{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U6L7SYBORWU3HRZE7Y7G4FT6ZZ","short_pith_number":"pith:U6L7SYBO","schema_version":"1.0","canonical_sha256":"a797f9602e8da9b3c724fe3e6e167ece4e80409c3c58ea55b8bc25b6143ab4ea","source":{"kind":"arxiv","id":"2301.11757","version":3},"attestation_state":"computed","paper":{"title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bernhard Sch\\\"olkopf, Flavio Schneider, Ojasv Kamal, Zhijing Jin","submitted_at":"2023-01-27T14:52:53Z","abstract_excerpt":"Recent years have seen the rapid development of large generative models for text; however, much less research has explored the connection between text and another \"language\" of communication -- music. Music, much like text, can convey emotions, stories, and ideas, and has its own unique structure and syntax. In our work, we bridge text and music via a text-to-music generation model that is highly efficient, expressive, and can handle long-term structure. Specifically, we develop Mo\\^usai, a cascading two-stage latent diffusion model that can generate multiple minutes of high-quality stereo mus"},"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":"2301.11757","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:52:53Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"bfae7d3d728561a8153ecce47917c548b7d91947eb52d594c7a4ed472906b8f1","abstract_canon_sha256":"1912cc7b65d1ac85641936171def1bf91a850c35dba8ddb117fc1c640d4f41bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:12.453751Z","signature_b64":"ilwkZ2ahsxtNJpoFN4UV4yxwMbJFwp5q0J5iaVAh0hZwfi6jL3DxBBiIeOYmSGYhzwB7vY832v4rUHaZ8I0vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a797f9602e8da9b3c724fe3e6e167ece4e80409c3c58ea55b8bc25b6143ab4ea","last_reissued_at":"2026-07-05T07:04:12.453247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:12.453247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bernhard Sch\\\"olkopf, Flavio Schneider, Ojasv Kamal, Zhijing Jin","submitted_at":"2023-01-27T14:52:53Z","abstract_excerpt":"Recent years have seen the rapid development of large generative models for text; however, much less research has explored the connection between text and another \"language\" of communication -- music. Music, much like text, can convey emotions, stories, and ideas, and has its own unique structure and syntax. In our work, we bridge text and music via a text-to-music generation model that is highly efficient, expressive, and can handle long-term structure. Specifically, we develop Mo\\^usai, a cascading two-stage latent diffusion model that can generate multiple minutes of high-quality stereo mus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11757","kind":"arxiv","version":3},"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/2301.11757/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":"2301.11757","created_at":"2026-07-05T07:04:12.453308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11757v3","created_at":"2026-07-05T07:04:12.453308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11757","created_at":"2026-07-05T07:04:12.453308+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6L7SYBORWU3","created_at":"2026-07-05T07:04:12.453308+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6L7SYBORWU3HRZE","created_at":"2026-07-05T07:04:12.453308+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6L7SYBO","created_at":"2026-07-05T07:04:12.453308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24307","citing_title":"Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24087","citing_title":"NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23727","citing_title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10203","citing_title":"Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ","json":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ.json","graph_json":"https://pith.science/api/pith-number/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/graph.json","events_json":"https://pith.science/api/pith-number/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/events.json","paper":"https://pith.science/paper/U6L7SYBO"},"agent_actions":{"view_html":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ","download_json":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ.json","view_paper":"https://pith.science/paper/U6L7SYBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11757&json=true","fetch_graph":"https://pith.science/api/pith-number/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/action/storage_attestation","attest_author":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/action/author_attestation","sign_citation":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/action/citation_signature","submit_replication":"https://pith.science/pith/U6L7SYBORWU3HRZE7Y7G4FT6ZZ/action/replication_record"}},"created_at":"2026-07-05T07:04:12.453308+00:00","updated_at":"2026-07-05T07:04:12.453308+00:00"}