MODEL ADOPTION #4039: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 32.5% to 34.0% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No element survives — the min-confirmations filter is a statistical artifact, not an E8-geometry edge. Confirmation count is a lagging, regime-dependent noise proxy; it does not align with Gods-Clock rhythm or FADE polarity timing. EXPECTED IMPACT: Real-world gain likely 0.0 to +0.3pp win rate, not +1.5pp. The backtest gain is overfit to a single window; blocked early entries include high-conviction winners in trending regimes. Reduced frequency (~10–15%) will cut both noise and alpha, netting near zero PnL. RISK: Filter removes early entries that catch reversals at the exact E8 rhythm turn — the core FADE edge. In choppy regimes, confirmations accumulate slowly, so the filter would systematically exclude the best counter-trend setups. Also, confirmation count is not monotonic with quality — it correlates with time-in-setup, not polarity strength. TEST: Before any reconsideration, run a 90-day replay-bench on all historical E8 signals (n≥5000) with min Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com