{"data":{"kind":"file","path":"README.md","version_id":"aizse4dxuhdatgnij8lo9fa6","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1012,"modified_at":"2025-10-19T21:26:33.622000","content_hash":"de2dce30381311de37eedfdadf60e5f0358482ee632cc0aa6f91c62a932ce1e0"},"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/prime-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":1012},"status":null}