{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.01667", "kind": "paper", "url": "https://arxiv.org/abs/2607.01667"}], "authors": ["Chen Zhao", "Jiajun Ma", "Qilong Huang", "Tiehan Fan", "Hongyu Li", "Zhuoliang Kang", "Xiaoming Wei", "Jian Yang", "Ying Tai"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.01667", "source_url": "https://arxiv.org/abs/2607.01667"}, "categories": ["General AI", "Reasoning", "Safety", "Vision & 3D"], "description": {"en": "TCA-Bench is a diagnostic benchmark for evaluating audiovisual binding and temporal relational reasoning in video captioning models, using a decoupled evaluation protocol."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.01667", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.01667", "title": "TCA-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.01667", "modality": null, "name": "TCA-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_tca-bench_07c28360", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a1dcefc1fbe858b79c50c22a024224bd3717908e6ed90e94ce40fd2ec3eafc29", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.01667"}, "publisher": null, "released": "2026-07-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.01667", "source_url": "https://arxiv.org/abs/2607.01667"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-01667", "source": "claire_radar", "source_benchmark_id": "2607.01667", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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/2607.01667", "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": "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": "0aabbac870ed441d764414f0936488bb2739d0a7f1cec44d73dbfb6e9923b736", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TCA-Bench is a diagnostic benchmark for evaluating audiovisual binding and temporal relational reasoning in video captioning models, using a decoupled evaluation protocol.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Furthermore, we present TCA-Bench, a diagnostic benchmark utilizing a Decoupled Evaluation Protocol to isolate and quantify model proficiency in audiovisual binding and temporal relational reasoning."}, "familyId": "bmf_82f0e5522516", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_tca-bench_07c28360", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.01667", "paper": "https://arxiv.org/abs/2607.01667", "pdf": "https://arxiv.org/pdf/2607.01667", "project": null, "report": "https://arxiv.org/abs/2607.01667"}, "metrics": [], "motivation": "While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a formidable challenge.", "name": "TCA-Bench", "oneLine": "TCA-Bench is a diagnostic benchmark for evaluating audiovisual binding and temporal relational reasoning in video captioning models, using a decoupled evaluation protocol.", "paperTitle": "Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.01667", "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": "2026-07-02", "source": {"authors": ["Chen Zhao", "Jiajun Ma", "Qilong Huang", "Tiehan Fan", "Hongyu Li", "Zhuoliang Kang", "Xiaoming Wei", "Jian Yang", "Ying Tai"], "categories": ["cs.CV"], "id": "2607.01667", "title": "Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning", "type": "arxiv", "url": "https://arxiv.org/abs/2607.01667"}, "sourceUpdatedAt": "2026-07-02T03:47:45Z", "topics": ["Safety", "Reasoning"], "venueAttempts": [], "whyItMatters": "It addresses the need for fine-grained evaluation of temporal and cross-modal alignment in audiovisual captioning, offering a protocol to isolate specific model capabilities."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
