Skip to content

KB/signal

Regime

Last verified

Auto-generated. This article is rebuilt from app/signals/config/signal_definitions.json by scripts/build_signals_kb.py. Edit the registry entry and re-run the script β€” do not edit this file directly.

Regime

What it is

Regime β€” registry key regime.

Macro regime classifier output β€” PANIC / RISK-OFF / RISK-ON / CAUTIOUS / TRANSITIONAL, evaluated most-severe-first.

Data-pyramid tier

T4 β€” Regime / state. This metric sits at the regime / state layer of the platform’s six-tier data pyramid (T0 raw inputs β†’ T5 actionable read). The tier reflects how far the value is from a raw measurement β€” not how strongly it is validated. Abstraction and validation are separate axes: a higher tier is not a claim of stronger evidence.

Horizon & validation

Horizon: COINCIDENT β€” a state read, not a forecast.

Coincident state descriptor, not a forecast β€” and not the same mechanism as score_weights.json’s regime_overrides (a separate, energy_regime-keyed conditional-scaling pattern). This label’s only weighting effect: PANIC amplifies credit/volatility alignment weight 1.5x (app/signals/regime.py:_category_regime_weight).

Source

Source module: capture
Data source: computed

Derived metric β€” produced inside the platform (app/signals/capture.py or equivalent) rather than fetched as a raw upstream value. See the How it's computed section below for the formula.

How it’s computed

Sequential first-match classifier over four inputs β€” DIX (dark-pool positioning), GEX (dealer gamma), HY OAS (credit spread), and breadth (% of names above their 50-day SMA) β€” evaluated most-severe-first: PANIC (VIX term structure in backwardation AND at least one extreme stress signal) β†’ RISK-OFF (any single strong negative signal) β†’ RISK-ON (all four signals constructive) β†’ CAUTIOUS (institutional buying + positive GEX with some caution) β†’ TRANSITIONAL (the mixed-signal fallback). Cut-points live in regime_config.json. See app/signals/regime.py:classify_regime.

Where it surfaces

Health-score / alignment role

Data carrier β€” no implication, no health-score contribution.

Persisted for downstream consumers (sparklines, base-rate matcher, calibration substrate) but does not classify into BULLISH / NEUTRAL / BEARISH and does not contribute to the 0-100 health score.

Release cadence

See also