MODEL ADOPTION #1968: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 5 conf — improves win rate from 32 — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — the USDCHF SHORT @ NY_OPEN + conf≥5 filter is a pair-specific, regime-dependent artifact, not an E8-geometry edge. The "5 conf" threshold is arbitrary and not derived from Gods-Clock rhythm logic. EXPECTED IMPACT: If adopted, win rate may rise temporarily (+10–15pp) but total R likely falls due to fewer trades; the +32pp backtest gain is overfit to a USD-strength window that will revert. Net profit impact: neutral-to-negative over 3 months. RISK: (1) Filter blocks high-RR USDCHF shorts during USD weakness, cutting real edge; (2) conf=5 threshold is brittle — conf=4 or 6 may flip results; (3) USDCHF correlation to XAUUSD/GBPUSD losses is coincidental, not causal — removing those losses via a pair filter masks the real risk-off trigger (NY_OPEN + rizzy5m), which remains unaddressed. TEST: Before any reconsideration, run a 60-day replay-bench on the live engine: (a) log all USDCHF SHORT signals at NY_OPEN with conf 3–7, but only Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com