LAB #2312 NEUTRAL: LEDGER BENCH: Apply filter: ETHUSD SHORT — improves win rate from 31.5% to 50.8% (+19.3pp, n=59) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: ETHUSD SHORT — improves win rate from 31.5% to 50.8% (+19.3pp, n=59) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked all ETHUSD trades — but none of the 10 listed trades are ETHUSD, so zero trades would have been affected. The claimed +19.3pp win-rate improvement (n=59) is from a different instrument and time period, so it provides no direct evidence for the current basket. Expected PnL delta in this window: 0.0% — the filter is irrelevant to the trades shown. OVER-TIME PROJECTION: If the 31.5% → 50.8% win-rate lift is real and stable, it would reduce ETHUSD short losses materially over 3–6 months, likely improving overall equity curve smoothness. However, n=59 is small, and the filter may be overfit to a specific volatility regime (e.g., trending ETHUSD). Risk: if ETHUSD enters a mean-reverting phase, the filter could block profitable shorts and degrade performance. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com