LAB #4618 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 32.2% to 44.7% (+12.5pp, n=38) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 32.2% to 44.7% (+12.5pp, n=38) SAME-WINDOW EFFECT: Applying an XAUUSD SHORT filter would have had zero effect on the current live window, as none of the ten listed trades involve XAUUSD. The filter would not have blocked, altered, or added any position, so the realized win rate (5W/3L among closed trades) and PnL would remain unchanged. The claimed +12.5pp improvement is derived from a separate backtest sample (n=38) that does not overlap with this live set, making it irrelevant to the current book. No trade in the window would have been saved or lost by this rule. OVER-TIME PROJECTION: Over 3–6 months, this filter would only matter if XAUUSD SHORT signals actually occur in the live stream — but the current engine shows no XAUUSD activity at all, suggesting either the strategy rarely trades gold or the filter targets a non-existent signal class. If applied blind Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com