momentum devandClaude Fable 5 a9aa37c885 backtest: replay the LIVE track only (v1) — shadow research tracks poisoned /backtest ...

replay_window reconstructed fires from ALL setup versions, so liq1/vr1/run1/pm1
(refuted shadow tracks, never traded live, 8:1 volume vs v1, tight-stop
artifacts) dominated /backtest: 17k trades / 45 sessions at -1.8R/trade —
garbage scale vs the harness-validated -0.08R/fire. reconstruct_fires_from_setups
gains an optional setup_version filter (default None: experiments unchanged);
replay_window pins it to v1.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-17 17:22:03 -05:00

..

conversion

conversion(009): committed go/no-go signal probe (Step 5 instrument)

2026-07-14 20:32:18 -04:00

experiments

backtest: replay the LIVE track only (v1) — shadow research tracks poisoned /backtest

2026-07-17 17:22:03 -05:00

ingestion

dilution(016): unbreak nightly EDGAR refresh + pre-register filing-veto experiment

2026-07-17 09:54:49 -05:00

__init__.py

Baseline before Postgres migration (WS0)

2026-06-15 23:39:29 -04:00

attribution.py

Component attribution: per-stage scorecard (CLI + /api/attribution + dashboard + board pulse)

2026-07-02 12:18:57 -04:00

eod_reconcile.py

money-path: nightly cage-count reconcile (broker vs event store) + schedule it

2026-07-13 22:29:00 -04:00

gapper_history.py

delete: dead DDL (10 tables), dead projections, pinned dead code; README/pyproject prune

2026-07-13 21:09:35 -04:00

labeler.py

labeler(009): market context + thin-name RVOL fallback (feature population)

2026-07-14 20:25:07 -04:00

multi_schema.py

Remove DuckDB remnants (datastore is Postgres)

2026-06-18 22:43:29 -04:00

premarket_eval.py

dilution(016): unbreak nightly EDGAR refresh + pre-register filing-veto experiment

2026-07-17 09:54:49 -05:00

query.py

Baseline before Postgres migration (WS0)

2026-06-15 23:39:29 -04:00

regime.py

Regime gate: make the live gate actually decide (it shipped inert) + fix breadth_rvol units

2026-07-16 14:00:07 -05:00

schema.py

Local-data cleanup: archive dead DuckDB relics, rotate logs, fix labels

2026-07-04 15:26:40 -04:00

sip_backfill.py

SIP re-backfill: fix the 2-5% IEX volume distortion across the whole dataset

2026-07-02 13:56:01 -04:00