---
name: undominated-synthetic-eval-diversity-audit
description: "Audits lexical and semantic diversity in synthetic evaluation sets to prevent test-set memorization and benchmark gaming. Recomputed fields must match the other inputs. A pass is not a compliance, safety, or price verdict."
license: MIT
metadata:
  author: Undominated.ai
  version: "1.1.0"
---

# Synthetic Eval Diversity Audit

## Description
Audits lexical and semantic diversity in synthetic evaluation sets to prevent test-set memorization and benchmark gaming.

## Category
`evaluation`

## Tags
`synthetic-eval`, `diversity`, `benchmark-gaming`, `evaluation`

## When to Use
Audit synthetically generated evaluation datasets to ensure wide prompt distribution.

## Operational Limitations
Evaluates pairwise n-gram overlap and embedding cosine dispersion.

## Verification Script
Run the deterministic verification checker:
```bash
python3 scripts/check.py examples/synthetic.json
```
Exit codes:
- `0`: Check passed and thresholds satisfied.
- `1`: Threshold breach or operational violation detected.
- `2`: Schema error or invalid usage.

## What the checker recomputes

The original threshold checks still apply:

- `lexical_diversity_score` must not be < `min_allowed_diversity`.

Every other declared field is type-checked. A negative value is rejected except for deltas, drifts, and gains. A type check does not, by itself, prove the measurement.

`population` and `observedAt` are required. The bundled examples are synthetic fixtures, not market measurements.

```bash
python3 scripts/check.py examples/synthetic.json
python3 scripts/check.py examples/contradiction.json
python3 scripts/check.py examples/broken.json
```

Exit 0 is a pass, exit 1 is a review, and exit 2 is invalid input. A pass does not certify a provider, a regulation, a release, or a price.
