jgrusewski 29f7e923c6 fix(ml-backtesting): skip queue-decay fill for sentinel-priced market-like orders — ACTUAL root cause of vwap=0/huge sentinels ...

S1.20-S1.22 chased a wrong hypothesis (walk_* deep-level filter) for
3 rounds. The actual bug: resting_orders.cu:344 fills at cost = take *
s.price in the queue-decay maturation arm. Market-like orders seed at
line 644 with sentinel s.price = 1e9 (buy) / 0 (sell), counting on the
marketability check at lines 372-... to fire first via walk_*. But
queue_position initializes to 0 (no book level matches the sentinel),
so on the first same-side trade volume the queue-decay arm fires and
injects the sentinel into cost: buy cost = take * 1e9 -> avg_px =
1e9 -> huge_flat=216, sell cost = take * 0 -> avg_px = 0 ->
zero_flat=194. Same pattern explains flip=9+6.

Fix: detect s.price outside [min_reasonable_px, max_reasonable_px] in
the queue-decay arm; absorb queue_position depletion without filling.
Marketability check fires in the same iteration via walk_* with proper
book prices.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-20 14:03:05 +02:00

..

cuda

fix(ml-backtesting): skip queue-decay fill for sentinel-priced market-like orders — ACTUAL root cause of vwap=0/huge sentinels

2026-05-20 14:03:05 +02:00

src

fix(ml-backtesting): per-level price-range validation in walk_ask_for_buy/walk_bid_for_sell — eliminates sized-but-bad-priced sentinel propagation

2026-05-20 13:49:28 +02:00

tests

diag(ml-backtesting): finer NaN instrumentation — per-vwap-write-site + last-bad-vwap capture

2026-05-20 13:27:03 +02:00

build.rs

feat(ml-backtesting): build.rs + book_update CUDA kernel + sim skeleton

2026-05-18 08:26:53 +02:00

Cargo.toml

test(ml-backtesting): Ring 2 invariant fuzz at N ∈ {1, 16, 256} (C10)

2026-05-18 09:00:49 +02:00