LAB #2066 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=1035) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter would have excluded trades opened during that quarterly phase. In the current window, the 2026-08-04 trades (XAUUSD SHORT loss, AUDUSD LONG win, USDCAD SHORT win, USDJPY SHORT open) fall within a likely MANIPULATION phase; removing them would drop 2 wins, 1 loss, and 1 open — netting roughly −1 win and −0.5% PnL versus the unfiltered set. The 2026-07-31 and earlier trades are likely in a different phase, so they remain unaffected. Net effect on this small sample is slightly negative, but the sample is too small to be meaningful. OVER-TIME PROJECTION: Over 3–6 months, a +0.8pp win-rate gain on n=1035 suggests a real but marginal edge, likely driven by avoiding low-quality entries during manipulation windows. However, the gain is within noise (standard erro Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com