LAB #2831 NEUTRAL: LEDGER BENCH: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 31.2% to 31.8% ( — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 31.2% to 31.8% (+0.7pp, n=1081) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter would have excluded trades outside that quarterly phase. In the current window, the 10 live trades span July 31–Aug 7, 2026 — likely a single quarter phase. If that phase is not MANIPULATION, all 10 trades would be blocked, eliminating 6 wins and 4 losses (net +2 wins). If it is MANIPULATION, no change. Expected PnL delta is therefore binary: either −0 (if phase matches) or −6 wins/+4 losses removed (net −2 wins, but also removes 4 losses, so PnL impact depends on risk/reward per trade — likely slightly negative if wins average smaller than losses). The +0.7pp win-rate gain from backtest is too small to overcome the risk of zeroing out an entire active quarter. OVER-TIME PROJECTION: Over 3–6 months, this filter would reduce trade frequency by roughly 75% Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com