Lexical detectors
N-gram overlap, canaries, hashes, and answer-format patterns.
AuraOne Open / Benchmark contamination
Scan evaluation items for n-gram overlap, canary strings, answer patterns, and hashes, with optional embedding similarity. Every finding names the item and the detector.
pip install contamination-auditThe example inputs live in the repository. Get them first:
git clone --depth 1 https://github.com/auraoneai/contamination-audit.git && cd contamination-auditThen run the example from the repository root:
contamination-audit run --eval-data examples/eval.jsonl --skip-embedding{
"item_count": 2,
"finding_count": 1,
"aggregate_risk_score": 0.1,
"findings": [
{
"detector": "answer_pattern",
"item_id": "1",
"match": "The answer is (B)"
}
],
"synthetic": true,
"reproducible": true
}What you can do
N-gram overlap, canaries, hashes, and answer-format patterns.
Each finding names the item, detector, and matched text.
Deterministic output for the same inputs and settings.
See how the product moves from setup through a useful output.
01
Install contamination-audit 0.1.2 from the package registry.
Package version
02
Run the quick start on the synthetic fixture and compare it with the output above.
Captured output
03
Point the same command at your own files, locally or in CI.
Local report
Release specifications
Review the current source, release, runtime, and support information.
Availability
Review the current version, source, packages, downloads, supported platforms, and install options.
PyPI 0.1.2 is available with a linked source tag v0.1.2.
When the work grows
Continue exploring
Each one lists its source, current version, and install path.