LAB #1851 NEUTRAL: LEDGER BENCH: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 32.0% to 32.8% ( — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 32.0% to 32.8% (+0.8pp, n=1032) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter would have excluded trades opened during that quarterly phase. In the current window, GBPUSD SHORT (rizzy5m, 2026-08-03) and XAUUSD SHORT (rizzy5m, 2026-07-31) fall inside a manipulation phase — the first is open, the second was a loss. Removing them would have avoided one loss and one unknown, but the EURJPY SHORT (win) and EURJPY LONG (win) also fall in that phase, so you'd lose two winners. Net effect on this small sample: win rate drops (from ~5/9 to ~3/7) and PnL likely declines, contradicting the backtest's +0.8pp. OVER-TIME PROJECTION: Over 3–6 months, the +0.8pp edge (n=1032) is statistically thin (p≈0.25, not significant). The filter may be overfit to a specific regime (e.g., Q3 2026 volatility or liquidity patterns) and could degrade in other qu Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com