{"data":{"kind":"file","path":"README.md","version_id":"jvd66vqb1w5v0a7vfuidnt2x","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":741,"modified_at":"2026-09-13T04:06:06.767000","content_hash":"4d1a3bbe21bf9384217a53b66237c23990341a174e674d2637379148caa339f2"},"entries":[],"content":"# i3-code\n\nSingle-turn Python code generation tasks. The model writes a solution that is scored by running it against the task's hidden test cases (stdin/stdout or functional) inside the rollout's runtime; reward is 1.0 iff every test passes.\n\n## Taskset\n\n- **Source:** [PrimeIntellect/INTELLECT-3-RL](https://huggingface.co/datasets/PrimeIntellect/INTELLECT-3-RL) (`code` subset, `train` split)\n- **Size:** 8,579 tasks\n\n## Changelog\n\n- 2026-09-03: Restore default solver network access by reverting the `network_allow=[]` default-deny policy introduced in #780; training rollouts need outbound network.\n- 2026-08-31: Yield task records on demand so bounded evaluations construct only the requested prefix.\n- 2026-06-25: Initial v1 taskset.\n","encoding":"utf-8","truncated":false,"total_bytes":741},"status":null}