{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VSH6FDCUT7JIAMNGGRUX3X7SW7","short_pith_number":"pith:VSH6FDCU","schema_version":"1.0","canonical_sha256":"ac8fe28c549fd28031a634697ddff2b7cc0b2eb669a2de26dd828bd033e5bdb5","source":{"kind":"arxiv","id":"2404.06393","version":4},"attestation_state":"computed","paper":{"title":"MuPT: A Generative Symbolic Music Pretrained Transformer","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenghua Lin, Emmanouil Benetos, Fengze Han, Ge Zhang, Gus Xia, Jiaheng Liu, Jie Fu, Junting Zhou, Ka Man Lo, Lejun Min, Ruibin Yuan, Shangda Wu, Shuyue Guo, Stephen W. Huang, Tianyu Zhang, Tianyu Zheng, Wei Xue, Xiang Yue, Xingwei Qu, Xinrun Du, Xueling Liu, Xu Tan, Yiming Liang, Yinghao Ma, Yizhi Li, Yuelin Bai, Ziyang Ma, Ziya Zhou","submitted_at":"2024-04-09T15:35:52Z","abstract_excerpt":"In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Notation, which aligns more closely with their design and strengths, thereby enhancing the model's performance in musical composition. To address the challenges associated with misaligned measures from different tracks during generation, we propose the development of a Synchronized Multi-Track ABC Notation (SMT-ABC Notation), which aims to preserve coh"},"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":"2404.06393","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-09T15:35:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"bc9086cfbc0f2c1b8f727a9171369206d23d2bdcc93519b6bfeaca635159fc2d","abstract_canon_sha256":"690155cfc0f0be3c0ee79c930923c1dfe02676477e30d5048810c817d8d3f84f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:01.282089Z","signature_b64":"gnZKz4mFAP5U2k9J0qqvUgNWMoYkrWKlCUAXFzTSSrUFcGAxEYIbRY3V0kor0DrwFGjXPQBikILNavREy66qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac8fe28c549fd28031a634697ddff2b7cc0b2eb669a2de26dd828bd033e5bdb5","last_reissued_at":"2026-07-05T09:31:01.280898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:01.280898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuPT: A Generative Symbolic Music Pretrained Transformer","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenghua Lin, Emmanouil Benetos, Fengze Han, Ge Zhang, Gus Xia, Jiaheng Liu, Jie Fu, Junting Zhou, Ka Man Lo, Lejun Min, Ruibin Yuan, Shangda Wu, Shuyue Guo, Stephen W. Huang, Tianyu Zhang, Tianyu Zheng, Wei Xue, Xiang Yue, Xingwei Qu, Xinrun Du, Xueling Liu, Xu Tan, Yiming Liang, Yinghao Ma, Yizhi Li, Yuelin Bai, Ziyang Ma, Ziya Zhou","submitted_at":"2024-04-09T15:35:52Z","abstract_excerpt":"In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Notation, which aligns more closely with their design and strengths, thereby enhancing the model's performance in musical composition. To address the challenges associated with misaligned measures from different tracks during generation, we propose the development of a Synchronized Multi-Track ABC Notation (SMT-ABC Notation), which aims to preserve coh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06393","kind":"arxiv","version":4},"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/2404.06393/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":"2404.06393","created_at":"2026-07-05T09:31:01.280954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06393v4","created_at":"2026-07-05T09:31:01.280954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06393","created_at":"2026-07-05T09:31:01.280954+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSH6FDCUT7JI","created_at":"2026-07-05T09:31:01.280954+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSH6FDCUT7JIAMNG","created_at":"2026-07-05T09:31:01.280954+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSH6FDCU","created_at":"2026-07-05T09:31:01.280954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13431","citing_title":"Text2Score: Generating Sheet Music From Textual Prompts","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05343","citing_title":"Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20719","citing_title":"ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7","json":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7.json","graph_json":"https://pith.science/api/pith-number/VSH6FDCUT7JIAMNGGRUX3X7SW7/graph.json","events_json":"https://pith.science/api/pith-number/VSH6FDCUT7JIAMNGGRUX3X7SW7/events.json","paper":"https://pith.science/paper/VSH6FDCU"},"agent_actions":{"view_html":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7","download_json":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7.json","view_paper":"https://pith.science/paper/VSH6FDCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06393&json=true","fetch_graph":"https://pith.science/api/pith-number/VSH6FDCUT7JIAMNGGRUX3X7SW7/graph.json","fetch_events":"https://pith.science/api/pith-number/VSH6FDCUT7JIAMNGGRUX3X7SW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7/action/storage_attestation","attest_author":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7/action/author_attestation","sign_citation":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7/action/citation_signature","submit_replication":"https://pith.science/pith/VSH6FDCUT7JIAMNGGRUX3X7SW7/action/replication_record"}},"created_at":"2026-07-05T09:31:01.280954+00:00","updated_at":"2026-07-05T09:31:01.280954+00:00"}