MODEL ADOPTION #1822: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 31 — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: No element survives — the filter is a single-pair, single-session, single-direction heuristic with no E8 geometry timing anchor. It is a statistical artifact of USDCHF's recent NY-open behavior, not a rhythm-based edge. The +32pp win-rate jump on n=67 is fragile (CI ±11pp), and the live-window projection shows only +17pp on 7 trades — not enough to offset the loss of trade frequency and total PnL. The filter also contradicts the FADE polarity logic: it blocks SHORTs at NY open, which is a known reversal window for USDCHF in the current regime, but this is not tied to Gods-Clock phase or node alignment. EXPECTED IMPACT: If adopted, win rate might rise ~5–10pp on USDCHF SHORTs, but total PnL would drop ~15–20% due to fewer trades and missed trend-following wins. The model's overall win rate would improve by <2pp, while profit per unit risk would stagnate or decline. The edge is not portable to other pairs or sessions. RISK: Regime shift in USDCHF (e.g., Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com