https://github.com/auraoneai/judge-card
A disclosure format for judge prompts, calibration results, known bias, and recommended use envelopes.
https://github.com/auraoneai/judge-card
ai-evaluation evals llm-as-judge model-card
Last synced: 6 days ago
JSON representation
A disclosure format for judge prompts, calibration results, known bias, and recommended use envelopes.
- Host: GitHub
- URL: https://github.com/auraoneai/judge-card
- Owner: auraoneai
- License: mit
- Created: 2026-05-12T01:33:01.000Z (22 days ago)
- Default Branch: main
- Last Pushed: 2026-05-12T04:02:53.000Z (22 days ago)
- Last Synced: 2026-05-12T04:32:48.781Z (22 days ago)
- Topics: ai-evaluation, evals, llm-as-judge, model-card
- Language: Python
- Homepage: https://auraone.ai/open
- Size: 6.84 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
README
# judge-card
`judge-card` validates, generates, and renders Judge Cards: disclosure artifacts for LLM judges.
## Quickstart
```bash
pip install judge-card
judge-card generate --from judge-bench-output.json --out card.md
judge-card validate examples/tutorial_judge_card.json
```
## What This Is Not
Not a model benchmark or endorsement. Examples are synthetic.