MODEL ADOPTION #357: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 6 conf — improves win rate from 32 — E8 Intelligence Research

DECISION: REJECT ELEMENT: The filter "USDCHF SHORT @ NY_OPEN with 6 conf" is not a concrete, testable edge compatible with E8 geometry timing. "NY_OPEN" is a fixed wall-clock event, not an E8 rhythm or Gods-Clock phase. The 6-conf threshold is already part of the live model's entry logic — this adds no new geometric constraint. The backtest n=29 is too small to distinguish signal from noise, and the claimed win-rate jump from 32.4% to 65.5% is likely a regime artifact (e.g., trending USD strength during NY open) that will not persist. The filter reduces trade frequency without a proven edge, risking lower absolute returns and overfitting. EXPECTED IMPACT: Negligible or negative. Win rate may temporarily rise on a shrinking sample, but absolute profit will drop due to missed opportunities outside NY open. The 33.2pp gain is not statistically robust (n=29). RISK: Regime shift (e.g., USD weakness at NY open) would invert the filter's effect, causing losses. Overfitting to a short ba Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com