{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5GAO4FCYTYORDNPRE6N2RHCZEP","short_pith_number":"pith:5GAO4FCY","schema_version":"1.0","canonical_sha256":"e980ee14589e1d11b5f1279ba89c5923fe3197fbcb4f0498a5ced112730aad98","source":{"kind":"arxiv","id":"2405.09901","version":1},"attestation_state":"computed","paper":{"title":"Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Lejun Min, Ziyu Wang","submitted_at":"2024-05-16T08:48:23Z","abstract_excerpt":"Recent deep music generation studies have put much emphasis on long-term generation with structures. However, we are yet to see high-quality, well-structured whole-song generation. In this paper, we make the first attempt to model a full music piece under the realization of compositional hierarchy. With a focus on symbolic representations of pop songs, we define a hierarchical language, in which each level of hierarchy focuses on the semantics and context dependency at a certain music scope. The high-level languages reveal whole-song form, phrase, and cadence, whereas the low-level languages f"},"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":"2405.09901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-16T08:48:23Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"00646dcd644861056ffaac08d220b0d70c9a7c334f299b3921ca2a7efb7706c3","abstract_canon_sha256":"8c41c72647b3fd6de75f4483b28fc61cecdd0cc924282ad89661dd845fe33859"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:50.320075Z","signature_b64":"x2MJaDv+CSyUswyt45Swf2qcoZhcJzyZv40x7ZGqeM9cIoEx6xndoVbZr3w/2eIom9+i0gqVMaZxQgC4X48MDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e980ee14589e1d11b5f1279ba89c5923fe3197fbcb4f0498a5ced112730aad98","last_reissued_at":"2026-07-05T08:19:50.319647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:50.319647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Lejun Min, Ziyu Wang","submitted_at":"2024-05-16T08:48:23Z","abstract_excerpt":"Recent deep music generation studies have put much emphasis on long-term generation with structures. However, we are yet to see high-quality, well-structured whole-song generation. In this paper, we make the first attempt to model a full music piece under the realization of compositional hierarchy. With a focus on symbolic representations of pop songs, we define a hierarchical language, in which each level of hierarchy focuses on the semantics and context dependency at a certain music scope. The high-level languages reveal whole-song form, phrase, and cadence, whereas the low-level languages f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09901","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/2405.09901/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":"2405.09901","created_at":"2026-07-05T08:19:50.319704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09901v1","created_at":"2026-07-05T08:19:50.319704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09901","created_at":"2026-07-05T08:19:50.319704+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GAO4FCYTYOR","created_at":"2026-07-05T08:19:50.319704+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GAO4FCYTYORDNPR","created_at":"2026-07-05T08:19:50.319704+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GAO4FCY","created_at":"2026-07-05T08:19:50.319704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.03612","citing_title":"Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP","json":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP.json","graph_json":"https://pith.science/api/pith-number/5GAO4FCYTYORDNPRE6N2RHCZEP/graph.json","events_json":"https://pith.science/api/pith-number/5GAO4FCYTYORDNPRE6N2RHCZEP/events.json","paper":"https://pith.science/paper/5GAO4FCY"},"agent_actions":{"view_html":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP","download_json":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP.json","view_paper":"https://pith.science/paper/5GAO4FCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09901&json=true","fetch_graph":"https://pith.science/api/pith-number/5GAO4FCYTYORDNPRE6N2RHCZEP/graph.json","fetch_events":"https://pith.science/api/pith-number/5GAO4FCYTYORDNPRE6N2RHCZEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP/action/storage_attestation","attest_author":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP/action/author_attestation","sign_citation":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP/action/citation_signature","submit_replication":"https://pith.science/pith/5GAO4FCYTYORDNPRE6N2RHCZEP/action/replication_record"}},"created_at":"2026-07-05T08:19:50.319704+00:00","updated_at":"2026-07-05T08:19:50.319704+00:00"}