MODEL ADOPTION #3257: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.9% to 41.5% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No element survives — the +9.6pp win-rate gain is a hit-rate illusion, not an edge. The filter (min confirmations ≥6) is a lagging indicator that prunes early entries, but E8's fade polarity edge depends on *timing* the reversal at the Gods-Clock rhythm boundary — adding confirmations delays entry past the optimal fade zone, converting high-RR reversals into lower-RR trend-following entries. The backtest's n=366 is too small to separate regime luck from structural improvement, and Merlin's own window test shows no PnL change (6/9 → 4/6, same win rate) — only reduced trade count. EXPECTED IMPACT: Win rate might rise to ~41.5% in the backtest, but average R-multiple per trade will drop (later entries = worse price), and absolute profit likely falls 15–25% due to fewer signals. Net effect: higher hit rate, lower expectancy — a classic overfitting trap. RISK: The filter will systematically exclude the highest-conviction early fades (which often win with <6 c Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com