{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.28192", "kind": "paper", "url": "https://arxiv.org/abs/2605.28192"}], "authors": ["Ke Xu", "Yuhao Wang", "Ziyang Cheng", "Hongcheng Liu", "Yanfeng Wang", "Yu Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.28192", "source_url": "https://arxiv.org/abs/2605.28192"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "MOV-Bench contains 519 questions requiring multi-hop reasoning over temporally dispersed audio-visual evidence, evaluating omni-modal LLMs on cross-modal reasoning tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.28192", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.28192", "title": "MOV-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.28192", "modality": null, "name": "MOV-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_mov-bench_db8a731e", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "6d9a67ebb51d83422b4359c51e4a3282fbdb99a68dcd09d3aafa258a1b45116a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.28192"}, "publisher": null, "released": "2026-05-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.28192", "source_url": "https://arxiv.org/abs/2605.28192"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-28192", "source": "claire_radar", "source_benchmark_id": "2605.28192", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "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/2605.28192", "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": ["Reasoning"], "confidence": "Medium", "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": "c097da2aa1043f63dd1e2aeae4f8aab528bb6dc2480d3cb2ba68281e33fb4f62", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MOV-Bench contains 519 questions requiring multi-hop reasoning over temporally dispersed audio-visual evidence, evaluating omni-modal LLMs on cross-modal reasoning tasks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "In this work, we introduce MOV-Bench, a benchmark containing 519 carefully curated questions that require multi-hop reasoning over temporally dispersed audio-visual evidence."}, "familyId": "bmf_5a9bcf5cba7a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mov-bench_db8a731e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.28192", "paper": "https://arxiv.org/abs/2605.28192", "pdf": "https://arxiv.org/pdf/2605.28192", "project": null, "report": "https://arxiv.org/abs/2605.28192"}, "metrics": [], "motivation": "Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across both audio and visual streams.", "name": "MOV-Bench", "oneLine": "MOV-Bench contains 519 questions requiring multi-hop reasoning over temporally dispersed audio-visual evidence, evaluating omni-modal LLMs on cross-modal reasoning tasks.", "paperTitle": "Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.28192", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-05-27", "source": {"authors": ["Ke Xu", "Yuhao Wang", "Ziyang Cheng", "Hongcheng Liu", "Yanfeng Wang", "Yu Wang"], "categories": ["cs.AI"], "id": "2605.28192", "title": "Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2605.28192"}, "sourceUpdatedAt": "2026-05-27T09:11:59Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing benchmarks offer limited investigation of multi-hop audio-visual reasoning; MOV-Bench provides a focused evaluation set for this capability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
