trading / confluences / b_adx

b_adx — Wilder ADX(14) trend-strength floor DEAD

Corpus lane — RG-23 · Scored and did not clear its own noise floor.

What it asks

Is there enough trend strength to bother? The bit wants ADX(14) on closed 5m bars at or above 20.

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

RG-23 trend-strength floor. 1 iff Wilder ADX(14) on CLOSED 5m bars at
the decision is >= 20.

Textbook Wilder construction, recomputed here through the restricted view:
TR / +DM / -DM per closed bar, Wilder-smoothed over 14 (first value = the
14-sum, then `prev - prev/14 + current`), +DI/-DI, DX = 100*|+DI - -DI| /
(+DI + -DI), and ADX = the Wilder smoothing of DX over 14 (first value =
the mean of the first 14 DX). Reads `view.history("m5", n=400)`.

Fixed a priori in SCREEN-2026-08-07-DESIGN.md §A.1: period 14, threshold 20
(the sources say "20-25"; 25 is NOT tested — one value, no sweep).
Fewer than 3*14+1 = 43 usable bars, or any non-finite intermediate -> 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 −0.051 R, win-rate delta −0.025, matched p=0.412 (58.8th percentile — squarely inside its own null), q=0.824. Worth stating what was NOT done: sources say '20–25' and only 20 was fixed a priori. 25 was never tested and will not be, because testing the second value after seeing the first fail is the definition of the sweep the design forbids.

Retest path

None on this data. A trend-strength gate is not refuted in general — one fixed parameterisation of it, on one method, on one instrument, failed to separate from noise.

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