feat: wide_stop_veto_v1 — skip entries with stops >12% below entry (shadow)

Year-replay stop-width buckets: <8% +0.072R, 8-12% +0.120R, 12-16%
-0.054R, >16% -0.092R — the wide cohort holds every recent dollar
disaster (BIYA 16.7%, FCUV day-2 17.5%), where the exit ladder's blind
spot (BE/trail only arm on the way up) rides the full catastrophe
distance. New stopwidth_gate intervention (fail-open without levels) +
registered spec, same forward bar as the pm-high gate; the two cohorts
overlap so the adjudicator attributes which does the work. In-sample
counts for nothing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

experiments/wide_stop_veto_v1.json

@@ -0,0 +1,9 @@
+{
+  "id": "wide_stop_veto_v1",
+  "hypothesis": "Skip ORB entries whose stop sits more than 12% below entry. Year-replay buckets (2026-08-03): <8% +0.072R, 8-12% +0.120R, 12-16% -0.054R, >16% -0.092R; both July dollar-disasters (BIYA 16.7%, FCUV day-2 17.5%) were wide-stop, where the exit ladder's blind spot (nothing arms until price rises) rides the full catastrophe distance. In-sample evidence counts for nothing toward the bar; overlaps orb_pmhigh_gate_v1's cohort — adjudicate both to attribute the work.",
+  "population": {"min_entry_gap_pct": 0.10, "min_day_volume": 300000, "price_min": 2.0, "price_max": 20.0},
+  "intervention": {"kind": "stopwidth_gate", "max_stop_pct": 0.12},
+  "bars": {"expR_delta_min": 0.05, "min_n": 200},
+  "futility": {"min_n": 400, "expR_delta_max": -0.02},
+  "fidelity": {"atr_frac": 0.25, "spread_mult": 3, "adverse_ticks": 1}
+}