---
name: undominated-context-distraction-audit
description: Audits retrieval accuracy degradation as irrelevant distractor documents are added to prompts (evaluating signal-to-noise ratio in long contexts).
license: MIT
metadata:
  author: Undominated.ai
  version: "1.0.0"
  tags: ["long-context", "distraction", "retrieval", "rag", "needle"]
---

# Long-Context Distraction Audit

Audits retrieval accuracy degradation as irrelevant distractor documents are added to prompts (evaluating signal-to-noise ratio in long contexts).

## When to Use
Deploy before loading 100k+ token document bundles into prompt context without prior reranking.

## Limitations
Distractor documents must share lexical domain similarity with target needles to detect realistic confusion.

## 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.