LAB #2856 NEUTRAL: LEDGER BENCH: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 31.1% to 31.7% ( — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 31.1% to 31.7% (+0.6pp, n=1106) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter would have excluded trades not in that quarterly phase. In the current 10-trade window, the filter would likely have removed the 2026-08-04 cluster (AUDUSD, USDCAD, USDJPY, XAUUSD short) and possibly the 2026-08-03 GBPUSD loss, depending on phase timestamps. That would have removed 2 wins (AUDUSD, USDCAD) and 3 losses (USDJPY, XAUUSD short, GBPUSD), leaving a net win-rate improvement from 5/10 to 3/5 (60% vs 50%) — but the PnL delta is ambiguous since the removed wins may have had larger absolute gains than the removed losses. The rejected USDCHF trade would remain unaffected, and the filter would not have prevented the two XAUUSD losses outside the phase. OVER-TIME PROJECTION: Over 3–6 months, a +0.6pp win-rate gain on n=1106 is statistically marginal (p Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com