Stress composite (WS C/E)

The question

Can a composite of stress sub-signals dynamically size portfolio risk capacity across market regimes?

How it was tested

The hypothesis, its exact trigger, the outcome it predicts, and the pass/fail bar were written down and cryptographically hash-locked before any data was tested, then held through a mandatory cooling-off period. The backfill ran exactly once against those frozen parameters — no re-tuning, no curve-fitting — using adversarial statistics (stationary-bootstrap confidence intervals, multiple-testing correction, purged cross-validation with an embargo, and walk-forward out-of-sample splits). The specific trigger thresholds are proprietary and omitted here.

The outcome

RAN 2026-05-22 → FAIL_DO_NOT_SHIP (1 of 5 pass criteria): stress signal real (crosses 70 on 100% of 8 events) + capacity-scaled Sharpe higher (0.53→0.87) BUT coincident-to-lagging (median lead −10d), normal-regime carry 8.31% > 5% bar, 4/7 sub-signal ICs negative on train. Per failureResponse: DON'T SHIP (a v2 = NEW sub-signals, separate pre-reg). data/backfill/stress_composite_2026-05-22.json. Rule #10: no iterate. FILED 2026-06-30 (surfaced by the research desk; 6wk-stale entry).

The backfill ran and the hypothesis failed its pre-registered bar. It is recorded and retired — not re-tested without a fresh, separately-registered hypothesis.