{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.30326", "kind": "paper", "url": "https://arxiv.org/abs/2605.30326"}, {"id": "gh:umass-embodied-agi/robowits", "kind": "repo", "url": "https://github.com/UMass-Embodied-AGI/RoboWits"}, {"kind": "website", "url": "https://umass-embodied-agi.github.io/RoboWits"}], "authors": ["Chunru Lin", "Hongxin Zhang", "Fenghao Yu", "Zhehuan Chen", "Thomas L. Griffiths", "Yejin Choi", "David Held", "Chuang Gan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.30326", "source_url": "https://arxiv.org/abs/2605.30326"}, "categories": ["Agents", "Agents & Tool Use", "Reasoning", "Robotics & Embodied AI", "Robustness", "Tool use"], "description": {"en": "RoboWits is a bi-manual robotic benchmark designed to evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions. It includes 30 seed tasks and 208 mutated tasks with graded difficulty across geometry, material, and assembly-based reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.30326", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.30326", "title": "RoboWits"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.30326", "modality": null, "name": "RoboWits", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_robowits_1755c069", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "127d87d67d0dbd40cd24b0480e34ed8c893d471f0a270f2633c23f44bea0a4e0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.30326"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.30326", "source_url": "https://arxiv.org/abs/2605.30326"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-30326", "source": "claire_radar", "source_benchmark_id": "2605.30326", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/UMass-Embodied-AGI/RoboWits", "githubScope": "benchmark_repo", "githubStars": 7, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2605.30326", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning", "Tool use", "Robustness"], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "62b701a819189a501668cd0b71bb780789cd7c6770e17bc63f9b46ecfd64230b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RoboWits is a bi-manual robotic benchmark designed to evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions. It includes 30 seed tasks and 208 mutated tasks with graded difficulty across geometry, material, and assembly-based reasoning.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce RoboWits, a bi-manual robotic benchmark designed to systematically evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions."}, "familyId": "bmf_dfdca2555adf", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/UMass-Embodied-AGI/RoboWits", "url": "https://umass-embodied-agi.github.io/RoboWits"}], "scope": "benchmark_repo", "url": "https://github.com/UMass-Embodied-AGI/RoboWits", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_robowits_1755c069", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/UMass-Embodied-AGI/RoboWits", "data": null, "hfPaper": "https://huggingface.co/papers/2605.30326", "paper": "https://arxiv.org/abs/2605.30326", "pdf": "https://arxiv.org/pdf/2605.30326", "project": "https://umass-embodied-agi.github.io/RoboWits", "report": "https://arxiv.org/abs/2605.30326"}, "metrics": [], "motivation": "The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments.", "name": "RoboWits", "oneLine": "RoboWits is a bi-manual robotic benchmark designed to evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions. It includes 30 seed tasks and 208 mutated tasks with graded difficulty across geometry, material, and assembly-based reasoning.", "paperTitle": "RoboWits: Unexpected Challenges for Robotic Creative Problem Solving", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.30326", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Chunru Lin", "Hongxin Zhang", "Fenghao Yu", "Zhehuan Chen", "Thomas L. Griffiths", "Yejin Choi", "David Held", "Chuang Gan"], "categories": ["cs.RO", "cs.AI"], "id": "2605.30326", "title": "RoboWits: Unexpected Challenges for Robotic Creative Problem Solving", "type": "arxiv", "url": "https://arxiv.org/abs/2605.30326"}, "sourceUpdatedAt": "2026-05-28T17:57:15Z", "topics": ["Agents", "Reasoning"], "venueAttempts": [], "whyItMatters": "Current robotic benchmarks focus on skill-level execution, not the cognitive reasoning needed for real-world adaptation. RoboWits aims to evaluate reasoning-centric capabilities under unexpected challenges."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
