{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LDEPDHFSLSCQGRJTMMIHC7PT6K","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":"d405776b8da5b9389ab9522960dd6bbed111c4792ea87d44f556563b541ad269","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T02:43:33Z","title_canon_sha256":"2a842a9125834f5b89b58cec073c1c0cb7ff762dc8440eb4ba3dbe584de3059e"},"schema_version":"1.0","source":{"id":"2409.00587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00587","created_at":"2026-07-05T09:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00587v2","created_at":"2026-07-05T09:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00587","created_at":"2026-07-05T09:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"LDEPDHFSLSCQ","created_at":"2026-07-05T09:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"LDEPDHFSLSCQGRJT","created_at":"2026-07-05T09:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"LDEPDHFS","created_at":"2026-07-05T09:52:15Z"}],"graph_snapshots":[{"event_id":"sha256:0c0ec55ebbbf48d3f99adb28f06006b97b4072365c31cd43ffb99fe1b8087195","target":"graph","created_at":"2026-07-05T09:52:15Z","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/2409.00587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic. Generally, along with design in advanced Flux\\footnote{https://github.com/black-forest-labs/flux} model, we transfers it into a latent VAE space of mel-spectrum. It involves first applying a sequence of independent attention to the double text-music stream, followed by a stacked single music stream for denoised patch prediction. We employ multiple pre-trained text encoders to sufficiently capture caption semantic information as well as inference flexibility. ","authors_text":"Changqian Yu, Junshi Huang, Mingyuan Fan, Zhengcong Fei","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T02:43:33Z","title":"FLUX that Plays Music"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00587","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:d8a7a633e81d58fa2b48d865c5f6aff655cd452aa5d59ae2dc3d618a102a3eb1","target":"record","created_at":"2026-07-05T09:52:15Z","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":"d405776b8da5b9389ab9522960dd6bbed111c4792ea87d44f556563b541ad269","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T02:43:33Z","title_canon_sha256":"2a842a9125834f5b89b58cec073c1c0cb7ff762dc8440eb4ba3dbe584de3059e"},"schema_version":"1.0","source":{"id":"2409.00587","kind":"arxiv","version":2}},"canonical_sha256":"58c8f19cb25c850345336310717df3f29007c5160df318cd4104e538ebf5f40c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58c8f19cb25c850345336310717df3f29007c5160df318cd4104e538ebf5f40c","first_computed_at":"2026-07-05T09:52:15.434268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:15.434268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dBt1JR2uGKxOz6RiJ0rdOZirGa1dwYpaagNySKZQR2NzkFNYUhh4mrbdhKIoryw34z1bUBYzyZlLn0k6DUucCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:15.434757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8a7a633e81d58fa2b48d865c5f6aff655cd452aa5d59ae2dc3d618a102a3eb1","sha256:0c0ec55ebbbf48d3f99adb28f06006b97b4072365c31cd43ffb99fe1b8087195"],"state_sha256":"19321b4f5ae1eb60a00e3aa0970a6275bd0470f12f130ff83eed35c896feb758"}