{"data":{"kind":"file","path":"README.md","version_id":"uffkn4bb8p1ladc7oni714q3","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":2150,"modified_at":"2026-03-12T19:26:47.648000","content_hash":"06ee0c3d7f2e59ecefd4237e4a72d49666830f9e9d3c816640f1ad8cb5d6811f"},"entries":[],"content":"# medpt\n\n### Overview\n- **Environment ID**: `medpt`\n- **Short description**: Verifiers port for MedPT dataset - classification of medical subspecialties in Portuguese. Abs: https://arxiv.org/abs/2511.11878v1\n- **Tags**: medical, classification, portuguese, train, eval\n\n### Datasets\n- **Primary dataset(s)**: MedPT\n- **Source links**: https://huggingface.co/datasets/AKCIT/MedPT\n- **Split sizes**: 384k raw. Split in 80% train, 20% eval after deduplication and top-k selection.\n\n### Task\n- **Type**: `vf.SingleTurnEnv`\n- **Output format expectations (optional)**: `vf.XMLParser` with `<profession>...</profession>` tags. If CoT is enabled, `<reasoning>...</reasoning>` tags are also expected.\n- **Rubric overview**: `vf.Rubric` with `exact_match` reward function and `format_reward_func`\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nprime eval run medpt\n```\n\nConfigure model and sampling:\n\n```bash\nprime eval run medpt   -m gpt-4.1-mini   -n 20 -r 3 -t 1024 -T 0.7   -a '{\"key\": \"value\"}'  # env-specific args as JSON\n```\n\nNotes:\n- Use `-a` / `--env-args` to pass environment-specific configuration as a JSON object.\n\n### Environment Arguments\n\n| Arg | Type | Default | Description |\n| --- | ---- | ------- | ----------- |\n| `dataset_path` | str | `\"AKCIT/MedPT\"` | Path to the dataset |\n| `dataset_split` | str | `\"train\"` | Split of the dataset to use |\n| `eval_size` | float | `0.2` | Size of the evaluation set |\n| `num_classes` | int | `20` | Number of classes to use |\n| `num_shots` | int | `0` | Number of k-shots to use for few-shot prompting |\n| `prompt_lang` | str | `\"pt\"` | Language of the prompt |\n| `seed` | int | `42` | Seed for data preparation |\n| `enable_cot` | bool | `False` | Enable chain-of-thought |\n| `enable_smart_dedup` | bool | `True` | Enable smart deduplication |\n| `format_reward_weight` | float | `0.0` | Weight of the format reward |\n\n### Metrics\n\nrubric.add_reward_func(exact_match, weight=1.0)\n    rubric.add_reward_func(parser.get_format_reward_func(), weight=0.0)\n\n| Metric | Meaning |\n| ------ | ------- |\n| `exact_match` | Exact match on target answer |\n| `format_reward` | Format reward |\n\n","encoding":"utf-8","truncated":false,"total_bytes":2150},"status":null}