LAB #4829 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.8% to 45.0% (+13.2pp, n=40) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.8% to 45.0% (+13.2pp, n=40) SAME-WINDOW EFFECT: The filter would have removed exactly one live trade from the current window — the XAUUSD SHORT via rizzy5m at 4393.01 on 2026-09-10, which closed as a LOSS. That single removal flips the window's realized XAUUSD record from 0W/1L to no-trade, and lifts the overall closed-trade win rate from 2W/5L (28.6%) to 2W/4L (33.3%). The claimed +13.2pp is not reproducible here: n=1 affected trade cannot support a 13.2pp shift, and the filter's own sample (n=40) is far too thin to be treated as a validated edge. Net PnL delta is one avoided loss — positive but statistically meaningless. OVER-TIME PROJECTION: If the 45.0% vs 31.8% split is real and stable, the filter is a genuine conditional edge on XAUUSD shorts and would compound positively over 3–6 months by cutting the worst-performing short bucket. The dominant risk is Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com