{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.00726", "kind": "paper", "url": "https://arxiv.org/abs/2607.00726"}, {"id": "gh:fgt7t6g/av-syncbench", "kind": "repo", "url": "https://github.com/fgt7t6g/AV-SyncBench"}, {"kind": "website", "url": "https://fgt7t6g.github.io/AV-SyncBench"}], "authors": ["Tianhong Zhou", "Mingyang Han", "Boyu Li", "Yuxuan Jiang", "Jiaxin Ye", "Dongxiao Wang", "Haoxiang Shi", "Kunpeng Wang", "Jun Song", "Cheng Yu", "Bo Zheng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.00726", "source_url": "https://arxiv.org/abs/2607.00726"}, "categories": ["General AI", "Multimodal", "cs.CV"], "description": {"en": "AV-SyncBench evaluates audio-visual synchronization by separating temporal and semantic consistency. It contains 3,269 videos and 38,390 samples across 10 scenarios and 5 tasks, with data filtered and verified for on-screen sound sources."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.00726", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.00726", "title": "AV-SyncBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University", "Alibaba Group (China)", "Fudan University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.00726", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.00726", "source_url": "https://openalex.org/W7167024464"}, "key": "claire-radar:2607.00726", "modality": null, "name": "AV-SyncBench", "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_av-syncbench_20190a72", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "96b0f0bf35b25963a59eec9cbef2841072173f435a8976208f2116deb4214447", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.00726"}, "publisher": null, "released": "2026-07-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.00726", "source_url": "https://arxiv.org/abs/2607.00726"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-00726", "source": "claire_radar", "source_benchmark_id": "2607.00726", "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": "https://github.com/fgt7t6g/AV-SyncBench", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.00726", "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", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "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": "34dda38356605d3475f21bd7a31babfcb03e38ef2bf133e7362bcc77ae5f0f2a", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AV-SyncBench evaluates audio-visual synchronization by separating temporal and semantic consistency. It contains 3,269 videos and 38,390 samples across 10 scenarios and 5 tasks, with data filtered and verified for on-screen sound sources.", "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", "public artifact URL"], "snippet": "We propose AV-SyncBench, the first benchmark to fully separate temporal and semantic evaluation for audio-visual synchronization."}, "familyId": "bmf_e3adb616e734", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/fgt7t6g/AV-SyncBench", "url": "https://fgt7t6g.github.io/AV-SyncBench"}], "scope": "benchmark_repo", "url": "https://github.com/fgt7t6g/AV-SyncBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_av-syncbench_20190a72", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/fgt7t6g/AV-SyncBench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.00726", "paper": "https://arxiv.org/abs/2607.00726", "pdf": "https://arxiv.org/pdf/2607.00726", "project": "https://fgt7t6g.github.io/AV-SyncBench", "report": "https://arxiv.org/abs/2607.00726"}, "metrics": [], "motivation": "Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks.", "name": "AV-SyncBench", "oneLine": "AV-SyncBench evaluates audio-visual synchronization by separating temporal and semantic consistency. It contains 3,269 videos and 38,390 samples across 10 scenarios and 5 tasks, with data filtered and verified for on-screen sound sources.", "paperTitle": "AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by Interspeech 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.00726", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Interspeech 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-01", "source": {"authors": ["Tianhong Zhou", "Mingyang Han", "Boyu Li", "Yuxuan Jiang", "Jiaxin Ye", "Dongxiao Wang", "Haoxiang Shi", "Kunpeng Wang", "Jun Song", "Cheng Yu", "Bo Zheng"], "categories": ["cs.CV", "cs.SD"], "id": "2607.00726", "title": "AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization", "type": "arxiv", "url": "https://arxiv.org/abs/2607.00726"}, "sourceUpdatedAt": "2026-07-01T10:12:25Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted by Interspeech 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted by Interspeech 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.00726"}], "reviewStatus": "accepted", "venueName": "Interspeech 2026"}], "whyItMatters": "Existing AV feature extraction evaluations are coupled, preventing independent assessment of temporal and semantic alignment. AV-SyncBench provides a decoupled benchmark to quantify feature quality for alignment and downstream tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
