{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.10382", "kind": "paper", "url": "https://arxiv.org/abs/2606.10382"}], "authors": ["Shi Jin", "Yuntian Wang", "Yuhui Duan", "Di Wu", "Gaoqi Dong", "Xiaohang Liu", "Xiaotong Li", "Hongfei Jia", "Zehao Zhang", "Tianyu Wang", "Zhongjie Jia", "Yuanqi Yao", "Chenjia Bai", "Zhaxizhuoma", "Siao Liu", "Nieqing Cao", "Jin Wang", "Chao Yu", "Yan Ding"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.10382", "source_url": "https://arxiv.org/abs/2606.10382"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "UMI-Bench 1.0 is a benchmark for tabletop robotic manipulation policies using the Universal Manipulation Interface, with a unified protocol for data collection, reset, execution, and logging."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.10382", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.10382", "title": "UMI-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.10382", "modality": null, "name": "UMI-Bench", "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_umi-bench_1bf436a3", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "81b5f56976c03a0e97fcba3d85f44a17a0d454160c6d56857500f7f579a2fd1d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.10382"}, "publisher": null, "released": "2026-06-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.10382", "source_url": "https://arxiv.org/abs/2606.10382"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-10382", "source": "claire_radar", "source_benchmark_id": "2606.10382", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.10382", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-24", "state": "stale"}}, "status": "stale"}, "capabilities": ["Robot manipulation"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "6079c9110175d6d6a2fb2d02525386190a09fdfd6523782622625793def40019", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "UMI-Bench 1.0 is a benchmark for tabletop robotic manipulation policies using the Universal Manipulation Interface, with a unified protocol for data collection, reset, execution, and logging.", "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"], "snippet": "We present UMI-Bench 1.0, a local-first real-robot benchmark for standardized evaluation of UMI-style manipulation policies."}, "familyId": "bmf_b7b6ea4bab62", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_umi-bench_1bf436a3", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.10382", "paper": "https://arxiv.org/abs/2606.10382", "pdf": "https://arxiv.org/pdf/2606.10382", "project": null, "report": "https://arxiv.org/abs/2606.10382"}, "metrics": [], "motivation": "Real-robot evaluation is essential for understanding whether learned manipulation policies can operate reliably outside curated demonstrations.", "name": "UMI-Bench", "oneLine": "UMI-Bench 1.0 is a benchmark for tabletop robotic manipulation policies using the Universal Manipulation Interface, with a unified protocol for data collection, reset, execution, and logging.", "paperTitle": "UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.10382", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-09", "source": {"authors": ["Shi Jin", "Yuntian Wang", "Yuhui Duan", "Di Wu", "Gaoqi Dong", "Xiaohang Liu", "Xiaotong Li", "Hongfei Jia", "Zehao Zhang", "Tianyu Wang", "Zhongjie Jia", "Yuanqi Yao", "Chenjia Bai", "Zhaxizhuoma", "Siao Liu", "Nieqing Cao", "Jin Wang", "Chao Yu", "Yan Ding"], "categories": ["cs.RO"], "id": "2606.10382", "title": "UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data", "type": "arxiv", "url": "https://arxiv.org/abs/2606.10382"}, "sourceUpdatedAt": "2026-06-09T03:47:54Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Real-robot evaluation is crucial for assessing manipulation policies beyond curated demos; UMI-Bench aims to standardize evaluation for UMI-style policies, which could aid comparisons and reproducibility."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
