{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.29937", "kind": "paper", "url": "https://arxiv.org/abs/2606.29937"}], "authors": ["Giuliano Pioldi", "Yashika Batra", "Arman Ibrayeva", "Yuanchen Bai", "Purnjay Maruur", "Promise Ekpo", "Angelique Taylor"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.29937", "source_url": "https://arxiv.org/abs/2606.29937"}, "categories": ["Robotics", "Robotics & Embodied AI"], "description": {"en": "REPAIR-Bench evaluates robot error perception and recovery in human-robot interaction. It includes 214 interaction trials from 41 participants with four induced failure types, synchronized facial action units, head pose, speech transcripts, and post-interaction reports. Three tasks cover failure detection across sessions, failure-type classification, and recovery prediction."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.29937", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.29937", "title": "REPAIR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Cornell University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.29937", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.29937", "source_url": "https://openalex.org/W7166724469"}, "key": "claire-radar:2606.29937", "modality": null, "name": "REPAIR-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_repair-bench_816a6914", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9e1ad05c01101098290247cae49b4881dc82e01a77326a7f7bb2cba0f2f515db", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.29937"}, "publisher": null, "released": "2026-06-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.29937", "source_url": "https://arxiv.org/abs/2606.29937"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-29937", "source": "claire_radar", "source_benchmark_id": "2606.29937", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2606.29937", "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", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "f9dfa802988a6a09d0afd85dfbb22788fe1b83946008ad8ae198a1c97f92b50b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "REPAIR-Bench evaluates robot error perception and recovery in human-robot interaction. It includes 214 interaction trials from 41 participants with four induced failure types, synchronized facial action units, head pose, speech transcripts, and post-interaction reports. Three tasks cover failure detection across sessions, failure-type classification, and recovery prediction.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present REPAIR-Bench, built on 214 interaction trials from 41 participants, the benchmark spans four induced failure types and provides synchronized facial action units, head pose, speech transcripts, and post-interaction affect and recovery reports."}, "familyId": "bmf_cd82db311a00", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_repair-bench_816a6914", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.29937", "paper": "https://arxiv.org/abs/2606.29937", "pdf": "https://arxiv.org/pdf/2606.29937", "project": null, "report": "https://arxiv.org/abs/2606.29937"}, "metrics": [], "motivation": "Understanding how users perceive and respond to robot failures is essential for building robust and trustworthy robot systems.", "name": "REPAIR-Bench", "oneLine": "REPAIR-Bench evaluates robot error perception and recovery in human-robot interaction. It includes 214 interaction trials from 41 participants with four induced failure types, synchronized facial action units, head pose, speech transcripts, and post-interaction reports. Three tasks cover failure detection across sessions, failure-type classification, and recovery prediction.", "paperTitle": "REPAIR-Bench: A Benchmark for Robot Error Perception And Interaction Recovery", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.29937", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ArXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.29937"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-29", "source": {"authors": ["Giuliano Pioldi", "Yashika Batra", "Arman Ibrayeva", "Yuanchen Bai", "Purnjay Maruur", "Promise Ekpo", "Angelique Taylor"], "categories": ["cs.RO"], "id": "2606.29937", "title": "REPAIR-Bench: A Benchmark for Robot Error Perception And Interaction Recovery", "type": "arxiv", "url": "https://arxiv.org/abs/2606.29937"}, "sourceUpdatedAt": "2026-06-29T08:14:27Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "REPAIR-Bench addresses the lack of unified benchmarks for HRI failures, enabling standardized evaluation of failure detection, classification, and recovery prediction. This supports the development of adaptive and trustworthy robot systems and provides a comparison baseline for future research."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
