{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U6L7SYBORWU3HRZE7Y7G4FT6ZZ","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":"1912cc7b65d1ac85641936171def1bf91a850c35dba8ddb117fc1c640d4f41bd","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:52:53Z","title_canon_sha256":"bfae7d3d728561a8153ecce47917c548b7d91947eb52d594c7a4ed472906b8f1"},"schema_version":"1.0","source":{"id":"2301.11757","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11757","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11757v3","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11757","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"U6L7SYBORWU3","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"U6L7SYBORWU3HRZE","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"U6L7SYBO","created_at":"2026-07-05T07:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:cbb848bcf98827681b4178f0f6b2ab657b1bf76eb0e7c7d14445c73151893426","target":"graph","created_at":"2026-07-05T07:04:12Z","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/2301.11757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bernhard Sch\\\"olkopf, Flavio Schneider, Ojasv Kamal, Zhijing Jin","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:52:53Z","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11757","kind":"arxiv","version":3},"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":"sha256:679b733e4b1ba985fb8ded7877f2fc5d585d3bccabbeab837206826322b10893","target":"record","created_at":"2026-07-05T07:04:12Z","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":"1912cc7b65d1ac85641936171def1bf91a850c35dba8ddb117fc1c640d4f41bd","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:52:53Z","title_canon_sha256":"bfae7d3d728561a8153ecce47917c548b7d91947eb52d594c7a4ed472906b8f1"},"schema_version":"1.0","source":{"id":"2301.11757","kind":"arxiv","version":3}},"canonical_sha256":"a797f9602e8da9b3c724fe3e6e167ece4e80409c3c58ea55b8bc25b6143ab4ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a797f9602e8da9b3c724fe3e6e167ece4e80409c3c58ea55b8bc25b6143ab4ea","first_computed_at":"2026-07-05T07:04:12.453247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:12.453247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ilwkZ2ahsxtNJpoFN4UV4yxwMbJFwp5q0J5iaVAh0hZwfi6jL3DxBBiIeOYmSGYhzwB7vY832v4rUHaZ8I0vAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:12.453751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11757","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:679b733e4b1ba985fb8ded7877f2fc5d585d3bccabbeab837206826322b10893","sha256:cbb848bcf98827681b4178f0f6b2ab657b1bf76eb0e7c7d14445c73151893426"],"state_sha256":"403c375ab6e0076f172dca873b8ab26490da581a7869785598ca57eea89cd791"}