---
name: undominated-ip-infringement-verbatim-audit
description: "Measures verbatim memorization rates of copyrighted code and text corpora in model completion outputs. 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"
---

# IP Infringement Verbatim Memorization Audit

## Description
Measures verbatim memorization rates of copyrighted code and text corpora in model completion outputs.

## Category
`security`

## Tags
`copyright`, `memorization`, `ip-risk`, `compliance`

## When to Use
Audit models for enterprise code generation to ensure outputs do not emit verbatim copyrighted source repositories.

## Operational Limitations
Evaluates 50-token exact match n-gram overlap against protected corpora.

## 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

- `rate` = 100 * verbatim_matches / sampled_completions, then the original `>` check against `max_allowed_match_percent`. `verbatim_matches` cannot exceed `sampled_completions`.

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.
