Skip to content

KB/signal

CFTC Specs Z

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 — do not edit this file directly.

CFTC Specs Z

What it is

CFTC Specs Z — registry key cot_specs_z.

Positioning extremes are contrarian setup signals, not direction indicators. Used by squeeze_setup composite + transitions; not in health score.

Data-pyramid tier

T1 — Signal. This metric sits at the signal layer of the platform’s six-tier data pyramid (T0 raw inputs → T5 actionable read). The tier reflects how far the value is from a raw measurement — not how strongly it is validated. Abstraction and validation are separate axes: a higher tier is not a claim of stronger evidence.

Horizon & validation

No validated skill horizon is on file for this metric — read it as context / a data carrier, not a validated edge. Stamps are added only when a gated research verdict lands.

Source

Source module: cot
Data source: back_fillable

Fetched directly from app/sources/cot.py; see source code for the upstream API call and any provider-specific handling.

How it’s computed

52-week Z-score of cot_specs_net (S&P 500 e-mini speculator net positioning): (specs_net_today − mean_52w) / stdev_52w. Flags spec positioning extremes; one of the squeeze_setup triggers when ≤ −1.5. See app/sources/cot.py:117.

Where it surfaces

Bands / thresholds

Classifier direction: range_is_better.

Range Label Dot Implication Points
-0.5 – 0.5 Neutral favorable NEUTRAL —
-1.5 – -0.5 Net short leaning NEUTRAL —
0.5 – 1.5 Net long leaning NEUTRAL —
< -1.5 Extreme short cautionary BULLISH —
≥ 1.5 Extreme long cautionary BEARISH —

Health-score / alignment role

Display-only — has bands for surface labeling but does not contribute to the health score (scoring is handled by a companion metric).

Release cadence

CFTC COT publishes Fridays at ~15:30 ET. Within 14 days = live.

See also