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>

2026-05-16 20:27:25 +02:00

..

2026-03-10-zero-cpu-hotpath-design.md

…

2026-03-11-dqn-factored-actions-design.md

…

2026-03-13-gpu-test-workflow-design.md

…

2026-03-14-kanidm-sso-design.md

…

2026-03-15-fused-cuda-training-design.md

…

2026-03-21-h100-epoch-optimization-design.md

…

2026-03-21-h100-epoch-optimization-phase3-design.md

…

2026-03-21-training-profiles-design.md

…

2026-03-22-gpu-composite-reward-design.md

…

2026-03-22-gpu-segment-tree-design.md

…

2026-03-22-two-phase-hyperopt-design.md

…

2026-03-23-9-exposure-action-space-design.md

…

2026-03-23-dual-distributional-c51-iqn-design.md

diag+docs(dqn): trunk-slice grad decomposition + stale IQN-trunk doc fix

2026-04-22 22:03:20 +02:00

2026-03-23-profitability-roadmap.md

…

2026-03-23-trading-realism-conformance.md

…

2026-03-25-boundary-trade-counting-design.md

…

2026-03-25-trade-lifecycle-fix-design.md

…

2026-03-26-eval-cleanup-design.md

…

2026-03-27-bf16-performance-design.md

…

2026-03-27-bug-fixes-design.md

…

2026-03-27-code-hygiene-design.md

…

2026-03-27-full-bf16-rewrite-design.md

…

2026-03-31-feature-precompute-pipeline-design.md

…

2026-04-01-h100-gpu-optimization-design.md

…

2026-04-04-c51-loss-accumulator-fix-design.md

…

2026-04-04-cuda-kernel-safety-design.md

…

2026-04-04-feature-extraction-pipeline-fix-design.md

…

2026-04-04-gpu-test-fixes-design.md

…

2026-04-04-q-value-explosion-investigation.md

…

2026-04-04-training-step-performance-design.md

…

2026-04-05-gpu-regime-and-training-hang-fix.md

…

2026-04-06-gpu-native-validation-design.md

…

2026-04-06-h100-maximum-performance.md

…

2026-04-06-per-prefix-sum-design.md

…

2026-04-06-per-tree-fix-and-zero-sync-readback.md

…

2026-04-07-f32-backtest-pipeline-design.md

…

2026-04-07-reward-v7-design.md

…

2026-04-07-reward-v8-master-plan.md

…

2026-04-07-reward-v71-fixes-design.md

…

2026-04-08-advantage-standardization-design.md

…

2026-04-08-h100-epoch-optimization-v2.md

…

2026-04-08-h100-graph-optimizations.md

…

2026-04-08-hierarchical-4branch-design.md

…

2026-04-08-per-branch-loss-weighting-design.md

…

2026-04-08-volume-bar-pipeline-design.md

…

2026-04-10-argo-training-pipeline-redesign.md

…

2026-04-10-dead-code-cleanup-gpu-profiling.md

…

2026-04-11-autonomous-branch-intelligence-design.md

…

2026-04-11-candle-varstore-elimination.md

…

2026-04-13-deterministic-forward-design.md

…

2026-04-13-iql-full-integration-design.md

…

2026-04-13-iql-h100-hardening-design.md

…

2026-04-13-single-cublas-handle-design.md

…

2026-04-14-adaptive-training-dynamics-design.md

…

2026-04-14-cross-pollinated-branch-intelligence-design.md

…

2026-04-14-direction-conditioned-magnitude-design.md

…

2026-04-15-oos-generalization-enhancement-design.md

…

2026-04-15-oos-performance-enhancement-design.md

…

2026-04-15-supervised-architecture-transfer-design.md

…

2026-04-16-homeostatic-regularization-design.md

spec: trade-level reward attribution + exploration risk budget + homeostatic regularization

2026-04-16 01:24:03 +02:00

2026-04-16-introspective-state-vector-design.md

spec: Phase 4 adaptive minimum hold time — prevent coin-flip exits

2026-04-16 23:51:45 +02:00

2026-04-16-learned-risk-management-design.md

feat: trade-level reward attribution + learned risk management spec

2026-04-16 01:29:11 +02:00

2026-04-16-self-improving-training-loop-design.md

spec: Self-Improving Training Loop — 9 enrichments, eval-as-training

2026-04-16 17:30:01 +02:00

2026-04-16-tick-microstructure-intelligence-design.md

spec: fix 4 critical issues from review — OFI_DIM cascade, deploy atomicity

2026-04-16 23:43:55 +02:00

2026-04-16-trade-level-reward-exploration-design.md

spec: trade-level reward attribution + exploration risk budget + homeostatic regularization

2026-04-16 01:24:03 +02:00

2026-04-16-trade-plan-head-design.md

spec: Plan Phase 2 — 6 pearls/gems/novels for adaptive planning

2026-04-17 09:01:53 +02:00

2026-04-16-training-environment-alignment-design.md

spec: adapt components instead of removing — DSR on trade P&L, rank non-zeros only

2026-04-16 21:44:35 +02:00

2026-04-17-unified-cublas-training-graph-design.md

docs: update unified graph spec with Phase 1 H100 measurements

2026-04-18 14:59:57 +02:00

2026-04-18-multi-stream-phase2-design.md

spec: Phase 2 multi-stream parallelism design

2026-04-18 16:03:45 +02:00

2026-04-18-true-single-graph-design.md

spec: true single-graph — zero CPU on hot path, zero ungraphed launches

2026-04-18 23:59:35 +02:00

2026-04-18-unified-single-graph-design.md

spec: add Phase 3 performance optimizations (8 items, prioritized)

2026-04-18 22:04:41 +02:00

2026-04-19-kernel-optimization-design.md

spec: kernel optimization — cuBLAS projections + batch-parallel scans

2026-04-19 12:10:49 +02:00

2026-04-19-ofi-momentum-dense-reward-design.md

feat: target_dim 4→6 + spec v5 with pearls (bar duration, book CoM, retrospective hold)

2026-04-19 23:47:04 +02:00

2026-04-20-adaptive-learning-dynamics-design.md

spec: review fixes — labels, dedup, P2 as 7th component, WinRate 55%

2026-04-20 18:58:35 +02:00

2026-04-20-bitonic-sort-integration-design.md

feat: wire config weights to kernel + revert C51 alpha + atom warm-start spec

2026-04-20 08:51:42 +02:00

2026-04-20-data-pipeline-gaps-design.md

cleanup: remove legacy Sequential q_network + tune config for dense reward

2026-04-20 08:17:34 +02:00

2026-04-20-dqn-cleanup-ralph-loop-design.md

docs(cleanup): ralph-loop prompt + scoreboard for DQN code cleanup sweep

2026-04-20 22:03:14 +02:00

2026-04-20-unified-state-layout-design.md

spec: unified state layout — fix train/validation mismatch

2026-04-20 14:29:53 +02:00

2026-04-21-phase1-reward-inventory.md

diag+gate: TD-propagation smoke test + entropy→plasticity gate + tx_cost doc

2026-04-21 02:05:28 +02:00

2026-04-21-policy-quality-baseline-metrics.md

docs(policy-quality): Task 0.17 baseline metrics — captured (Phase 0 complete)

2026-04-22 08:42:50 +02:00

2026-04-21-policy-quality-design.md

docs(policy-quality): main-branch workflow — cut feat/wip branches

2026-04-21 21:06:33 +02:00

2026-04-21-policy-quality-task2x-scoping.md

docs(policy-quality): Task 2.X scoping — per-bin variance + Q-spread regularization

2026-04-22 11:43:17 +02:00

2026-04-21-policy-quality-track1-triage.md

docs(policy-quality): Track 1 magnitude triage (Phase 1) — H4 + H10 CONFIRMED

2026-04-22 08:51:51 +02:00

2026-04-21-policy-quality-track2-triage.md

cleanup+fix(reward): Task 2.4 R6 relocation + Task 2.5 Bug #6 docstring

2026-04-22 16:56:36 +02:00

2026-04-21-policy-quality-track3-triage.md

docs(policy-quality): Track 3 controllers audit (Phase 1) — 0 load-bearing, 6 diagnostic, 1 candidate-for-delete

2026-04-22 09:09:09 +02:00

2026-04-21-policy-quality-track4-triage.md

docs(policy-quality): Track 2 reward audit (Phase 1) — 2 DELETE, 3 KEEP

2026-04-22 09:06:50 +02:00

2026-04-21-unified-train-val-env-design.md

phase3(env-unification): full unification — all 3 kernels now call unified_env_step_core

2026-04-21 11:04:51 +02:00

2026-04-23-isv-signal-quality-audit.md

docs(isv): signal quality audit for DQN ISV bus — L40S oscillation diagnosis

2026-04-23 10:15:16 +02:00

2026-04-23-isv-v-range-unification.md

feat(dqn): ISV-unified per-branch Q-support range (spec 2026-04-23)

2026-04-23 21:18:19 +02:00

2026-04-23-tlob-feature-integration.md

docs(tlob): feature-diff doc for TLOB 51 vs OFI 20 — Phase A

2026-04-23 09:12:01 +02:00

2026-04-24-dqn-v2-unified-design.md

spec(dqn-v2): D.8 TLOB pivot — cuBLAS port using existing DQN infra, no ONNX, no pretraining

2026-04-24 21:03:57 +02:00

2026-04-26-distributional-rl-aggregation-design.md

spec(dqn): Plan C Phase 2 ACTIVE — UCB asymmetry regression triggers Thompson resumption

2026-04-29 16:02:53 +02:00

2026-04-27-moe-regime-redesign-design.md

spec+plan(moe): correct gate input dim 42 → STATE_DIM=128

2026-04-27 18:22:40 +02:00

2026-04-29-numerical-stability-investigation-design.md

spec(dqn): SP1 numerical stability — revise per critical review

2026-04-29 22:59:00 +02:00

2026-04-29-numerical-stability-sp2-sp3-design.md

spec(dqn): SP2 + SP3 combined — F0 regression fix + Q-learning structural stability

2026-04-30 08:36:32 +02:00

2026-04-30-sp4-signal-driven-magnitude-control-design.md

fix(sp4): migrate fast/slow grad-norm EMA update to GPU per feedback_no_cpu_compute_strict

2026-05-01 14:07:10 +02:00

2026-05-01-sp5-magnitude-differentiation-and-eval-collapse-design.md

docs(sp5): remove duplicate Layer A close-out section (superseded by Layer D)

2026-05-01 19:54:02 +02:00

2026-05-02-sp6-per-branch-consumer-infrastructure-refactor.md

docs(sp6): brainstorm spec — per-branch consumer infrastructure refactor

2026-05-02 01:36:48 +02:00

2026-05-03-sp7-loss-balance-controller-design.md

spec(sp7): v2 — flatness-gated targets + Wiener α + sentinel-bootstrap

2026-05-03 00:11:26 +02:00

2026-05-03-sp9-kelly-cold-start-isv-driven.md

spec(sp9): Kelly cold-start warmup floor — fully ISV-driven design

2026-05-03 20:33:36 +02:00

2026-05-03-sp10-unconditional-thompson-selector-isv-temperature.md

spec(sp10): unconditional Thompson selector + ISV-driven temperature

2026-05-03 22:24:14 +02:00

2026-05-04-sp11-reward-as-controlled-subsystem.md

spec(sp11): amend B1b smoke-recovery — z-score normalization for mag-ratio canary

2026-05-04 11:30:52 +02:00

2026-05-04-sp12-quality-over-quantity-reward-shaping.md

spec(sp12): per-trade event-driven reward composition (v3)

2026-05-04 18:41:57 +02:00

2026-05-04-sp13-redefine-success-for-predictive-skill.md

docs(sp13): v3 spec + plan — Hold-pricing replaces Hold-elimination

2026-05-04 23:18:58 +02:00

2026-05-05-sp14-aux-q-wire-earned-gradient-flow.md

docs(sp14): spec v3 — K=4 direction + ISV-adaptive β rate limiter

2026-05-05 17:21:17 +02:00

2026-05-06-trader-discipline-and-recovery-design.md

docs(sp15): amend spec v2 — 10 fixes from second critical review

2026-05-06 08:58:28 +02:00

2026-05-08-sp18-reward-shape-hold-attractor-design.md

docs(sp18): copy spec + plan to feat/sp18-combined branch

2026-05-09 00:25:06 +02:00

2026-05-09-sp19-20-wr-first-design.md

feat(sp20): Phase 1.4 (Path C) — kernel-arg refactor + aggregation kernel + wire-up

2026-05-09 20:49:07 +02:00

2026-05-10-foxhunt-specialized-agents-design.md

docs(claude): foxhunt-aware agents & skills design — phase 1 (12 items)

2026-05-10 22:19:28 +02:00

2026-05-15-mamba2-grn-integration-notes.md

docs(phase-e-4-a): mamba2 + grn integration research — use ml-alpha Mamba2Block

2026-05-15 20:32:47 +02:00

2026-05-15-phase-e-temporal-encoder-design.md

docs(phase-e): E.4 temporal encoder design + E.4.A implementation plan

2026-05-15 20:42:35 +02:00

2026-05-15-t10-mamba2-backward-from-h-enriched.md

docs(phase-e-4-a): execution status + T10 backward_from_h_enriched patch sketch

2026-05-15 22:08:31 +02:00

2026-05-16-ml-alpha-cfc-ppo-design.md

spec(ml-alpha): GPU/CPU contract, CUDA Graphs, cold-start, disconnect handling

2026-05-16 20:27:25 +02:00