{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LDEPDHFSLSCQGRJTMMIHC7PT6K","short_pith_number":"pith:LDEPDHFS","schema_version":"1.0","canonical_sha256":"58c8f19cb25c850345336310717df3f29007c5160df318cd4104e538ebf5f40c","source":{"kind":"arxiv","id":"2409.00587","version":2},"attestation_state":"computed","paper":{"title":"FLUX that Plays Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Changqian Yu, Junshi Huang, Mingyuan Fan, Zhengcong Fei","submitted_at":"2024-09-01T02:43:33Z","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. "},"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":"2409.00587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T02:43:33Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"2a842a9125834f5b89b58cec073c1c0cb7ff762dc8440eb4ba3dbe584de3059e","abstract_canon_sha256":"d405776b8da5b9389ab9522960dd6bbed111c4792ea87d44f556563b541ad269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:15.434757Z","signature_b64":"dBt1JR2uGKxOz6RiJ0rdOZirGa1dwYpaagNySKZQR2NzkFNYUhh4mrbdhKIoryw34z1bUBYzyZlLn0k6DUucCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58c8f19cb25c850345336310717df3f29007c5160df318cd4104e538ebf5f40c","last_reissued_at":"2026-07-05T09:52:15.434268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:15.434268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLUX that Plays Music","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Changqian Yu, Junshi Huang, Mingyuan Fan, Zhengcong Fei","submitted_at":"2024-09-01T02:43:33Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00587","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/2409.00587/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":"2409.00587","created_at":"2026-07-05T09:52:15.434329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00587v2","created_at":"2026-07-05T09:52:15.434329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00587","created_at":"2026-07-05T09:52:15.434329+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDEPDHFSLSCQ","created_at":"2026-07-05T09:52:15.434329+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDEPDHFSLSCQGRJT","created_at":"2026-07-05T09:52:15.434329+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDEPDHFS","created_at":"2026-07-05T09:52:15.434329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21670","citing_title":"Improving Text-to-Music Generation with Human Preference Rewards","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01669","citing_title":"UT-AISTimprt submission for ICME 2026 Grand Challenge on Academic Text-to-Music Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30965","citing_title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14765","citing_title":"Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21538","citing_title":"Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21538","citing_title":"Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2508.03448","citing_title":"SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K","json":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K.json","graph_json":"https://pith.science/api/pith-number/LDEPDHFSLSCQGRJTMMIHC7PT6K/graph.json","events_json":"https://pith.science/api/pith-number/LDEPDHFSLSCQGRJTMMIHC7PT6K/events.json","paper":"https://pith.science/paper/LDEPDHFS"},"agent_actions":{"view_html":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K","download_json":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K.json","view_paper":"https://pith.science/paper/LDEPDHFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00587&json=true","fetch_graph":"https://pith.science/api/pith-number/LDEPDHFSLSCQGRJTMMIHC7PT6K/graph.json","fetch_events":"https://pith.science/api/pith-number/LDEPDHFSLSCQGRJTMMIHC7PT6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K/action/storage_attestation","attest_author":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K/action/author_attestation","sign_citation":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K/action/citation_signature","submit_replication":"https://pith.science/pith/LDEPDHFSLSCQGRJTMMIHC7PT6K/action/replication_record"}},"created_at":"2026-07-05T09:52:15.434329+00:00","updated_at":"2026-07-05T09:52:15.434329+00:00"}