---
name: undominated-false-refusal-rate-audit
description: Quantifies false-positive refusal rates on benign software engineering, cybersecurity, and clinical research queries.
license: MIT
metadata:
  author: Undominated.ai
  version: "1.0.0"
  tags: ["safety", "refusals", "over-refusal", "usability", "alignment"]
---

# False-Positive Refusal Rate Audit

Quantifies false-positive refusal rates on benign software engineering, cybersecurity, and clinical research queries.

## When to Use
Use when evaluating enterprise safety fine-tunes to prevent disruption of legitimate developer workflows.

## Limitations
Test datasets must exclude genuinely dangerous dual-use materials to measure true false positives.

## Verification Script
Run the deterministic stdlib checker:
```bash
python3 scripts/check.py examples/synthetic.json
```
Exits `0` on verified pass, `1` on failed assertion, `2` on malformed input.