{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U53XFOSQRAKKUD7Y4QLYNE4FBB","short_pith_number":"pith:U53XFOSQ","schema_version":"1.0","canonical_sha256":"a77772ba508814aa0ff8e4178693850843fde168ccfcc6574443876f4fbed5f4","source":{"kind":"arxiv","id":"2504.00369","version":2},"attestation_state":"computed","paper":{"title":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Julian McAuley, Sean O'Brien, Taylor Berg-Kirkpatrick, Yongyi Zang, Zachary Novack","submitted_at":"2025-04-01T02:34:19Z","abstract_excerpt":"Large Audio Language Models (LALMs), where pretrained text LLMs are finetuned with audio input, have made remarkable progress in music understanding. However, current evaluation methodologies exhibit critical limitations: on the leading Music Question Answering benchmark, MuchoMusic, text-only LLMs without audio perception capabilities achieve surprisingly high accuracy of up to 56.4%, on par or above most LALMs. Furthermore, when presented with random Gaussian noise instead of actual audio, LALMs still perform significantly above chance. These findings suggest existing benchmarks predominantl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.00369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-01T02:34:19Z","cross_cats_sorted":[],"title_canon_sha256":"9da7080edd88062f561402164d7ec1baaf65fd436096dfd63afad93885d2baad","abstract_canon_sha256":"67b677307285d2821e404243c3164c5b0c81ee4beefc0309545aad7ecf6fda4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:42.546874Z","signature_b64":"+b3QaOvM/H0YasOQSbh2Y/hsFNZUN+Oo06AdbxCUdE448IN+f85vQy/7CMlyoPbGr+piwAOFks3drFSkxbqwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77772ba508814aa0ff8e4178693850843fde168ccfcc6574443876f4fbed5f4","last_reissued_at":"2026-07-05T11:18:42.546456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:42.546456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are you really listening? Boosting Perceptual Awareness in Music-QA Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Julian McAuley, Sean O'Brien, Taylor Berg-Kirkpatrick, Yongyi Zang, Zachary Novack","submitted_at":"2025-04-01T02:34:19Z","abstract_excerpt":"Large Audio Language Models (LALMs), where pretrained text LLMs are finetuned with audio input, have made remarkable progress in music understanding. However, current evaluation methodologies exhibit critical limitations: on the leading Music Question Answering benchmark, MuchoMusic, text-only LLMs without audio perception capabilities achieve surprisingly high accuracy of up to 56.4%, on par or above most LALMs. Furthermore, when presented with random Gaussian noise instead of actual audio, LALMs still perform significantly above chance. These findings suggest existing benchmarks predominantl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00369","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.00369/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.00369","created_at":"2026-07-05T11:18:42.546510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00369v2","created_at":"2026-07-05T11:18:42.546510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00369","created_at":"2026-07-05T11:18:42.546510+00:00"},{"alias_kind":"pith_short_12","alias_value":"U53XFOSQRAKK","created_at":"2026-07-05T11:18:42.546510+00:00"},{"alias_kind":"pith_short_16","alias_value":"U53XFOSQRAKKUD7Y","created_at":"2026-07-05T11:18:42.546510+00:00"},{"alias_kind":"pith_short_8","alias_value":"U53XFOSQ","created_at":"2026-07-05T11:18:42.546510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31338","citing_title":"Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20641","citing_title":"Investigating Modality Contribution in Audio LLMs for Music","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09721","citing_title":"Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17765","citing_title":"Qwen3-Omni Technical Report","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15804","citing_title":"Qwen3.5-Omni Technical Report","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB","json":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB.json","graph_json":"https://pith.science/api/pith-number/U53XFOSQRAKKUD7Y4QLYNE4FBB/graph.json","events_json":"https://pith.science/api/pith-number/U53XFOSQRAKKUD7Y4QLYNE4FBB/events.json","paper":"https://pith.science/paper/U53XFOSQ"},"agent_actions":{"view_html":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB","download_json":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB.json","view_paper":"https://pith.science/paper/U53XFOSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00369&json=true","fetch_graph":"https://pith.science/api/pith-number/U53XFOSQRAKKUD7Y4QLYNE4FBB/graph.json","fetch_events":"https://pith.science/api/pith-number/U53XFOSQRAKKUD7Y4QLYNE4FBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB/action/storage_attestation","attest_author":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB/action/author_attestation","sign_citation":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB/action/citation_signature","submit_replication":"https://pith.science/pith/U53XFOSQRAKKUD7Y4QLYNE4FBB/action/replication_record"}},"created_at":"2026-07-05T11:18:42.546510+00:00","updated_at":"2026-07-05T11:18:42.546510+00:00"}