LAB #4866 NEUTRAL: LEDGER BENCH: Apply filter: Pool density HIGH (>=90) — improves win rate from 31.9% 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 31.9% to 33.3% (+1.5pp, n=1939) SAME-WINDOW EFFECT: The live window contains 10 trades, of which 4 are still open/rejected and 6 are resolved (3 losses, 2 wins, 1 rejected-open). Pool density HIGH (>=90) is a regime filter, not a signal filter — it would have suppressed entries during low-density periods, but nothing in the provided window tells us which of these 10 trades had density >=90 at entry. Without that per-trade density tag, the honest read is: this filter cannot be verified against the current window at all. If it did suppress the three rizzy5m/7m shorts that lost (EURUSD, XAUUSD, AUDUSD), the window would flip from 2W/3L to 2W/0L on the surviving sample — but that is a post-hoc story, not evidence. OVER-TIME PROJECTION: A +1.5pp win-rate lift on n=1939 is statistically thin — roughly 29 extra wins, well inside one standard deviation of bi Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com