{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AGWJTH2UQOYISVSX7KO5TFIXXM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee395df3c23eb7ef8dc7af11930b784c4ba5569bada8c60f783abf152e3af306","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-16T06:09:33Z","title_canon_sha256":"d2984a4292fda2f83b88e3f5a5b0cde5de27a1900cde79e0e9292484ac958444"},"schema_version":"1.0","source":{"id":"2404.10301","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10301","created_at":"2026-07-05T08:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10301v2","created_at":"2026-07-05T08:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10301","created_at":"2026-07-05T08:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"AGWJTH2UQOYI","created_at":"2026-07-05T08:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"AGWJTH2UQOYISVSX","created_at":"2026-07-05T08:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"AGWJTH2U","created_at":"2026-07-05T08:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:71155d333e7f5559e9702e3455aeb57b3f2ee98442bd36fcc7f6666b2ffdbfdd","target":"graph","created_at":"2026-07-05T08:49:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.10301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Zach Evans, Zack Zukowski","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-16T06:09:33Z","title":"Long-form music generation with latent diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10301","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:976ddc7bb0c285fd7ad573473313f5122758ef2ef8c10916b6b298b5eba80f64","target":"record","created_at":"2026-07-05T08:49:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee395df3c23eb7ef8dc7af11930b784c4ba5569bada8c60f783abf152e3af306","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-16T06:09:33Z","title_canon_sha256":"d2984a4292fda2f83b88e3f5a5b0cde5de27a1900cde79e0e9292484ac958444"},"schema_version":"1.0","source":{"id":"2404.10301","kind":"arxiv","version":2}},"canonical_sha256":"01ac999f5483b0895657fa9dd99517bb264f0c0320747c9f01ece2e488c330cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01ac999f5483b0895657fa9dd99517bb264f0c0320747c9f01ece2e488c330cc","first_computed_at":"2026-07-05T08:49:33.121519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:33.121519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mXUNPlBXNEr2I89h7ITDQrmNFyyGNr1BsXBtu95U4F6cyv27KgI76bMRZgH3xRVOfVwCpxVac36b54x9A+HvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:33.122002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10301","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:976ddc7bb0c285fd7ad573473313f5122758ef2ef8c10916b6b298b5eba80f64","sha256:71155d333e7f5559e9702e3455aeb57b3f2ee98442bd36fcc7f6666b2ffdbfdd"],"state_sha256":"7b3dd3bb614afe56395b8fbd2b20136594dc82b50185ae57831ed478ca5d8707"}