{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.26176", "kind": "paper", "url": "https://arxiv.org/abs/2605.26176"}], "authors": ["Milan Liessens Dujardin", "Song-Ze Yu", "Craver Corbyn Thomas-Smith", "David M. Chan", "Karina Nguyen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.26176", "source_url": "https://arxiv.org/abs/2605.26176"}, "categories": ["General AI", "Speech & Audio", "cs.SD"], "description": {"en": "PitchBench evaluates pitch hearing in audio-language models across 28 experiments spanning absolute and relative pitch perception in sequences and chords, varying acoustic conditions and response formats."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.26176", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.26176", "title": "PitchBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California, Berkeley", "Johnson Center for Child Health and Development"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.26176", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.26176", "source_url": "https://openalex.org/W7162490832"}, "key": "claire-radar:2605.26176", "modality": null, "name": "PitchBench", "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_pitchbench_7fffde93", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "bec98ffc451e6320254f427898b010a938d7b8797c6b867a97172758e042488e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.26176"}, "publisher": null, "released": "2026-05-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.26176", "source_url": "https://arxiv.org/abs/2605.26176"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-26176", "source": "claire_radar", "source_benchmark_id": "2605.26176", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Speech & Audio", "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/2605.26176", "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": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3adb7e98ef93ba2631d3d5782ce14338969a9f02f423d508df118dece5bc5f18", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PitchBench evaluates pitch hearing in audio-language models across 28 experiments spanning absolute and relative pitch perception in sequences and chords, varying acoustic conditions and response formats.", "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": "We introduce PitchBench, an evaluation suite that systematically measures pitch hearing in ALMs."}, "familyId": "bmf_ccf6122c0774", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_pitchbench_7fffde93", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.26176", "paper": "https://arxiv.org/abs/2605.26176", "pdf": "https://arxiv.org/pdf/2605.26176", "project": null, "report": "https://arxiv.org/abs/2605.26176"}, "metrics": [], "motivation": "Audio-language models (ALMs) are increasingly used in real-world applications that require understanding music, from music tutoring and transcription to captioning, recommendation systems, and music production.", "name": "PitchBench", "oneLine": "PitchBench evaluates pitch hearing in audio-language models across 28 experiments spanning absolute and relative pitch perception in sequences and chords, varying acoustic conditions and response formats.", "paperTitle": "PitchBench: Measuring Pitch Hearing in Audio-Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.26176", "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": "2026-05-25", "source": {"authors": ["Milan Liessens Dujardin", "Song-Ze Yu", "Craver Corbyn Thomas-Smith", "David M. Chan", "Karina Nguyen"], "categories": ["cs.SD", "cs.AI"], "id": "2605.26176", "title": "PitchBench: Measuring Pitch Hearing in Audio-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2605.26176"}, "sourceUpdatedAt": "2026-05-25T05:37:15Z", "topics": ["cs.SD"], "venueAttempts": [], "whyItMatters": "Pitch perception is foundational for musical reasoning, yet existing benchmarks probe it indirectly. PitchBench provides a systematic, controlled evaluation to identify limitations in current models and support the development of pitch-aware audio-language systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
