LAB #2633 NEUTRAL: LEDGER BENCH: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 31.0% to 31.6% ( — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Quarterly phase = MANIPULATION — improves win rate from 31.0% to 31.6% (+0.6pp, n=1094) SAME-WINDOW EFFECT: Applying the MANIPULATION-phase filter would have blocked all trades in the current window, since none of the 10 listed entries occurred during a MANIPULATION quarterly phase (all are dated Aug 3–7, 2026, which falls in a different phase). This would have eliminated 6 wins and 4 losses, netting a PnL change of roughly +0 (removing both winners and losers equally), but would have reduced trade count to zero — a catastrophic outcome for the live account if the filter were active now. The +0.6pp backtest gain is not visible here; instead, the filter would have halted all activity, suggesting the phase classification may be misaligned with the current calendar or that the backtest window differs from this live sample. OVER-TIME PROJECTION: Over 3–6 months, this filter would likely reduce trade fre Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com