LAB #5079 NEUTRAL: TG AUTO: Institutional metrics refreshed — Sharpe 1.66 · Sortino 3.85 · Calmar 2.08 — E8 Intelligence Research

IDEA: AUTO-FORWARDED from the Telegram/breakthrough stream (#1355472, division=institutional, agent=gtx_institutional): { "generated": "2026-09-14T04:45:28.703073+00:00", "method": "Out-of-sample verified weighted portfolio: sleeve weights trained on the first 70% of months only, verified on the final 30% (OOS Sharpe 1.82). Spread costs included, Dukascopy tick-derived data, 1% risk base. Member configs proprietary.", "config": { "engine": "GTX PORTFOLIO \u2014 6 weighted verified configs", "timeframe_min": 60, "filters": "PROPRIETARY (vaulted)" }, "sample": { "trades": 8595, "months": 225, "wins": 200, "breakevens": 675, "losses": 49 }, "metrics": { "win_rate_decided_pct": 80.3, "no_loss_rate_pct": 94.7, "profit_factor": 3.54, "sharpe_ratio": 1.66, "sortino_rat SAME-WINDOW EFFECT: Nothing would have changed. The proposal is a 60-minute portfolio engine with proprietary filters; the live window is 15s–7m scalps on rizzy5m/rizzy7m with geometry-set tar Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com