LAB #4844 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.8% to 33.3% (+1.5pp — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.8% to 33.3% (+1.5pp, n=1940) SAME-WINDOW EFFECT: The filter would only bite on trades where pool density was actually computed and logged at entry — nothing in the live window above shows density values, so the affected set is unverifiable from this ledger. If HIGH-density is the minority regime, most of the 10 trades (7 of which are REJECTED/open, not resolved) would be untouched, and the two CLOSED/WINs (USDCHF, USDCAD) plus three CLOSED/LOSSes are too few to move a 31.8%→33.3% needle. Net expected delta on this window: roughly zero to one trade flipped, PnL change within noise. The +1.5pp claim cannot be confirmed or refuted here — the window is underpowered and the density field is absent. OVER-TIME PROJECTION: A +1.5pp edge on n=1940 is a real but thin signal — the 95% CI on that delta spans roughly -0.5pp to +3.5pp, so it may be indistinguis Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com