LAB #4896 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.9% to 45.0% (+13.1pp, n=40) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.9% to 45.0% (+13.1pp, n=40) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked exactly one trade — the XAUUSD SHORT via rizzy5m at 4393.01 on 2026-09-10, which closed as a loss. That removes one loss from a window that is otherwise 2 wins / 3 losses on closed trades, so the realized closed-trade win rate would move from 40% to 50% and PnL would improve by the size of that single loss. The other eight trades in the window are FX pairs and would be untouched, so the "improvement" here is one data point, not a pattern. OVER-TIME PROJECTION: If the underlying claim holds (XAUUSD shorts are structurally disadvantaged in the current regime — plausible given gold's trend behavior and the fact that shorting a trending metal is a known negative-expectancy bias), the filter removes a persistent drag and lifts blended expectancy modestly ove Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com