{"record": {"aliases": ["CrossSearch", "CrossSearch: 100-task paper set"], "artifacts": [{"kind": "website", "url": "https://huggingface.co/datasets/AfterQuery/CrossSearch"}], "audits": [], "categories": ["professional"], "description": {"en": "Evaluation-only benchmark: 100 professional tasks where an agent must reconcile files in a local workspace with public web sources, graded on atomic rubrics for full credit (reported as pass@1 and pass^3). The dataset preserves rollout traces, attachments, reference answers, rubric judgments and model rewards, and documents native and alternative search-engine conditions separately. A reward may be absent for a limit outcome, and results from different conditions, judge versions or task-set revisions are not interchangeable. The authors' blog reports a leaderboard and dates the release 2026-11-12, but the dataset card states no release date and this registry cites only the benchmark URL, so the entry carries no released field; the blog also reports two metrics, so no score rows are added."}, "documents": [], "evidence_summary": {"document_count": null, "model_count": null, "model_count_basis": null}, "key": "model-reports:crosssearch", "modality": null, "name": "CrossSearch", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"registry": "data/model_cards.yml", "score_archive": "data/benchmark_scores.yml", "source_url": "https://huggingface.co/datasets/AfterQuery/CrossSearch"}, "publisher": null, "released": null, "released_reference": null, "schema_version": 1, "sizes": [], "slug": "crosssearch", "source": "model_reports", "source_benchmark_id": "crosssearch"}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
