Parameter Version Dispersion (PVD)

GMI-EGD-009Evidence-Governed DataPilot-Ready

Definition

The share of the active claim corpus carrying grades produced under a superseded parameter version, with the share whose standing would change under the current version reported alongside.

The Measurement Gap

There is no metric that tells you what share of the active corpus carries grades produced under superseded parameter versions and how many of those would change standing under the current version, which means a heterogeneous corpus is consumed as though it were homogeneous.

Formula

PVD = C_superseded / C_active , with the companion S = C_changed / C_sampled

Proposed formula, pending validation pilots.

At a Glance

Unit
Ratio (0 to 1)
Trend Direction
Lower
Category
Grading Integrity and Determinism

Decision Supported

Whether a corpus can be read as a single graded population or must be re-graded before use.

← Grade Movement Attribution Rate (GMAR)UNKNOWN Displacement Rate (UDR) →

Assess Your Organization

The AI-GPS Assessment evaluates your AI governance maturity and recommends KPIs like this one for your implementation roadmap.

Take the Free AI-GPS Assessment