jgrusewski c0327ab319 feat: wire self-improving enrichments into epoch boundary + smoke test ...

Post-validation enrichment: extract eval trades from WindowMetrics,
run all 8 enrichments, apply adaptive epsilon + gamma + agreement
threshold. Smoke test verifies enrichment runs at least once.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-16 17:45:52 +02:00

..

dqn

feat: wire self-improving enrichments into epoch boundary + smoke test

2026-04-16 17:45:52 +02:00

tft

fix: wire real GPU backprop + SPSA gradients, fix checkpoint loading, eliminate candle from examples

2026-03-20 15:41:42 +01:00

curriculum.rs

fix: update 5 ml tests for 7-level ExposureLevel

2026-04-11 12:21:52 +02:00

liquid.rs

fix: wire real GPU backprop + SPSA gradients, fix checkpoint loading, eliminate candle from examples

2026-03-20 15:41:42 +01:00

mamba2.rs

fix: wire real GPU backprop + SPSA gradients, fix checkpoint loading, eliminate candle from examples

2026-03-20 15:41:42 +01:00

mod.rs

refactor(ml): eliminate candle from all 104 src files

2026-03-18 00:24:35 +01:00

online_learning.rs

fix(ml): migrate all test code to GPU types — 125 compile errors fixed

2026-03-18 14:47:33 +01:00

ppo.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

tft_parquet.rs

audit: annotate all remaining to_vec/memcpy_dtoh — categorized 158 sites

2026-03-18 19:36:41 +01:00

tlob.rs

refactor: rename all bf16 transfer functions → f32 across 19 files, delete legacy aliases

2026-04-10 18:11:50 +02:00

validation_metrics.rs

refactor: restructure repo — crates/, bin/, testing/ layout

2026-02-25 11:56:00 +01:00