in build.rs and
pinned_mem.rs replaced with neutral wording. The Argo template
comment about "downstream gate consumption" becomes "for monitoring".
Test status: all 26+ ml-alpha tests pass. AUC tests (6/6) still pass
under the eval:: namespace.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
6e868fd136 |
spec(ml-alpha): gate-baseline ablation strategy amendment
Defines the Mamba2-only baseline for the stacked-vs-baseline gate verdict as an ablation of the SAME PerceptionTrainer (a --bypass-cfc flag), not a separate model. Apples-to-apples; same data window, same hyperparameters, same code path. The only difference is whether the CfC step is in the loop. Three ablation options evaluated: 1. --bypass-cfc flag (recommended): Mamba2 -> heads directly 2. --mamba2-state-dim 2 (crippled Mamba2, CfC stays) 3. Frozen CfC initialized to identity (no code branch needed) Option 1 wins on clarity: it answers "is CfC additive on top of Mamba2" unambiguously, with the same Mamba2 capacity and same training regime in both arms. Concrete next-session work documented (1-2 hours): - PerceptionTrainerConfig.bypass_cfc: bool + step() branch - alpha_train --bypass-cfc CLI flag - alpha-perception-template.yaml workflow parameter + bash branch - submit both runs, fetch summaries, alpha_gate, commit verdict gate_verdict logic unchanged — the cfc/mamba2 naming in the report becomes stacked/bypass at the binding layer; the verdict math is generic. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
3389a59281 |
spec(ml-alpha): stacked Mamba2 -> CfC amendment
Mid-execution architecture revision: Mamba2 stays as a sequence encoder; CfC becomes the layer on top (replacing the Phase 1d.3 MLP stacker). Gate becomes 'stacked AUC >= Mamba2-only stacker AUC at every horizon' — proves the CfC layer is additive, rather than CfC alone beating Mamba2 alone. Plan 1 kernels (cfc_step, heads, projection, BCE, AdamW, Graph A) are unchanged. Only CfcTrunk's forward path gains a Mamba2 prefix that consumes the snapshot stream and emits a 128-dim h_mamba which CfC reads. The Mamba2 kernel (mamba2_alpha_kernel.cubin) is already in the build. Option B (parallel + fused dual-stream) is documented as the Plan 2 fallback if the stacked gate fails. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
90d14aaba5 |
spec(ml-alpha): GPU/CPU contract, CUDA Graphs, cold-start, disconnect handling
Critical-review pass on the CfC+PPO design adds: - Public API: mapped-pinned ingress slots, single DtoH per decision - Section 5.5: CUDA Graph capture topology (perception / policy / training), kernel inventory, cuBLAS Lt epilogue fusion, persistent ring layouts, determinism mode, build-time cubin compilation, perf budget - Section 5.6: Databento/IBKR disconnect + failure response, never-do list - Section 6 cold-start: 4-state bootstrap, Phase B walk-forward stats as pre-deployment kill-switch baseline, always-live ISV controllers Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
d4ea54d780 |
spec(ml-alpha): CfC + PPO greenfield design
Approved design document for the ml-alpha rebuild. Seven sections plus
appendices, all 7 sections + ISV-driven auto-tuning addition approved
via the brainstorming-skill flow.
Key architectural decisions:
- Full closed-loop scope: training + offline inference + live IBKR
- Three components: ml-alpha library, alpha_train binary, AlphaPpoStrategy
in trading_agent_service (reuses existing data_acquisition,
trading_service, broker_gateway, and the 1177-LOC IBKR adapter that
already exists in trading_engine)
- Snapshot-level CfC perception trunk (Closed-form Continuous-time, the
trainable LTC variant from Hasani 2022) — chosen over Mamba2 for
native multi-time-scale via per-cell learnable τ; hard validation
gate requires CfC AUC ≥ Mamba2 baseline before continuing
- 5 multi-horizon heads at {30, 100, 300, 1000, 6000} snapshots forward
- Decision-stride 50 snapshots (~1 min); empirically validated this
session (per-bar→stride=200 flipped 3-fold mean Sharpe from -4.29 to
+1.78 at quarter-tick cost)
- Action: target_position categorical ∈ {-10, ..., +10}; max_train=10
fixed at architecture level, max_live ≤ 10 runtime-cappable
- Reward in price units (position-size invariant): dense per-segment
PnL − C_trade·|Δcontracts| − C_vol·vol_excess; C_trade=0.034 fixed
(IBKR $1.70 RT ÷ $50/point), C_vol=0 default
- Full online learning with EWC anchoring + 80/20 offline/live replay
buffer + kill-switch on σ-band metric deviations (loss, mean reward,
hit-rate, KL, entropy)
- All hyperparameters that vary during training are ISV-driven
(controller outputs, not magic numbers) per
pearl_controller_anchors_isv_driven.md
- Fully GPU-resident on hot path per feedback_cpu_is_read_only.md
- $35k starting capital; conservative max_live ramp 1→2→3 contracts
with manual config bumps gated on realized track record
- Documented IBKR-specific quirks (PDT, mid-session margin spikes,
rollover, halts, rate limits) with concrete design responses
Supersedes the abandoned 2026-05-16-alpha-ppo-trainer.md (DQN-port plan)
which inherited the wrong architectural shape.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
2fe76f2f34 |
docs(phase-e-4-a): execution status + T10 backward_from_h_enriched patch sketch
Two documentation deliverables produced while T14 backtest runs: 1. Plan update (specs/2026-05-15-phase-e-4-a-temporal-foundation.md): adds 'Execution Status' section reflecting actual T1-T14 progression. T5 deferred (real MBP-10 peek), T9 skipped (GRN moved to E.4.B per integration notes), T10 partial (new C51 grad-input kernel landed but Mamba2 backward wiring deferred), T14 in flight. Documents the 4 execution learnings: research-first saved a week of duplicate kernel work; cheap falsification experiments (Path 2, Path 3) avoided expensive investments; C51 borrow was the largest single Sharpe-lift in the session; GpuTensor/CudaSlice interop friction is the real integration cost. 2. T10 patch sketch (specs/2026-05-15-t10-mamba2-backward-from-h-enriched.md): ready-to-apply patch for ml-alpha::Mamba2Block adding a new public method backward_from_h_enriched(cache, d_h_enriched). Bypasses the W_out projection backward, accepts the [B, hidden_dim] gradient from C51's grad-input kernel directly, zero-initialises dw_out/db_out (AdamW step on zero grad is a no-op with correct moment decay — effectively freezes W_out params which is correct semantics since Phase E never uses them). Includes the smoke binary wiring snippet that consumes the new method via launch_alpha_c51_grad_input → Mamba2 backward → AdamW step. Application gated on T14 backtest validation — if frozen Mamba2 already lifts Sharpe, T10 becomes optimisation rather than prerequisite. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
eb9047fc30 |
docs(phase-e): E.4 temporal encoder design + E.4.A implementation plan
Design doc (specs/): TFT-style architecture for Phase E execution
policy — sliding window → Mamba2 SSM → GRN trunk → MoE regime gate
→ C51 head → Thompson selector. Two core pillars added per user:
A) Full L1-L10 LOB depth input via hybrid MBP-10 peek
B) ISV-continual-learning: controllers fire at training AND
inference; Q-net weights frozen at inference but effective
policy adapts via ISV modulation
Plan doc (plans/): 14-task implementation plan for E.4.A foundation
(window buffer + L1-L10 depth + Mamba2 forward+backward + ISV-eval
controllers). Falsification gates: smoke R_mean improvement ≥ 50%,
backtest cost=0 Sharpe ≥ +8 (no regression vs C51-flat +10.41),
half-tick Sharpe ≥ -8 (closes 5pt+ of 10pt gap to Phase 1d.4
baseline -4.0).
TGGN (foxhunt Temporal Graph Gated Network) explicitly deferred to
Phase E.5+: existing CPU graph implementation + GPU adapter at
ml-supervised/src/tgnn/ — marginal benefit for single-instrument ES
futures vs the TFT-Mamba2 stack; revisit for multi-instrument
extension or production HFT inference layer.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
588a6d38af |
docs(phase-e-4-a): mamba2 + grn integration research — use ml-alpha Mamba2Block
Findings: - Production Mamba2 (gpu_dqn_trainer) is coupled to SH2=256 trunk + ofi_embed + ISV[8] temporal routing — not portable to Phase E. - ml-alpha::mamba2_block::Mamba2Block is from-scratch, fully configurable (in_dim/hidden_dim/state_dim/seq_len), GPU-pure with forward_train/backward/AdamW. Used in Phase 1d.2 to lift AUC 0.50 to 0.66. ml-alpha is already a workspace dep of ml. - GRN skipped for E.4.A — Mamba2 output goes straight to C51 head. Reintroduce GRN in E.4.B if Sharpe gates don't pass. - Controller-at-inference: kernel has no training-mode branches; Wiener state preserved across episodes/cost cells for natural live-deployment simulation. Revises Tasks 8-10 of the plan: use Mamba2Block API instead of writing custom kernels. Only new CUDA needed: alpha_c51_grad_input (C51 gradient w.r.t. input features, for Mamba2 backward chain). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
9e6637c065 |
docs(claude): foxhunt-aware agents & skills design — phase 1 (12 items)
Pattern-cluster auditors + workflow-skill hybrid that internalize accumulated project wisdom (15 feedback_*, 30+ pearl_*, 12+ project_* memory files; 30 SP specs) into foxhunt-namespaced agents and skills under .claude/agents/foxhunt/ and .claude/skills/foxhunt/. Phase 1: 5 auditor agents (isv-discipline, gpu-contract, reward-controller, code-hygiene, sp-critical-reviewer) + 5 workflow skills (sp-spec-writer, isv-slot-scaffolder, pearl-distiller, argo-deploy-helper, smoke-pilot) + 2 maintenance skills (memory-curator, stale-worktree-cleaner). Hook integration is warn-only PostToolUse via a single thin router; agents read memory but only pearl-distiller and memory-curator may write into memory/. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
235e838422 |
feat(sp20): Phase 1.4 (Path C) — kernel-arg refactor + aggregation kernel + wire-up
Atomic Phase 1.4 commit per `feedback_no_partial_refactor`. Wires the
SP20 fused-producer chain (Stats → Aggregate → EMAs → Controllers) into
GpuExperienceCollector's per-rollout-step path with one new aggregation
kernel + Phase 1.2 EMA kernel-signature refactor + production wire-up
+ tests + audit/spec/plan amendments, all in one commit.
## Path C decision rationale
The Phase 1.2 EMA kernel originally took 9 scalar value-args. The Phase
1.4 wire-up site (per-rollout-step in GpuExperienceCollector) needs to
feed per-env GPU-resident trade signals (trade_close_per_sample,
step_ret_per_sample, hold_at_exit_per_sample, packed factored
actions_out) into the kernel — forbidden via host sync
(`feedback_cpu_is_read_only`) and via memcpy_dtoh/htod
(`feedback_no_htod_htoh_only_mapped_pinned`). Path C refactors the EMA
kernel to take a device struct pointer (`SP20EmaInputs* ema_inputs`) +
adds an aggregation kernel that writes the struct on the GPU. Phase 1.2
had zero production consumers yet, so the sig change + Phase 1.4 wire-up
land atomically.
## What this commit contains
1. **EMA kernel signature refactor** (Phase 1.2 → Path C):
`sp20_emas_compute_kernel.cu` swaps 9 scalar args for a single
`const SP20EmaInputs* __restrict__ ema_inputs` device pointer.
Math semantics bit-identical. Rust `EmaInputs` mirrored as
`#[repr(C)]` byte-for-byte; new `pack_inputs_into_f32_view` helper
for tests + collectors that fill the struct via a mapped-pinned
f32-aliased buffer.
2. **New aggregation kernel** (`sp20_aggregate_inputs_kernel.cu`):
Per-env arrays (sliced to current rollout step) + sp20_stats outputs
(p50/std) + aux_dir_acc_reduce_kernel output [0] → SP20EmaInputs
struct. Block tree-reduce (4 stripes × bdim × 4 bytes shmem); no
atomicAdd. Aggregation rules per spec §4.5:
- is_close = OR over envs
- is_win = (≥ 0.5 of closed envs were wins)
- trade_duration = round(mean(hold_at_exit) over closed envs)
- action_is_hold = strict majority (count*2 > n_envs) HOLD
- alpha = 0.0 (Phase 2 forward ref — reward kernel)
- per_bar_hold_reward = 0.0 (Phase 3.2 forward ref — Hold-cost dual)
- aux_logits_p50/std/dir_acc forwarded from upstream
3. **Production wire-up in GpuExperienceCollector**:
4 kernel handles + 4 mapped-pinned buffers (struct fields, alloc,
init); per-rollout-step launch sequence after env_step (step 5c):
`Stats → Aggregate → EMAs → Controllers`. All on the same stream;
stream-implicit producer→consumer ordering. Gated on
`isv_signals_dev_ptr != 0 && trainer_params_ptr != 0` (matches the
existing SP14-β EGF chain pattern).
4. **Fold-boundary reset**:
3 new RegistryEntry records (sp20_ema_inputs_buf,
sp20_emas_internal_buf, sp20_emas_obs_count_buf) + 13 new dispatch
arms in training_loop.rs (10 SP20 ISV slot resets + 3 buffer resets).
Closes the pre-existing `every_fold_and_soft_reset_entry_has_dispatch_arm`
regression (was failing on fresh check after the SP20 ISV slot
registrations landed in commit
|
||
|
jgrusewski
|
4e21c38b85 |
fixup(sp20): Phase 1.1 K=3 → K=2 retarget (production aux head is K=2)
The Phase 1.1 sp20_stats_compute kernel (
|
||
|
jgrusewski
|
9d9ca3e6e7 |
spec(sp19+20): apply Q1(b) — Hold-reward EMA for Q-scale comparability
Q1 design decision (b): add explicit hold_reward_ema to center the per-bar Hold reward, so Q(Hold) and Q(trade) targets are scale-comparable. The marginal Q(trade) > Q(Hold) preference now comes from data variance in each state (high-aux states pull Q(Hold) more negative), not from structural scale asymmetry that depends on cost_scale magnitude. Q2 decision: keep 4-quadrant fixed (no ramping partials). Already in spec. Changes: - §4.2 Hold opp-cost: dual emission documented — R_per_bar_centered (= R_per_bar - hold_reward_ema) for Q-target/replay tuple, R_per_bar uncentered for hold_baseline_buffer (Component 1 baseline) - §4.5 Kernel 1: hold_reward_ema added (per-step on Hold-state bars only) - §5 data flow: per-bar reward path shows the centered/uncentered split - ISV slots: 9 → 10 (HOLD_REWARD_EMA_INDEX added) - §8 footprint: Component 2 LoC 70 → 90 (+20 for dual emission) - Total LoC estimate: 1620 |
||
|
jgrusewski
|
defbd0abe1 |
spec(sp19+20): patch 7 review issues
P1 (must-fix bugs/gaps): 1. ASYM_RATIO_INDEX → LOSS_CAP_INDEX with explicit formula in §4.1 and §4.5 (was double source-of-truth — formula in §4.1, ISV slot orphaned) 2. Replay buffer schema change (per-bar aux_conf) added to §8 implementation footprint (~50 LoC additional, was invisible in original spec) 3. hold_baseline_buffer size specified = LOOKAHEAD_HORIZON_MAX = 30 bars (§4.2) 4. "4-tier gate" typo → "5-tier gate" in §7 P2 (clarifications): 5. alpha_ema centering documented as load-bearing for cold-start learning (§4.1) — not just for Q-target stability. EV is slightly negative at WR=46% with uninformed SP19 label; advantage-style centering rescues cold-start. 6. Q-scale asymmetry between Hold (uncentered) and trade (alpha_ema centered) documented as INTENTIONAL design choice (§4.2) — produces marginal Q(trade) > Q(Hold) preference that counteracts the Q(Hold) attractor. Behavioral test sp20_pure_noise validates the no-signal Hold default still works. P3 (tightening): 7. Behavioral test thresholds tightened (§4.6): - sp20_pure_trend: WR > 70% → > 90%, PF > 2.0 → > 3.0 - sp20_pure_noise: Hold% > 80% → > 95%, trades < 50 → < 20 |
||
|
jgrusewski
|
730337375f |
spec(sp19+20): WR-first reward + multi-horizon label utilization
Combines SP19 (multi-horizon labels, already landed) + SP20 (WR-first reward) into one spec per pearl_no_deferrals_for_complementary_fixes. Goal: WR ≥ 55%, textbook PF ≥ 2.0, walk-forward stable, per-regime stable. Six components, atomic ship per feedback_no_partial_refactor: 1. Reward kernel (event-driven, 4-quadrant, asymmetric clamp ramped from wr_ema, multi-horizon directional ground-truth check) 2. Hold opportunity-cost (per-bar, dual emission for real reward + Hold baseline buffer) 3. n-step credit distributor (uniform over trade duration, fixes SP18 B-leg self-bootstrap bug at gpu_experience_collector.rs:4154) 4. Aux→Q confidence gate (sigmoid threshold, mean_a Q baseline avoids Hold-everywhere punishment) 5. 3 fused producer kernels (sp20_emas, sp20_controllers, sp20_stats) driving 9 ISV slots in [510..520) 6. 7 behavioral tests on RTX 3050 Ti, gating L40S deployment ~1,550 LoC total. Spec includes data flow, error handling philosophy, 4-tier test gate, success criteria with explicit failure modes. Cross-references: - pearl_event_driven_reward_density_alignment (design principle) - pearl_audit_unboundedness_for_implicit_asymmetry (asymmetric clamp) - pearl_separate_aux_trunk_when_shared_starves (aux gate leverages SP14-C) - project_metric_pipeline_inflation_audit (WR honest, Sharpe honest, goal grounded) - project_goal_wr_55_pf_2 (the goal this spec implements) |
||
|
jgrusewski
|
44e1f58b69 |
docs(sp18): copy spec + plan to feat/sp18-combined branch
Mirrors the SP17 PP.1 plan-copy pattern. Plan and spec source-of-truth live on the sister `feat/sp17-dueling-q-network` worktree; this commit copies them onto the SP18 branch so subsequent commits reference local paths. Spec: docs/superpowers/specs/2026-05-08-sp18-reward-shape-hold-attractor-design.md Plan: docs/superpowers/plans/2026-05-08-sp18-reward-shape-hold-attractor.md Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
5417e27567 |
docs(sp15): amend spec v2 — 10 fixes from second critical review
Second critical review pass found 10 more issues, 3 critical. All addressed: CRITICAL: - §8.2 (3.1): ALPHA_SPLIT cold-start was unspecified — formula produces 0/0=0, not the claimed 0.5 sentinel. Now: ISV slot initialized DIRECTLY to 0.5 in trainer constructor; formula takes over only after both grad-norm EMAs accumulate N_warm non-zero observations - §9.2 (3.5.4): plasticity now performs TWO-STEP recovery: (1) Flat all positions at fire bar (close current losing trade), (2) engage warmup cooldown forcing Hold for M_warm bars. Without step 1, forced Hold preserved the losing position that drove drawdown for the entire 200-bar warmup - §12.2: stale "5-10%" baseline cost estimate updated to "15-25%" matching §6.4 (was contradicting earlier amendment) IMPORTANT: - §9.2 (3.5.5): DD_TRAJECTORY_DECREASING threshold 0.02 hardcoded → ISV-driven via new slot DD_TRAJECTORY_FLOOR (slot 441, 25th percentile of running dd_pct distribution) - §8.2 (3.5): HOLD_FLOOR_ALPHA tracked from rolling 95th percentile of |Q_dir| (NOT running max — was outlier-ratchet vulnerable) - §9.2 (3.5.3): MEDIAN_STREAK_LENGTH formerly undefined in cooldown K formula → ISV-driven via new slot 442, running median of observed loss-streak lengths via two-heap algorithm - §9.2 (3.5.2): asymmetric reward × α split compound interaction explicitly stated as intentional with POS_CAP as binding ceiling NIT: - §7.4: "2C: Group 3 (4 tests)" → "(5 tests)" (was off-by-one after 2.22 added) - §9.2 (3.5.4): Xavier → Kaiming-He init for advantage head reset (architecturally appropriate for ReLU-gated activation chain) ISV_TOTAL_DIM: 441 → 443 post-SP15 (added DD_TRAJECTORY_FLOOR and MEDIAN_STREAK_LENGTH at slots [441..443)). 46 SP15 slots total. File: 799 → 811 lines. Spec is now consistent end-to-end with no contradictions between sections, no hardcoded values violating feedback_isv_for_adaptive_ bounds, and no underspecified load-bearing parameters. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
f3cb0c78c2 |
docs(sp15): amend spec — 14 fixes from critical review
Critical review (combined fresh-eyes subagent + self-critique) flagged 14 issues. All addressed in this amendment. CRITICAL (blocks implementation): - §4.3 NEW: ISV slot allocation map [397..441) per phase, prevents parallel-dispatch ISV-table conflict (was: undefined, would break Approach B) - §4.4 NEW: Phase 2A ↔ Phase 1.2 ABI contract (LobBar struct as canonical contract, Phase 2A defines first; Phase 1.2 conforms). Restores parallelism dependency - §9.2 (3.5.4): plasticity injection now MANDATES cooldown engagement via PLASTICITY_WARM_BARS_REMAINING slot 438. NEW anchor test 2.22 plasticity_cooldown_interlock prevents random-tail-output retrigger loop - §9.2 (3.5.5): recovery curriculum replaced episode-level metadata (didn't exist in transition-level PER) with per-step DD_TRAJECTORY_ DECREASING signal — same goal, no PER restructure IMPORTANT (rework prevention): - §9.2 (3.5.3): cooldown K threshold from running mean of per-trade PnL (NOT variance — variance is LOW during streaks, would delay cooldown when needed) - §8.2 (3.5): Hold floor function form specified as bounded sigmoid with α/k/ε₀ ISV-driven; was "monotonic_inv_func" (undefined family) - §6.2: cost kernel per-side semantics explicit. Half-spread × side_ indicator at entry AND exit; commission_per_rt on close. Resolves round-trip vs per-side ambiguity - §6.2: OFI impact λ initial value 2e-4 + ISV refit methodology; was "empirical fit from MES historical" (hand-wavy) - §6.4: 8 baselines now mandate shared trunk forward; honest 15-25% overhead estimate (was 5-10%, optimistic) - §12.3: Q9 burn policy explicitly honor-system, not enforcement. Mitigations described as deterrents not enforcement - §10.6: Phase 4.5 thresholds CLI-config-driven with rationale, anchored empirically post-Phase-1 (was hardcoded > 1.0) NIT: - §9.2 (3.5.2): multiplier vs SP12 cap interaction explicit (applied BEFORE cap) - §8.2 (3.1): α=0.7 hardcoded → ISV-driven from grad ratio (was feedback_isv_for_adaptive_bounds violation) - §13: pearls reframed as candidates pending validation per discipline rule; pre-naming pressure removed Test count: 21 → 22 (added 2.22). Phase 2 LOC: 2000 → 2100. ISV_TOTAL_DIM: 396 → 441 post-SP15. All 14 issues addressed in spec text. Ready for user review. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
fb5f2394d0 |
docs(sp15): trader discipline and recovery design spec
Design spec for SP15 — addresses the train-dd4xl downward spiral post-mortem (8 epochs, trades 131k→64k, sharpe 79→44 with monotone descent across active_frac, dir_entropy) and the walk-forward audit finding (test_start..test_end slice generated but never consumed, val IS the selection set, no sealed test). Six phases over ~13-21 days: - Phase 0: SP14 EGF ISV-driven retune (gate1=closed forever fix) - Phase 1: honest numbers — unified sharpe kernel, cost-net (commission + spread + OFI-impact, dev/prod parity), drawdown reporting, 8 counterfactual baselines, dd_pct as foundational state input, --holdout-quarters/--dev-quarters CLI, consume abandoned test slice - Phase 2: 21 behavioral tests on dev RTX 3050 Ti, pre-commit hook gates argo-train.sh - Phase 3: 5 trader teachings (r_quality/r_discipline split, explicit cost, quadratic DD, regret, confidence-aware Hold floor) - Phase 3.5: 4 recovery mechanisms (asymmetric reward under DD, cooldown gate, plasticity injection, recovery curriculum in PER) - Phase 4: L40S walk-forward Q1-Q7, Q8 final dev, sealed Q9 OOS Cross-cutting discipline rule: no new pearl/controller/kernel/ISV slot/reward term ships without a Phase 2 behavioral test that proves the intended trader behavior. Hard rule, no exceptions. Decisions captured from 7 clarifying questions answered 2026-05-06. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
40e737a181 |
docs(sp14): spec v3 — K=4 direction + ISV-adaptive β rate limiter
Two further user-flagged corrections from second-critical review:
1. Direction Q-head emits K=4 actions, NOT K=3.
Authoritative source: state_layout.cuh:123-126
#define DIR_SHORT 0 // open/maintain short
#define DIR_HOLD 1 // keep current position (no-op)
#define DIR_LONG 2 // open/maintain long
#define DIR_FLAT 3 // close all to zero
The "default: 3 — Short/Flat/Long" comment at gpu_dqn_trainer.rs:2438
is stale pre-SP13. Production callsites all set branch_0_size: 4.
SP13 added DIR_HOLD as a separate fourth direction action (Hold-pricing).
The config default comment was never updated when DIR_HOLD landed.
This is exactly the feedback_trust_code_not_docs failure mode — a
single stale comment would have silently corrupted the q_disagreement
signal (Hold/Flat being indices 1/3 instead of just Flat=1).
Updates:
- B.1 action-space context: 4 actions with Hold AND Flat both
non-committal (Hold = keep position, Flat = exit to zero)
- B.2.3 q_disagreement mapping: K=4↔K=2 with both Hold and Flat
masked from disagreement signal (no new directional commitment
to evaluate); only Short and Long picks contribute to disagreement
- Edge case handling for all-Hold/all-Flat batches
2. Adaptive β rate limiter (was structural β=0.9).
Per feedback_isv_for_adaptive_bounds, β should be signal-driven
not hardcoded. v3 derives β from variance of α_grad_raw, mirroring
the k_aux/k_q variance-driven steepness pattern in B.2.5.
Formula:
β = clip(β_base + variance_alpha_raw / variance_ref_alpha,
[β_base, β_max])
β_base = 0.5 (light smoothing baseline; ~2-step half-life)
β_max = 0.95 (heavy smoothing; ~20-step half-life)
Stable α_grad_raw → β = β_base (preserves directional intent)
Volatile α_grad_raw → β → β_max (dampens jitter)
Adds 2 ISV slots:
ALPHA_GRAD_RAW_VARIANCE_EMA_INDEX (Welford variance)
BETA_RATE_LIMITER_ADAPTIVE_INDEX (current β value)
ISV slot count: 11 → 13 (net +2 for variance + adaptive β).
LOC estimate: ~1150 → ~1180 (negligible delta; 3 Welford
variances now in alpha_grad_compute_kernel instead of 2).
HEALTH_DIAG pearl_egf_diag emit updated to expose all three
adaptive scalars (α, β, k_aux/k_q) plus all three driving
variances (var_alpha, var_aux, var_q) for full observability.
Verified against current code at HEAD
|
||
|
jgrusewski
|
d243a6f080 |
docs(sp14): spec v2 — critical review corrections
8 corrections from code-anchored critical review at HEAD
|
||
|
jgrusewski
|
eaf4adcb98 |
docs(sp14): spec — aux→Q wire + Earned Gradient Flow pearl
Designs the SP14 chain on top of SP13 Layer B (HEAD
|
||
|
jgrusewski
|
ba83fcd1f5 |
docs(sp13): v3 spec + plan — Hold-pricing replaces Hold-elimination
P0a.T3 v2 implementer's audit revealed `DirectionAction` enum doesn't exist; the codebase uses an 8-variant fused `ExposureLevel` (ShortSmall/Half/Full, Hold, LongSmall/Half/Full, Flat) with cross-crate consumers across 77 files and 32+ test files pinning the 8-variant invariant. Atomic Hold elimination would cascade massively. User insight (2026-05-04): Hold being FREE is the bug, not Hold itself. MFT trading legitimately needs multi-bar holds; we want the model to use them deliberately, not as a CQL-bias lazy default. Holding isn't free in the real world — broker fees, margin interest, opportunity cost. v3 reframes as Hold-pricing: - 4-way action space stays; ExposureLevel::Hold stays; no cross-crate cascade - 3 new ISV slots (380-382): HOLD_COST_INDEX, HOLD_RATE_TARGET_INDEX, HOLD_RATE_OBSERVED_EMA_INDEX - Hold-rate observer: small GPU kernel + Pearls A+D smoothing - Hold-cost controller: 5-line deficit-driven formula (excess > target → cost rises 1×→5× base; observed ≤ target → relax) - Per-bar reward subtraction at action == DIR_HOLD site - 2 GPU oracle tests for the controller P0a.T3 cuts from ~250 LOC + 32-test cascade → ~120 LOC additive. T1+T2 already-staged work unchanged. T4/T5/Layer B/C/D structure preserved. Tension with pearl_event_driven_reward_density_alignment acknowledged in spec — per-bar Hold cost is exposure-NEGATIVE (away from Hold), models real economic carry, ISV-bounded by controller. Inverse of the pearl's failure mode. Faithful reward modeling, not artificial shaping. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
0ca45ef61d |
docs(sp13): v2 spec + plan after critical review
Spec v2 supersedes v1 with five major fixes from the critical review: - Drop alpha-vs-benchmark reward (mathematically tautological — Long trades had alpha = -costs always against always-long benchmark) - Split Phase 0 into 0a (Hold-only, clean test of user hypothesis) + 0b (aux amplification probe, only if 0a partial), avoiding the v1 confounded experiment - Bound direction-skill bonus relative to |alpha| (cap_ratio × |alpha|) to prevent reward gaming on small-alpha correct-direction losers; spec adds 8-quadrant worked-example matrix verifying the no-negative-EV invariant - Replace 5-epoch absolute-threshold gate with 10-epoch trajectory criterion to avoid false-negatives from aux head underconvergence - Aux_w controller adds dual-EMA stagnation detector (decays toward base when no improvement) — prevents permanent destabilization of Q-head in data-limited case Plan v2 mirrors spec changes: - Phase 0a (Hold elimination + dir_acc instrumentation, ~300 LOC, 1 atomic commit) - Phase 0b (aux_w controller replacement, conditional, ~80 LOC) - Layer B (aux head regression -> binary classification, ~120 LOC) - Layer C (skill bonus + luck discount with calibrated bounds, ~150 LOC) - Layer D (30-epoch validation + 3 new pearls) ISV slot allocation [372..380): drops slot 371 (BENCHMARK_PNL_CUMULATIVE), adds 374 (AUX_DIR_ACC_LONG_EMA — stagnation), 379 (SKILL_BONUS_CAP_RATIO). Plan integrates Explore-agent touch-list (50-70 sites) with corrected enum ordering: Short=0, Long=1, Flat=2 (preserves codebase Short-first convention, avoids 30+ stale-comment churn). Adds direction-bias signal handling at experience_kernels.cu:5159 (Hold's 0.5 softening gate vanishes -> [1, 1, 0]). Three new pearls planned for Layer D close-out: - pearl_redefine_success_for_predictive_skill - pearl_skill_bonus_must_be_alpha_bounded (calibration lesson) - pearl_reward_quadrant_audit_required (meta-pearl) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
jgrusewski
|
ecab584c32 |
spec(sp12): per-trade event-driven reward composition (v3)
Three architectural changes in one unified design to push the model from
HFT noise extraction (62% trade rate, sharpe-gaming) toward MFT alpha-hunting:
1. Asymmetric bounded cap (-10/+5) — restores loss aversion erased by
SP11 symmetric cap. 2:1 ratio matches Kahneman/Tversky prospect theory.
Anchor: pearl_audit_unboundedness_for_implicit_asymmetry.
2. Min-hold soft penalty with temperature curriculum — patience requirement
at exit. Soft factor = deficit/(deficit+T), T anneals 50→5 over 50 epochs.
Forces commitment without paralysis in early training.
3. Zero per-bar shaping (gate micro/opp_cost on events) — eliminates
continuous-reward gradient that pulls toward continuous exposure.
Anchor: pearl_event_driven_reward_density_alignment.
Combined: reward fires only on trade events with prospect-theory loss
aversion + commitment requirement. Pure per-trade event-driven Q-learning
properly aligned with per-trade P&L objective.
~50 LOC across 3-4 files. No new ISV slots in Phase 1 (constants only).
Cost ~€1.30 (€0.30 smoke + €1.00 30-epoch validation).
Empirical motivation: train-multi-seed-pmbwn 50-epoch on commit
|
||
|
jgrusewski
|
85069ba75e |
spec(sp11): amend B1b smoke-recovery — z-score normalization for mag-ratio canary
smoke-test-6wd2c on commit |
||
|
jgrusewski
|
9395b983cc |
spec(sp11): fix all 13 review issues — straight-up implementation
Critical bugs fixed:
1. Z-score formula: was mean(Δ)/mean(|Δ|), bounded to [-1,+1] — sigmoid
never saturated, controller stuck in [0.27, 0.73]. Now true Z-score:
delta_ema / sqrt(delta_var_ema) with two-pass var. Renamed canary
slot 351 from VAL_SHARPE_STD_EMA to VAL_SHARPE_VAR_EMA.
2. Component weight renormalization added — Σweights = 1 enforced
post-floor so PopArt's reward-magnitude EMA stays uncontaminated.
3. SABOTEUR_MIN bound violation — engagement-floor (0.1) was silently
pulling output below 0.5 stated minimum. Added post-multiplication
clamp to [SABOTEUR_MIN, SABOTEUR_MAX].
4. ratios[] undeclared — now __shared__ float ratios[6] block-loaded
once from ISV.
5. §3.6 slot count off-by-five (15 → 20). All 20 slots get FoldReset
entries; cold-start window behavior specified explicitly (no NaN path).
Architectural fixes:
6. Q-overconfidence concern addressed in scope — controller's
REWARD_CF_WEIGHT_INDEX covers CQL conservatism. No SP11′ deferral;
if T10 fails, extend controller outputs (e.g., target-update τ).
7. Curiosity recompute-at-replay specified (§3.5.1) — replay buffer
stores base reward only; curiosity added per-tuple at replay time
against current visit-count and current ISV. Eliminates stale-signal
replay contamination that would worsen ep1-overfitting.
Smaller fixes:
8. Novelty signal specified — SimHash 42×16 projection → 16-bit code,
1M-slot per-bucket count table, 1/sqrt(1+count). Hash table lives
in state-reset registry (cleared at fold boundary).
9. Saboteur engagement operationally defined — per-bar
|reward_with_saboteur − reward_without_saboteur| > EPS_ENGAGEMENT,
block tree-reduce, EMA'd. EPS_ENGAGEMENT = 0.01 × PnL_EMA.
10. Duplicate sentence in §7 component-starvation paragraph removed.
11. Validation criteria strengthened (§9): aggregation across 9
trajectories specified; primary metric = median peak-epoch ≥ 10
(baseline median peak-epoch = 1); secondary = drop-from-peak ≤ 5%
by ep20; tertiary = ep20 mean ≥ baseline ep1 mean. §9.3 fix-forward
response codified — no rollback.
12. Phases split per project pattern — Layer A additive (3 commits:
slots, canaries, controller), Layer B atomic consumer migration
(1 commit, including replay-time curiosity), Layer C validation +
close-out. No falsification gate; smoke is validation only.
13. Pearls A+D applied to controller outputs (§3.4.1) — chained
apply_pearls_ad_kernel after controller writes scratch, smoothed
values land in ISV. Consumers read smoothed slots.
Constants surviving (Invariant-1 anchors only, all rate-not-regime):
EPS_DIV, WEIGHT_HARD_FLOOR, SABOTEUR_MIN/MAX, CURIOSITY_PERMANENT_FRACTION,
CURIOSITY_BOUND_FRACTION, WEIGHT_FLOOR_FRACTION, ENGAGEMENT_FLOOR.
Spec is now full straight-up implementation; smoke validates Layer A
infrastructure and Layer B consumers, T10 validates SP11 success metric.
~1550 LOC across 3 commits in Layer A + 1 atomic commit in Layer B +
close-out in Layer C.
|
||
|
jgrusewski
|
d49fbbe4e2 |
spec(sp11): reframe curiosity as feature + add permanent floor
User correction: curiosity is the *fix* for the ep1-peak overfitting pathology, not a hazard to defend against. Reframed §7 from "Risks" to "Design notes" — curiosity bound is a signal-relative scale, not a defensive cap. Fix the contradiction this exposed in the formula: previous `curiosity_pressure = stagnant_or_worse * curiosity_bound` went to zero when improving, which would cancel the always-on exploration the §7 narrative now relies on. Replace with permanent-floor pattern per pearl_blend_formulas_must_have_permanent_floor: curiosity_floor = 0.2 * curiosity_bound (CURIOSITY_PERMANENT_FRACTION) curiosity_dynamic = stagnant_or_worse * curiosity_bound curiosity_pressure = max(curiosity_dynamic, curiosity_floor) Now curiosity is always ≥ 20% of bound (anti-overfitting baseline) and rises toward the bound when stagnant (stagnation breaker). Updated unit-test guidance to assert pressure > 0 even at z=+10. CURIOSITY_PERMANENT_FRACTION=0.2 added to Invariant-1 fraction list. Saboteur-rising-with-improvement reframed as adversarial-load feature rather than over-stress risk. |