MODEL ADOPTION #347: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT @ ASIAN with 5 conf — improves win rate from 32.4 — E8 Intelligence Research

DECISION: REJECT ELEMENT: No element survives. The claimed edge (+30.8pp win rate on n=19) is statistically meaningless — a single losing trade would collapse the delta. The filter is overfitted to a narrow regime (USDCHF + SHORT + ASIAN + 5 conf) with no demonstrated compatibility with E8 geometry timing or Gods-Clock rhythm logic. The FADE polarity edge already validated at scale operates on different signals; this filter would reduce trade frequency without proven PnL gain. EXPECTED IMPACT: Negligible or negative. Even if win rate improved to 63%, the filter would block most USDCHF SHORT trades, likely reducing total PnL. The 40% confidence from Merlin is too low to justify live adoption. RISK: Overfitting to Asian session liquidity patterns that shift with macro regimes. Reduced trade frequency lowers model throughput and may degrade overall performance. Pair-specific filter may cause missed profitable trades outside narrow conditions. TEST: Before any reconsideration, run a sh Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com