{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TSPMC4KCPDJWR7WJHEQCLXKMKX","short_pith_number":"pith:TSPMC4KC","schema_version":"1.0","canonical_sha256":"9c9ec1714278d368fec9392025dd4c55ccbdc122c1161243ce416cb5db4cb8df","source":{"kind":"arxiv","id":"2508.19514","version":1},"attestation_state":"computed","paper":{"title":"MQAD: A Large-Scale Question Answering Dataset for Training Music Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bin Chen, Daiyu Zhang, Ju-Chiang Wang, Quan Lin, Shangjie Li, Zhihao Ouyang","submitted_at":"2025-08-27T02:05:27Z","abstract_excerpt":"Question-answering (QA) is a natural approach for humans to understand a piece of music audio. However, for machines, accessing a large-scale dataset covering diverse aspects of music is crucial, yet challenging, due to the scarcity of publicly available music data of this type. This paper introduces MQAD, a music QA dataset built on the Million Song Dataset (MSD), encompassing a rich array of musical features, including beat, chord, key, structure, instrument, and genre -- across 270,000 tracks, featuring nearly 3 million diverse questions and captions. MQAD distinguishes itself by offering d"},"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":"2508.19514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-27T02:05:27Z","cross_cats_sorted":[],"title_canon_sha256":"a9c6e4c567d3e6589b33439de447ed53f4dc4949cb9ebdb8d710f78d21df9e02","abstract_canon_sha256":"0e3bbda001d508402fd6b2eb9ee33d89e88f095094562078c2cc0561b79ac265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:12.944133Z","signature_b64":"xH/vQOtsgoQPDUf1YFFlsYr6dJ2DVJlARVh9FNRc5n1xlk4RUqlodIyvDbTFkuU+5FXFRtXov07Gxk3OYSYHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c9ec1714278d368fec9392025dd4c55ccbdc122c1161243ce416cb5db4cb8df","last_reissued_at":"2026-07-05T12:00:12.943726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:12.943726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MQAD: A Large-Scale Question Answering Dataset for Training Music Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Bin Chen, Daiyu Zhang, Ju-Chiang Wang, Quan Lin, Shangjie Li, Zhihao Ouyang","submitted_at":"2025-08-27T02:05:27Z","abstract_excerpt":"Question-answering (QA) is a natural approach for humans to understand a piece of music audio. However, for machines, accessing a large-scale dataset covering diverse aspects of music is crucial, yet challenging, due to the scarcity of publicly available music data of this type. This paper introduces MQAD, a music QA dataset built on the Million Song Dataset (MSD), encompassing a rich array of musical features, including beat, chord, key, structure, instrument, and genre -- across 270,000 tracks, featuring nearly 3 million diverse questions and captions. MQAD distinguishes itself by offering d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19514","kind":"arxiv","version":1},"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/2508.19514/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":"2508.19514","created_at":"2026-07-05T12:00:12.943794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19514v1","created_at":"2026-07-05T12:00:12.943794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19514","created_at":"2026-07-05T12:00:12.943794+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSPMC4KCPDJW","created_at":"2026-07-05T12:00:12.943794+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSPMC4KCPDJWR7WJ","created_at":"2026-07-05T12:00:12.943794+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSPMC4KC","created_at":"2026-07-05T12:00:12.943794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX","json":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX.json","graph_json":"https://pith.science/api/pith-number/TSPMC4KCPDJWR7WJHEQCLXKMKX/graph.json","events_json":"https://pith.science/api/pith-number/TSPMC4KCPDJWR7WJHEQCLXKMKX/events.json","paper":"https://pith.science/paper/TSPMC4KC"},"agent_actions":{"view_html":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX","download_json":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX.json","view_paper":"https://pith.science/paper/TSPMC4KC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19514&json=true","fetch_graph":"https://pith.science/api/pith-number/TSPMC4KCPDJWR7WJHEQCLXKMKX/graph.json","fetch_events":"https://pith.science/api/pith-number/TSPMC4KCPDJWR7WJHEQCLXKMKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX/action/storage_attestation","attest_author":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX/action/author_attestation","sign_citation":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX/action/citation_signature","submit_replication":"https://pith.science/pith/TSPMC4KCPDJWR7WJHEQCLXKMKX/action/replication_record"}},"created_at":"2026-07-05T12:00:12.943794+00:00","updated_at":"2026-07-05T12:00:12.943794+00:00"}