LAB #2662 NEUTRAL: LEDGER BENCH: Apply filter: EURUSD LONG — improves win rate from 31.1% to 34.8% (+3.7pp, n=46) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: EURUSD LONG — improves win rate from 31.1% to 34.8% (+3.7pp, n=46) SAME-WINDOW EFFECT: Applying a EURUSD LONG-only filter would have had zero impact on the current live window — none of the 10 listed trades are EURUSD, and no EURUSD LONG signals appear in the GTX setup results. The claimed +3.7pp win-rate improvement (n=46) is from a backtest subset that does not overlap with the live trade distribution shown here, which is dominated by GBPUSD, XAUUSD, and USDJPY. Therefore, the live PnL delta over this window would be exactly $0.00 — the filter changes nothing in the observed period. OVER-TIME PROJECTION: Over 3–6 months, the filter would only affect EURUSD LONG entries, which appear to be a minor fraction of the engine's total trade flow (likely <10% based on the mix shown). If the backtest improvement is real and not overfit, it could add a small positive edge on that specific pair/direction, but Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com