trading / confluences / b_orwcap

b_orwcap — wide-open-day cap DEAD

Corpus lane — RG-17 · Scored and did not clear its own noise floor.

What it asks

Skip days that open wild: the bit is 0 when today's 09:30–09:35 opening-range width exceeds 1.5× the median of the same window over the prior 20 sessions.

Exact definition · verbatim docstring from backtests/conf_lab/bits.py (sha1 5473adbbf694)

RG-17 wide-open-day cap. 1 iff today's 09:30-09:35 ET opening-range
width is <= 1.5 x the median of that SAME window's width over the prior 20
RTH sessions.

Width = max high - min low over CLOSED 1m bars whose OPEN time-of-day is in
[09:30, 09:35). Prior sessions are days strictly before the decision day
that have a non-empty window; the last 20 of them form the median and at
least 10 are required. If the decision instant is before 09:35 ET (the
window has not fully closed) or today's window has no bars -> 0.

NOT the FDR-dead `n1-narrowOR`: that bit rewarded narrowness; this one only
excludes the extreme wide tail. Multiple 1.5 and lookback 20 fixed a priori.

Fixed parameters & provenance

Every parameter below was fixed in the design document before any candidate value was computed. No sweep, no tuning: a bit that needs tuning to pass has failed.

Screen analytics — screen-2026-08-07

Conditional association on mean solo R, stratified on the count of the OTHER live bits, against a per-bit prevalence-matched null (50,000 i.i.d. Bernoulli draws at this bit's own prevalence, scored on its own strata). Population: 2,882 candidates, 2,289 filled, MES, 2019-06-04 → 2026-07-31.

Per era · reported separately, never pooled into a verdict — each cell is a smaller sample than the headline

Funnel & fill conditioning · a bit that mostly predicts whether a limit FILLS is not the same discovery as a bit that predicts whether a trade WINS

Novelty vs the six live bits · high agreement means the bit is mostly restating a gate that is already in the stack

By stratum — does it work where the method actually trades? · the live A/B take rule is count >= 4, so the count>=4 rows are the only ones that could change a live trade

Status — DEAD

NEGATIVE: pooled −0.045 R, matched p=0.546 (45.4th percentile), q=0.874. It was carefully built NOT to be the FDR-dead n1-narrowOR — that bit rewarded narrowness, this one only excludes the extreme wide tail — and it still found nothing. Prevalence 0.832 means it is a rarely-binding cap, which is consistent with an effect this small.

Retest path

None. The neighbouring mechanism (opening-range width as a signal) is already on the do-not-retest list via n1-narrowOR; this was the last legitimate variant of it and it is spent.

Standing caveats

• Fill model optimistic: touch fills, zero net slippage, entry-bar SL/TP not checked inside the fill minute.
• Not a holdout — 2019-2026 was selected on, tuned on and reported on before this lab existed. A good number here means 'worth pre-registering', nothing more.
• MES only; the P1 edge is MES-centric and recent-regime.
• Masters miss four Sunday-evening blocks (May-Jun 2026); data ends 2026-07-31.
• Mean solo R is an average per candidate. The solo ledger is not a book and is never summed (PROTOCOL.md §0).
• Per-era cells are reported separately and are NOT pooled into a verdict; each is a smaller sample than the headline.
• Nothing on this page is TV-verified. A backtest number becomes actionable only after an independent TradingView Pine port reproduces entries AND per-trade PnL on a Deep Backtest export.
• Screening is not certification. Promotion requires all seven PROTOCOL gates, ending in a forward paired evaluation and a Pine referee.

← all confluences