{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.30026", "kind": "paper", "url": "https://arxiv.org/abs/2606.30026"}, {"id": "gh:musebench/musebench-code", "kind": "repo", "url": "https://github.com/musebench/musebench-code"}, {"kind": "website", "url": "https://musebench.github.io"}], "authors": ["Yuxuan Fan", "Gyusik Seo", "Jing Hao", "Jaemin Cho", "Mohit Bansal", "Jaehong Yoon"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.30026", "source_url": "https://arxiv.org/abs/2606.30026"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "MuseBench evaluates multimodal large language models on intent-level understanding of audiovisual arts, covering cinematic arts, static visual arts, stage performing arts, and game arts with 4,016 questions in single- and multi-select formats."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.30026", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.30026", "title": "MuseBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Nanyang Technological University", "University of Hong Kong", "Johns Hopkins University", "Johns Hopkins University Applied Physics Laboratory", "University of North Carolina Health Care"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.30026", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.30026", "source_url": "https://openalex.org/W7166691412"}, "key": "claire-radar:2606.30026", "modality": null, "name": "MuseBench", "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_musebench_7c930c72", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "5e0272942883633d900e313577ad8b7dde8adae4ba256e6f31e825f472aa3c33", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.30026"}, "publisher": null, "released": "2026-06-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.30026", "source_url": "https://arxiv.org/abs/2606.30026"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-30026", "source": "claire_radar", "source_benchmark_id": "2606.30026", "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": "https://github.com/musebench/musebench-code", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 5, "hfPaperUrl": "https://huggingface.co/papers/2606.30026", "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": "2026-10-04", "state": "stale"}}, "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": "02efd189ac6f4f0d72cba16da7eff21a3083aee28aff4b4f3be33048ddf67c96", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MuseBench evaluates multimodal large language models on intent-level understanding of audiovisual arts, covering cinematic arts, static visual arts, stage performing arts, and game arts with 4,016 questions in single- and multi-select formats.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To address this gap, we introduce Musebench, a comprehensive benchmark designed to evaluate MLLMs on nuanced artistic understanding."}, "familyId": "bmf_a54402b9054c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/musebench/musebench-code", "url": "https://github.com/musebench/musebench-code"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/musebench/musebench-code", "url": "https://huggingface.co/papers/2606.30026"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/musebench/musebench-code", "url": "https://musebench.github.io"}], "scope": "benchmark_repo", "url": "https://github.com/musebench/musebench-code", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_musebench_7c930c72", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/musebench/musebench-code", "data": null, "hfPaper": "https://huggingface.co/papers/2606.30026", "paper": "https://arxiv.org/abs/2606.30026", "pdf": "https://arxiv.org/pdf/2606.30026", "project": "https://musebench.github.io", "report": "https://arxiv.org/abs/2606.30026"}, "metrics": [], "motivation": "Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinations of visual, auditory, and narrative elements (e.g., fear amplified through claustrophobic framing, or grief conveyed through silence and lingering close-ups).", "name": "MuseBench", "oneLine": "MuseBench evaluates multimodal large language models on intent-level understanding of audiovisual arts, covering cinematic arts, static visual arts, stage performing arts, and game arts with 4,016 questions in single- and multi-select formats.", "paperTitle": "MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.30026", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MuseBench project", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/musebench/musebench-code"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-06-29", "source": {"authors": ["Yuxuan Fan", "Gyusik Seo", "Jing Hao", "Jaemin Cho", "Mohit Bansal", "Jaehong Yoon"], "categories": ["cs.CV", "cs.AI"], "id": "2606.30026", "title": "MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2606.30026"}, "sourceUpdatedAt": "2026-06-29T09:27:02Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing video and multimodal benchmarks mostly test perceptual recognition, leaving artistic intent and creative reasoning unevaluated. MuseBench measures a distinct capability gap, providing a reference for progress in creative-domain expertise."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
