{"data":{"kind":"file","path":"README.md","version_id":"t89bmlfb4d6bdmw1i0ftzrnt","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1509,"modified_at":"2026-09-13T04:06:06.953000","content_hash":"71d945cb4b4dd58f2b01134f2ea9827c553ecf1f329af327084c100313bb7414"},"entries":[],"content":"# wideseek\n\nWideSearch-style broad information seeking: each task poses a complex, multi-faceted query whose gold answer is a Markdown table; the taskset is tool-free (the harness supplies web search) and the agent emits the table as its final message. Table tasks are scored by WideSearch item-level (cell) F1 — rows aligned by the dataset's `unique_columns` primary keys, cells matched normalized with an optional LLM judge for semantic equivalence — while the short-answer `depth` split is scored by answer equivalence.\n\n## Taskset\n\n- **Source:** [RLinf/WideSeek-R1-train-data](https://huggingface.co/datasets/RLinf/WideSeek-R1-train-data) (`width` split; also `depth` / `hybrid`)\n- **Size:** 20000 tasks\n\n## Changelog\n\n- 2026-08-31: Yield task records on demand so bounded evaluations construct only the requested prefix.\n- 2026-08-30: Standardized short-answer equivalence on the native `ReferenceJudge` contract while retaining the hardened message boundary and specialized batched table-cell judge.\n- 2026-07-10: Ported to the task-centric verifiers API: rewards and lifecycle hooks live on the `Task` (a `TaskData` row + behavior split), and task-facing config knobs (judges, tool/user placement, scoring parameters) moved from `--env.taskset.*` to `--env.taskset.task.*`. Requires `verifiers>=0.2.0` and Python `>=3.11`.\n- 2026-06-24: Initial release — WideSearch-style table compilation on RLinf's WideSeek-R1 data; item-level F1 reward aligned by `unique_columns` with an optional LLM judge.\n","encoding":"utf-8","truncated":false,"total_bytes":1509},"status":null}