{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.13056", "kind": "paper", "url": "https://arxiv.org/abs/2607.13056"}], "authors": ["Chang Liu", "Jiawei Zhang", "Tao Zhang", "Ye Wang", "Hongyu Zhou", "Qin Jin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.13056", "source_url": "https://arxiv.org/abs/2607.13056"}, "categories": ["Robotics", "Robotics & Embodied AI"], "description": {"en": "HRIBench evaluates intent-aware human-robot collaboration through structured scenario scripts covering roles of Instructor, Collaborator, and Intruder, with 13 tasks and 650 episodes, scoring synchronization, responsiveness, protocol compliance, and safety."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.13056", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.13056", "title": "HRIBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Renmin University of China", "Beijing Normal University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.13056", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.13056", "source_url": "https://openalex.org/W7168738206"}, "key": "claire-radar:2607.13056", "modality": null, "name": "HRIBench", "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_hribench_c65825aa", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3bc77b826044b314fb029e7bd8873b30122aacfcb072a08e3fe2ba3478529e78", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.13056"}, "publisher": null, "released": "2026-07-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.13056", "source_url": "https://arxiv.org/abs/2607.13056"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-13056", "source": "claire_radar", "source_benchmark_id": "2607.13056", "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/2607.13056", "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": "2026-10-04", "state": "stale"}}, "status": "stale"}, "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": "7e1e7e0b42abdc53a3334f4312f2089ded4d9900e0e8dc77aa433188ecd3dd9d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "HRIBench evaluates intent-aware human-robot collaboration through structured scenario scripts covering roles of Instructor, Collaborator, and Intruder, with 13 tasks and 650 episodes, scoring synchronization, responsiveness, protocol compliance, and safety.", "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": "To address this gap, we introduce HRIBench, a diagnostic benchmark for intent-aware human-robot collaboration based on executable interaction scenarios."}, "familyId": "bmf_9b6d4c3d73e5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_hribench_c65825aa", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.13056", "paper": "https://arxiv.org/abs/2607.13056", "pdf": "https://arxiv.org/pdf/2607.13056", "project": null, "report": "https://arxiv.org/abs/2607.13056"}, "metrics": [], "motivation": "Current vision-language-action (VLA) benchmarks primarily evaluate isolated manipulation skills while leaving human-robot interaction structure largely unmodeled.", "name": "HRIBench", "oneLine": "HRIBench evaluates intent-aware human-robot collaboration through structured scenario scripts covering roles of Instructor, Collaborator, and Intruder, with 13 tasks and 650 episodes, scoring synchronization, responsiveness, protocol compliance, and safety.", "paperTitle": "HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.13056", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "HRIBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.13056"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-05", "source": {"authors": ["Chang Liu", "Jiawei Zhang", "Tao Zhang", "Ye Wang", "Hongyu Zhou", "Qin Jin"], "categories": ["cs.RO", "cs.LG"], "id": "2607.13056", "title": "HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration", "type": "arxiv", "url": "https://arxiv.org/abs/2607.13056"}, "sourceUpdatedAt": "2026-07-05T09:15:35Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Existing VLA benchmarks focus on isolated manipulation, leaving a gap in evaluating coordination under shared agency. HRIBench provides a standardized protocol for assessing temporal coordination and intent understanding, with evidence that fine-tuning on its data improves real-world task success."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
