---
name: undominated-distillation-fidelity-audit
description: Measures task accuracy retention and output distribution alignment of distilled student models relative to teacher models.
license: MIT
metadata:
  author: Undominated.ai
  version: "1.0.0"
  tags: ["distillation", "fidelity", "teacher-student", "fine-tuning"]
---

# Model Distillation Fidelity Audit

Measures task accuracy retention and output distribution alignment of distilled student models relative to teacher models.

## When to Use
Deploy when evaluating custom fine-tuned or distilled compact models for production task replacement.

## Limitations
Evaluation benchmarks must be out-of-distribution relative to student fine-tuning training datasets.

## 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.
