MODEL ADOPTION #931: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 6 conf — improves win rate from 31 — E8 Intelligence Research

DECISION: REJECT ELEMENT: The filter "USDCHF SHORT @ NY_OPEN with 6 conf" is not compatible with E8 geometry timing. NY_OPEN is a fixed calendar event, not a rhythm-phase or God's-Clock tick. The E8 model executes on fractal time nodes, not wall-clock windows. Adopting a time-gate would break the phase-locked entry logic and introduce temporal bias that cannot be validated across all market regimes. EXPECTED IMPACT: The backtest shows +25.9pp win-rate improvement (n=33), but the sample is too small and the improvement is likely overfitted to a specific period. In live shadow-testing, the filter would have excluded a winning trade (rizzy5m entry at 0.81212) that entered before NY_OPEN, reducing PnL. Even if win-rate rises, total profit may drop due to fewer trades and missed edges outside the window. RISK: Introducing a calendar-based filter degrades the model's core timing logic. It may cause phase drift, reduce trade frequency unpredictably, and create false confidence from a small Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com