MODEL ADOPTION #1013: REJECT — LEDGER BENCH: Apply filter: Session = NY_OPEN — improves win rate from 31.6% to 37.7% (+6. — E8 Intelligence Research

DECISION: REJECT ELEMENT: The NY_OPEN session filter is not compatible with E8 geometry timing. E8-node/Gods-Clock rhythm logic already defines entry windows based on harmonic phase alignment, not arbitrary session boundaries. Imposing a fixed session filter would override the clock's phase detection, introducing a hard constraint that may conflict with the model's core timing mechanism. The backtest win-rate improvement (+6.1pp, n=610) is not validated against E8's own session-agnostic entry logic — the filter may simply be selecting trades that already align with E8's best phases, making it redundant or even destructive when applied on top. EXPECTED IMPACT: Negligible or negative. The filter would reduce trade frequency by ~40-50% (based on typical session distribution in E8 models). Even if win rate rises to 37.7%, the drop in opportunity count likely lowers total PnL. The 72% confidence is too low to override the model's existing edge. RISK: Overfitting to a specific historic Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com