{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.29300", "kind": "paper", "url": "https://arxiv.org/abs/2605.29300"}, {"id": "gh:sony/mustbench", "kind": "repo", "url": "https://github.com/sony/MusTBench"}], "authors": ["Daeyong Kwon", "Qiyu Wu", "Shinobu Kuriya", "Junghyun Koo", "Shuyang Cui", "Zhi Zhong", "Wei-Hsiang Liao", "Hiromi Wakaki", "Yuki Mitsufuji"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.29300", "source_url": "https://arxiv.org/abs/2605.29300"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "MusTBENCH evaluates temporal grounding in Large Audio-Language Models through five temporally grounded question-answering tasks, validated by music experts, to test alignment with audio regions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.29300", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.29300", "title": "MusTBENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.29300", "modality": null, "name": "MusTBENCH", "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_mustbench_8ac41de6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a28e3d53d4aa6fd367043d0c258157343655ca3bef7b526837b6f03edcb87339", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.29300"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.29300", "source_url": "https://arxiv.org/abs/2605.29300"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-29300", "source": "claire_radar", "source_benchmark_id": "2605.29300", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/sony/MusTBench", "githubScope": "benchmark_repo", "githubStars": 13, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2605.29300", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "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": "53e6a10d7325b477c2f3a6e990e56a1628109bac0a3199f6131f7c9d651ec7b7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MusTBENCH evaluates temporal grounding in Large Audio-Language Models through five temporally grounded question-answering tasks, validated by music experts, to test alignment with audio regions.", "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 MusTBENCH, a music-expert-validated benchmark designed to evaluate temporal grounding in LALMs through five temporally grounded question-answering tasks."}, "familyId": "bmf_246fae86adcc", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-report", "linkedUrl": "https://github.com/sony/MusTBench", "url": "https://arxiv.org/abs/2605.29300"}], "scope": "benchmark_repo", "url": "https://github.com/sony/MusTBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_mustbench_8ac41de6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/sony/MusTBench", "data": null, "hfPaper": "https://huggingface.co/papers/2605.29300", "paper": "https://arxiv.org/abs/2605.29300", "pdf": "https://arxiv.org/pdf/2605.29300", "project": null, "report": "https://arxiv.org/abs/2605.29300"}, "metrics": [], "motivation": "Recent Large Audio-Language Models (LALMs) have demonstrated promising abilities in understanding musical content.", "name": "MusTBENCH", "oneLine": "MusTBENCH evaluates temporal grounding in Large Audio-Language Models through five temporally grounded question-answering tasks, validated by music experts, to test alignment with audio regions.", "paperTitle": "MusTBENCH: Benchmarking and Advancing Temporal Grounding in Music LLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.29300", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Daeyong Kwon", "Qiyu Wu", "Shinobu Kuriya", "Junghyun Koo", "Shuyang Cui", "Zhi Zhong", "Wei-Hsiang Liao", "Hiromi Wakaki", "Yuki Mitsufuji"], "categories": ["cs.CL", "cs.AI", "cs.SD"], "id": "2605.29300", "title": "MusTBENCH: Benchmarking and Advancing Temporal Grounding in Music LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2605.29300"}, "sourceUpdatedAt": "2026-05-28T03:28:16Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Temporal grounding is critical for music understanding, where events are localized. MusTBENCH establishes this as a missing capability and offers a challenging benchmark for improvement."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
