trading / confluences / b_dwell

b_dwell — persistence of the break DEAD

Corpus lane — EN-35 · Scored and did not clear its own noise floor.

What it asks

Did the break hold? The bit wants the last two closed 1-minute bars to BOTH close beyond the level in the signal direction.

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

EN-35 persistence-of-break. 1 iff the last 2 CLOSED 1m bars at the
decision BOTH close strictly beyond the candidate's `level` in the signal
direction (long: close > level; short: close < level).

Persistence, not bar size — deliberately distinct from the FDR-dead
`n3-displacement`. Fewer than 2 closed 1m bars, or a non-finite close -> 0.

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 −0.026 R, win-rate delta −0.032, matched p=0.663 (33.7th percentile), q=0.928. It also carries the slate's second-largest fill conditioning in the wrong direction (fills 76.0% with the bit vs 89.0% without), which is the mechanical explanation for why 'wait for confirmation' costs more than it earns here: the trades you confirm your way into are the ones that ran away from your limit. Distinct from the dead n3-displacement by design (persistence, not bar size) — the distinction was honoured and the answer was still no.

Retest path

None. Its 5m sibling b_closeconf was dropped as a tautology before scoring, so the whole close-confirmation family is now answered on this method.

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