gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 4336a71e26 feat(surfer): diversifier hunt — no robust partner (TS-trend real but stale) jgrusewski 2026-06-06 16:24:55 +02:00
  • 99b747ad2c feat(surfer): turnover optimization resolves capacity — deployable momentum spec jgrusewski 2026-06-06 16:20:12 +02:00
  • a2cbed4a83 feat(surfer): capstone — low-vol fails battery; momentum is small-capacity jgrusewski 2026-06-06 16:17:33 +02:00
  • 7edeec9106 feat(surfer): proper (a)robust-construction + (b)diversifier research jgrusewski 2026-06-06 16:12:55 +02:00
  • ca3877c328 feat(surfer): execution-realism stress — honest momentum magnitude ~0.4-0.6 jgrusewski 2026-06-06 16:07:31 +02:00
  • 7495eaa286 feat(surfer): point-in-time survivorship test PASSED — momentum is real jgrusewski 2026-06-06 16:04:19 +02:00
  • 0d6d58428d feat(surfer): momentum robustness battery — crypto XS momentum is a robust real edge jgrusewski 2026-06-06 15:18:59 +02:00
  • 0f1a04d16d fix(surfer): universe-robustness exposes carry as cherry-picked; momentum is robust jgrusewski 2026-06-06 15:16:56 +02:00
  • af5e6d523b feat(surfer): broaden crypto sweep + regime/cost robustness — carry crash found jgrusewski 2026-06-06 15:10:40 +02:00
  • cb402ab81f feat(surfer): crypto carry+momentum sweep — FIRST real edge (funding carry) jgrusewski 2026-06-06 15:05:20 +02:00
  • 1283812c54 feat(surfer): deflated signal-sweep engine + Batch 1 (futures factor zoo = null) jgrusewski 2026-06-06 14:54:06 +02:00
  • 1cf38232e8 fix(surfer): full-16y MFT settle — regime-adaptive surfer significantly negative jgrusewski 2026-06-06 12:15:37 +02:00
  • fa700c7b5f feat(surfer): MFT regime-adaptive quality test (intraday, GPU, 4GB-safe) jgrusewski 2026-06-06 10:08:16 +02:00
  • 2bb2b50fd1 fix(surfer): correct roll handling (held-contract return stitching) + cost stress + dual gates jgrusewski 2026-06-06 01:43:06 +02:00
  • 8df1c7eea2 feat(surfer): Phase 0 GPU floor + validation harness — first real (weak) OOS trend edge jgrusewski 2026-06-06 01:31:37 +02:00
  • e07c409950 revise(surfer): Phase 0 to CUDA-only per foxhunt architecture (CPU read-only) jgrusewski 2026-06-05 21:23:15 +02:00
  • 565511c5f5 plan(surfer): Phase 0 — diversified-trend floor + validation harness jgrusewski 2026-06-05 21:08:44 +02:00
  • ce13a72ba1 docs(surfer): design spec — the surfer over an uncorrelated universe jgrusewski 2026-06-05 21:05:57 +02:00
  • 44cbeef321 feat(scripts): cross-asset trend/lead-lag harness (6E/ES/NQ/ZN OHLCV) ml-alpha-regime-observer jgrusewski 2026-06-05 20:39:31 +02:00
  • 292147090f feat(scripts): lower-frequency directional IC harness (intraday + daily + backtest) jgrusewski 2026-06-05 19:58:18 +02:00
  • 343e90af54 feat(scripts): queue-aware passive-MM fill model (decisive viability test) jgrusewski 2026-06-05 19:28:05 +02:00
  • f6745400ef feat(scripts): passive market-making markout/adverse-selection harness jgrusewski 2026-06-05 19:21:30 +02:00
  • 7b33533bc8 feat(scripts): OFI information-coefficient signal-validation harness jgrusewski 2026-06-05 19:14:26 +02:00
  • fa3f723983 docs: Phase A verdict — RA-G1 PASS, RA-G3 starvation-limited on clean data; proceed to D2 jgrusewski 2026-06-05 18:35:52 +02:00
  • 6df3284d0d fix(data): MBP-10 decoder corrupted the inside quote (level 0) jgrusewski 2026-06-05 14:48:05 +02:00
  • 31f858b5ea docs(superpowers): edge investigation decision record + F4-gating/reward-alignment specs & plans jgrusewski 2026-06-05 12:59:19 +02:00
  • e57b076577 feat(scripts): reward-pnl alignment measurement harness (RA-G3 gate) jgrusewski 2026-06-05 09:23:29 +02:00
  • d8447475c9 feat(ml-alpha): Phase A — surfer-scaffold force-pin (slot 824 + kernel gate + env flag + diag) jgrusewski 2026-06-05 09:18:39 +02:00
  • 7376b1c670 feat(ml-alpha): Phase 7b F5 engagement — bootstrap RL_F5_STATE_MASK_ENABLED to 1.0 jgrusewski 2026-06-05 01:47:01 +02:00
  • e82049c779 feat(ml-alpha): Phase 7b F5 Option A — gate-aware Hold suppression for confidence + FRD gates jgrusewski 2026-06-05 01:28:32 +02:00
  • 9ea7692abd feat(ml-alpha): Phase 7b F5 — state-conditional action availability mask jgrusewski 2026-06-05 01:00:01 +02:00
  • 43e7b6383b feat(ml-alpha): Phase 7a F2 — Q-centered hinged-advantage distill target wired jgrusewski 2026-06-04 23:59:39 +02:00
  • f788da862a feat(ml-alpha): Phase 7a Task 1.5 — comprehensive F2 diagnostic emissions (13 fields) jgrusewski 2026-06-04 23:43:39 +02:00
  • 66a6db89b3 feat(ml-alpha): Phase 7a F2 — allocate ISV slots 817-818 for Q-centered distill target jgrusewski 2026-06-04 23:11:21 +02:00
  • 0463e44e0c feat(ml-alpha): Phase 5 — trail-max + MTM reward + entropy formula fix jgrusewski 2026-06-04 17:04:17 +02:00
  • f593b1e617 feat(infra): plumb FOXHUNT_BAND_ENABLED through alpha-rl template jgrusewski 2026-06-04 09:05:25 +02:00
  • 65c328d3f1 fix(ml-alpha): Phase 4-A3 — band position-zero exception (opens-from-flat allowed) jgrusewski 2026-06-04 09:03:01 +02:00
  • 1c23ff368a feat(ml-alpha): Phase 4-A2 — band exploration bypass (slot 813) jgrusewski 2026-06-04 08:17:28 +02:00
  • 552d91bf45 feat(ml-alpha): Tier 3 Phase 4-B — Band turnover controller + backward chain wiring jgrusewski 2026-06-04 01:41:45 +02:00
  • e41a732081 feat(ml-alpha): Phase 4-A — No-transaction-band foundation (ISV slot 799 gate) jgrusewski 2026-06-04 00:50:27 +02:00
  • bd811a7748 feat(ml-alpha): Phase 3D — three-intervention overtrading fix (A+B+C) jgrusewski 2026-06-03 23:31:29 +02:00
  • 17e453a1d5 fix(ml-alpha): gate rl_popart_v_correct by slot 793 (Phase 3B-Y companion fix) jgrusewski 2026-06-03 22:06:55 +02:00
  • 093feac3da feat(ml-alpha): Phase 3B+Y — reward-pnl alignment foundation jgrusewski 2026-06-03 21:37:38 +02:00
  • c5036af030 feat(infra): plumb FOXHUNT_USE_MULTI_HEAD_POLICY through alpha-rl template jgrusewski 2026-06-03 16:46:33 +02:00
  • c8c81ab7e4 feat(ml-alpha): Phase 2A-D B1.3 — adaptive gate LR controller jgrusewski 2026-06-03 16:35:29 +02:00
  • 6f3639bfbf feat(ml-alpha): Phase 2A-D B1 — gate LR multiplier (ISV slot 790) jgrusewski 2026-06-03 13:49:20 +02:00
  • 5f10bcde3a feat(ml-alpha): Phase 2A-C+ — device-aggregated gate diag jgrusewski 2026-06-03 12:15:39 +02:00
  • 3e36f4a0e6 feat(ml-alpha): Phase 2A-C — trainer integration behind FOXHUNT_USE_MULTI_HEAD_POLICY flag jgrusewski 2026-06-03 11:07:27 +02:00
  • e22da61cf8 feat(ml-alpha): Phase 2A-B — MultiHeadPolicy backward + aux KL prior jgrusewski 2026-06-03 09:51:55 +02:00
  • 0b3e401500 feat(ml-alpha): Phase 2A-A — MultiHeadPolicy foundation (inert) jgrusewski 2026-06-03 01:41:57 +02:00
  • 779c03b9d7 feat(ml-alpha): Phase 1B-B — rollout collection loop + GAE behind FOXHUNT_USE_ROLLOUT flag jgrusewski 2026-06-02 22:42:39 +02:00
  • 969caf26c3 docs(ml-alpha): spec + plan for Phase 1B trainer rollout-buffer + GAE refactor jgrusewski 2026-06-02 22:10:16 +02:00
  • 5cd2f87039 feat(ml-alpha): Phase 1B-A — RolloutBuffer + GAE kernel foundation jgrusewski 2026-06-02 22:09:47 +02:00
  • cfaa420bd4 fix(ml-alpha): Phase 0 — per-step authoritative USD pnl in diag + fix mislabeled fields jgrusewski 2026-06-02 19:55:31 +02:00
  • 629ebd667c feat(ml-alpha): deterministic same-seed training + Tier 1.5 fast-dev-cycle jgrusewski 2026-06-02 17:56:00 +02:00
  • 63fc16f173 fix(rl): surfer-scaffold v5.2 — drop wr_excess clamp, full scaffold when novice jgrusewski 2026-06-02 00:34:03 +02:00
  • 4a4953b01f fix(rl): surfer-scaffold v5.1 — decay re-engagement requires EXCESS alertedness jgrusewski 2026-06-02 00:22:23 +02:00
  • 38a4aa15b3 feat(rl): adaptive surfer-scaffold reward shaping (spec v5 A+B combined) jgrusewski 2026-06-01 23:52:14 +02:00
  • fa347e4812 feat(rl): reward-policy alignment — pure-pnl mode default (spec 2026-06-01) jgrusewski 2026-06-01 22:38:47 +02:00
  • b45c2fb108 fix(rl): edge-decay PH — flip sign for downside detection jgrusewski 2026-06-01 21:36:46 +02:00
  • 34806b6b62 diag(rl): edge-decay detector Phase 1 — Page-Hinkley on per-trade EV jgrusewski 2026-06-01 21:04:47 +02:00
  • a5e0d00794 diag(rl): CMDP fleet-fraction observability — 4 new ISV slots jgrusewski 2026-06-01 16:53:06 +02:00
  • 251b871294 fix(build): ml-backtesting honors CUDA_COMPUTE_CAP for sm_90 on H100 ml-alpha-dd049d9a4-eval-fix jgrusewski 2026-06-01 11:00:53 +02:00
  • b7bbb700f8 fix(rl): eval_summary aggregates across all b_size accounts (E.4-E.5) jgrusewski 2026-05-31 18:09:16 +02:00
  • 84caa99b65 feat(lobsim): per-backtest trade-count read + 4× TRADE_LOG_CAP (E.1-E.3) jgrusewski 2026-05-31 18:01:16 +02:00
  • f428be794b Revert "feat(rl): B-11-β Q-distill informativeness gate" jgrusewski 2026-06-01 14:57:41 +02:00
  • b93971726d feat(rl): B-11-β Q-distill informativeness gate jgrusewski 2026-06-01 13:00:06 +02:00
  • c1dc84a345 fix(rl): B-10 wire G1 Q-distribution launch into step_with_lobsim_gpu jgrusewski 2026-06-01 12:25:47 +02:00
  • 8c7ce02da9 feat(rl): B-10 policy-quality cascade diagnostic jgrusewski 2026-06-01 12:20:42 +02:00
  • 033906f213 docs(rl): fix stale C51 V_MAX/V_MIN "ratchet" claims + B-9 test bug jgrusewski 2026-06-01 11:31:31 +02:00
  • 87a8259c6e fix(build): ml-backtesting honors CUDA_COMPUTE_CAP for sm_90 on H100 jgrusewski 2026-06-01 11:00:53 +02:00
  • 29b5acad55 feat(rl): B-9 C51 Bellman-target saturation observability jgrusewski 2026-06-01 10:31:18 +02:00
  • 1739d9c173 feat(rl): B-8 popart σ_welford disaggregation + identity invariant jgrusewski 2026-06-01 10:15:36 +02:00
  • 55d049ecf4 feat(rl): B-7 ISV-toggle reward clamp (default disabled) jgrusewski 2026-06-01 10:05:59 +02:00
  • 912f33c6fc test(rl): B-6 invariant regression test — asymmetric Wiener-α / Bayesian shrinkage jgrusewski 2026-06-01 01:19:52 +02:00
  • bc9eaac89d fix(rl): B-6 — ISV-driven adaptive asymmetric Wiener-α (Bayesian shrinkage) jgrusewski 2026-06-01 01:13:27 +02:00
  • d725b77031 fix(rl): B-5 — asymmetric Wiener-α replaces B-4 caps (math gap fix) jgrusewski 2026-06-01 00:57:58 +02:00
  • cbe4869375 fix(rl): B-4 — extend Winsorization rate-cap to Kelly input EMAs jgrusewski 2026-06-01 00:32:06 +02:00
  • 42b4898239 fix(rl): B-3 — Kelly fractional-trust schedule + avg_win/loss cold-start jgrusewski 2026-05-31 23:35:20 +02:00
  • 16cf9f260c fix(rl): B-2 — pos_max_ema cold-start cascade eliminated, ISV-driven cap jgrusewski 2026-05-31 23:09:59 +02:00
  • 1aa92f57f0 fix(rl): eval-boundary addendum — reward_scale warmed_flag + pos_max_ema rate-cap jgrusewski 2026-05-31 22:25:24 +02:00
  • 72684ed3ef fix(rl): preserve normalization EMAs across eval boundary jgrusewski 2026-05-31 21:10:59 +02:00
  • 22e6ddbcac fix(rl): eval_summary aggregates across all b_size accounts (E.4-E.5) jgrusewski 2026-05-31 18:09:16 +02:00
  • fa0858f0b1 feat(lobsim): per-backtest trade-count read + 4× TRADE_LOG_CAP (E.1-E.3) jgrusewski 2026-05-31 18:01:16 +02:00
  • ad16e9d941 fix(trainer): address Phase A code review minors (8 fixes) jgrusewski 2026-05-31 17:49:23 +02:00
  • 210794626a feat(rl): emit eval-phase per-step diag to eval_diag.jsonl jgrusewski 2026-05-31 17:26:21 +02:00
  • 8a93a77adc refactor(trainer): extract json!{} into IntegratedTrainer::build_diag_value jgrusewski 2026-05-31 17:25:47 +02:00
  • 13d8ed76da docs: checkpoints + eval-diag spec + plans (v1 superseded by v2) jgrusewski 2026-05-31 16:57:43 +02:00
  • 7b3309edcc fix(rl): eliminate atomicAdd in PPO+DQN loss reduction (F4.1) jgrusewski 2026-05-31 14:40:58 +02:00
  • 30982963ef feat(rl): IQN τ tail-recency consumer + G24/G25 invariants (F5) jgrusewski 2026-05-31 12:59:48 +02:00
  • 6dacde95ef feat(rl): popart per-account max-magnitude envelope (F4) — Problem 3 fix jgrusewski 2026-05-31 12:50:31 +02:00
  • cfe40f2f3f test(rl): G10-G12 back-compat + G15-G21 Kelly resurrection (F2.3+F2.4) jgrusewski 2026-05-31 12:42:16 +02:00
  • ad05ffeb2a feat(rl): Kelly resurrection override (F2) — Problem 1 fix jgrusewski 2026-05-31 12:33:13 +02:00
  • bf214d1a09 refactor(rl): v9 slot rename — RL_EVAL_WARMUP_* → RL_REGIME_TRANSITION_* (F3) jgrusewski 2026-05-31 12:26:54 +02:00
  • b09feaf9e4 feat(rl): regime_observer diag emit (F1.8) jgrusewski 2026-05-31 12:17:13 +02:00
  • 0a9ff73b1f feat(rl): reset_session_state regime boundary policy (F1.7) jgrusewski 2026-05-31 12:15:34 +02:00
  • 67f862191f feat(rl): regime_observer bootstrap entries (F1.6) — array 179→199 jgrusewski 2026-05-31 12:14:30 +02:00
  • 9e97c2acaf feat(rl): wire regime_observer into step_with_lobsim_reward_and_train (F1.5) jgrusewski 2026-05-31 12:12:46 +02:00
  • 79b8a43491 style(rl): F1.4 code review fixes — borrow + naming + format jgrusewski 2026-05-31 12:11:02 +02:00
  • 6e0c9abff2 feat(rl): regime_observer trainer wiring — loaders + struct + launchers (F1.4) jgrusewski 2026-05-31 12:05:49 +02:00