LAB #964 PROMISING: LEDGER BENCH: Apply filter: Phase distance MODERATE (5-10deg) — improves win rate from 31.5% to 33.3 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Phase distance MODERATE (5-10deg) — improves win rate from 31.5% to 33.3% (+1.8pp, n=156) SAME-WINDOW EFFECT: Applying a phase distance filter of 5-10 degrees to the current live window would have rejected the EURUSD SHORT (loss) and the GBPUSD LONG (loss), as both likely fell outside the moderate phase distance band. It would also have rejected the GBPUSD SHORT via rizzy5m (currently open/rejected), but that trade is already not contributing to PnL. The net effect on this small sample would be removing two confirmed losses, improving the win rate from roughly 57% (4 wins out of 7 closed trades) to 80% (4 wins out of 5 closed trades), though the sample is too small to be statistically meaningful. OVER-TIME PROJECTION: Over 3-6 months, a +1.8pp win rate improvement on a 31.5% baseline is modest but real, assuming the backtest holds. The risk is that the filter may also reject some winning trades that Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com