{"data":{"kind":"file","path":"README.md","version_id":"g47wktv39glozoimkaz2y9p8","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1786,"modified_at":"2026-09-13T04:06:06.936000","content_hash":"a58c7b5a1df0d7d21e2386d1144702e71382c58ae8b4f592c3cef4195e27e662"},"entries":[],"content":"# virl39k\n\nViRL39K — 38,870 verifiable vision-language QAs curated for RL training ([VL-Rethinker](https://github.com/TIGER-AI-Lab/VL-Rethinker), [paper](https://arxiv.org/abs/2504.08837)). Each task interleaves the question's images at its `<image>` markers and scores the final answer with math-verify.\n\n## Taskset\n\n- **Source:** [`TIGER-Lab/ViRL39K`](https://huggingface.co/datasets/TIGER-Lab/ViRL39K) (`train` split; images read lazily from the repo's `images.zip`, ~1.8 GB on first download)\n- **Prompt:** the question with images interleaved, plus the upstream VL-Rethinker instruction: \"Please reason step by step, and put your final answer within \\boxed{}\"\n- **Scoring:** math-verify equivalence against the gold `\\boxed{}` answer, lenient on format — the boxed answer is preferred, but without one math-verify's own extraction is used (LaTeX/plain expressions, plus option letters on its A–D default), so a correct answer is never scored 0 just for a missing box. `has_boxed_answer` is tracked as a metric.\n- **Filters:** `--env.taskset.category` (exact match, e.g. `Spatial Reasoning`), `--env.taskset.min-pass-rate` / `--env.taskset.max-pass-rate` on the dataset's `PassRate_32BTrained` annotation for difficulty selection.\n\n## Deviations from upstream\n\n- Upstream (VL-Rethinker) requires a `\\boxed{}` answer; this port falls back to math-verify's own extraction when the box is missing, by design, to avoid penalizing format.\n- ~850 rows carry no `<image>` marker in the question text; their image is placed before the question (the usual VLM convention).\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- 2026-07-19: Initial port.\n","encoding":"utf-8","truncated":false,"total_bytes":1786},"status":null}