{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AGWJTH2UQOYISVSX7KO5TFIXXM","short_pith_number":"pith:AGWJTH2U","schema_version":"1.0","canonical_sha256":"01ac999f5483b0895657fa9dd99517bb264f0c0320747c9f01ece2e488c330cc","source":{"kind":"arxiv","id":"2404.10301","version":2},"attestation_state":"computed","paper":{"title":"Long-form music generation with latent diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Zach Evans, Zack Zukowski","submitted_at":"2024-04-16T06:09:33Z","abstract_excerpt":"Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure from text prompts. We show that by training a generative model on long temporal contexts it is possible to produce long-form music of up to 4m45s. Our model consists of a diffusion-transformer operating on a highly downsampled continuous latent representation (latent rate of 21.5Hz). It obtains state-of-the-art generations according to metrics on audio quality and prompt alignment, and subjective tests reveal that it produces "},"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":"2404.10301","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-16T06:09:33Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d2984a4292fda2f83b88e3f5a5b0cde5de27a1900cde79e0e9292484ac958444","abstract_canon_sha256":"ee395df3c23eb7ef8dc7af11930b784c4ba5569bada8c60f783abf152e3af306"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:33.122002Z","signature_b64":"mXUNPlBXNEr2I89h7ITDQrmNFyyGNr1BsXBtu95U4F6cyv27KgI76bMRZgH3xRVOfVwCpxVac36b54x9A+HvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01ac999f5483b0895657fa9dd99517bb264f0c0320747c9f01ece2e488c330cc","last_reissued_at":"2026-07-05T08:49:33.121519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:33.121519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-form music generation with latent diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Zach Evans, Zack Zukowski","submitted_at":"2024-04-16T06:09:33Z","abstract_excerpt":"Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure from text prompts. We show that by training a generative model on long temporal contexts it is possible to produce long-form music of up to 4m45s. Our model consists of a diffusion-transformer operating on a highly downsampled continuous latent representation (latent rate of 21.5Hz). It obtains state-of-the-art generations according to metrics on audio quality and prompt alignment, and subjective tests reveal that it produces "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10301","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/2404.10301/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":"2404.10301","created_at":"2026-07-05T08:49:33.121578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10301v2","created_at":"2026-07-05T08:49:33.121578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10301","created_at":"2026-07-05T08:49:33.121578+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGWJTH2UQOYI","created_at":"2026-07-05T08:49:33.121578+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGWJTH2UQOYISVSX","created_at":"2026-07-05T08:49:33.121578+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGWJTH2U","created_at":"2026-07-05T08:49:33.121578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":111,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12555","citing_title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22717","citing_title":"Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13404","citing_title":"Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM","json":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM.json","graph_json":"https://pith.science/api/pith-number/AGWJTH2UQOYISVSX7KO5TFIXXM/graph.json","events_json":"https://pith.science/api/pith-number/AGWJTH2UQOYISVSX7KO5TFIXXM/events.json","paper":"https://pith.science/paper/AGWJTH2U"},"agent_actions":{"view_html":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM","download_json":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM.json","view_paper":"https://pith.science/paper/AGWJTH2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10301&json=true","fetch_graph":"https://pith.science/api/pith-number/AGWJTH2UQOYISVSX7KO5TFIXXM/graph.json","fetch_events":"https://pith.science/api/pith-number/AGWJTH2UQOYISVSX7KO5TFIXXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM/action/storage_attestation","attest_author":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM/action/author_attestation","sign_citation":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM/action/citation_signature","submit_replication":"https://pith.science/pith/AGWJTH2UQOYISVSX7KO5TFIXXM/action/replication_record"}},"created_at":"2026-07-05T08:49:33.121578+00:00","updated_at":"2026-07-05T08:49:33.121578+00:00"}