MODEL ADOPTION #3095: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.2% to 38.4% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No element survives — the "min confirmations >= 6" filter is a statistical artifact, not a geometric edge. E8-node/Gods-Clock rhythm logic already encodes timing; adding a confirmation count is redundant and likely regime-dependent. EXPECTED IMPACT: Win-rate gain (+7.2pp) is real in backtest but not causal — it merely removes early entries that fail in low-volatility chop. In trending or news-heavy periods, delayed entries will miss the best price, cutting R:R and net profit. The 71.4% window result is cherry-picked (n=7) and not reproducible. RISK: Filter systematically excludes high-volatility breakouts that occasionally produce outsized winners (tail risk). Over 3–6 months, frequency drops ~25%, but average R:R shrinks — net PnL likely flat or negative. Overfits to 2026 summer low-vol regime; will degrade in live trending markets. TEST: Must pass a 30-day shadow replay on all 10 instruments with ≥150 filtered and ≥150 skipped signals, requiring: (a) Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com