{"data":{"kind":"file","path":"README.md","version_id":"b9c60dtxn7ng9k6vn9qfuwl7","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1016,"modified_at":"2026-03-29T12:29:19.476000","content_hash":"851a4cddfc535fe56b3f377eef8d4de359f521c12fbee9fe7c873bf554d8cb32"},"entries":[],"content":"# llm-writer-negative-style\n\nENV for self-grading for LLM Writer Style. Style guide is in the individual prompt file.\nReward function for each setup is broken down into a rubric env to make the score continuous.\n\n### Overview\n- **Environment ID**: `llm-writer-negative-style`\n- **Short description**: Is the style of text written like an LLM?\n- **Tags**: single-turn\n\n### Datasets\n- **Primary dataset(s)**: N/A\n- **Source links**: https://github.com/PrimeIntellect-ai/community-environments/pull/131\n- **Split sizes**: N/A\n\n### Task\n- **Type**: single-turn\n- **Parser**: N/A\n- **Rubric overview**: Several rules that encode common LLM writing styles, with binary reward.\n\n### Quickstart\n```bash\nuv run vf-eval llm-writer-negative-style -m gpt-4.1-mini -n 5 --save-dataset --rollouts-per-example 3\n```\n\n### Environment Arguments\nN/A\n\n### Metrics\nSummarize key metrics your rubric emits and how they’re interpreted.\n\n| Metric | Meaning |\n| ------ | ------- |\n| `reward` | Equal weighted rule based binary scoring. |\n","encoding":"utf-8","truncated":false,"total_bytes":1016},"status":null}