{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FQD3MJBLJG5PAUBZY4MRXYOMPW","short_pith_number":"pith:FQD3MJBL","schema_version":"1.0","canonical_sha256":"2c07b6242b49baf05039c7191be1cc7d9f76e15028c048e1baa81775cef2bb34","source":{"kind":"arxiv","id":"2507.12890","version":2},"attestation_state":"computed","paper":{"title":"DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunbo Hao, Guobin Ma, Huakang Chen, Jian Luan, Jixun Yao, Lei Xie, Meng Meng, Shuai Wang, Yuepeng Jiang, Ziqian Ning","submitted_at":"2025-07-17T08:18:55Z","abstract_excerpt":"Songs, as a central form of musical art, exemplify the richness of human intelligence and creativity. While recent advances in generative modeling have enabled notable progress in long-form song generation, current systems for full-length song synthesis still face major challenges, including data imbalance, insufficient controllability, and inconsistent musical quality. DiffRhythm, a pioneering diffusion-based model, advanced the field by generating full-length songs with expressive vocals and accompaniment. However, its performance was constrained by an unbalanced model training dataset and l"},"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":"2507.12890","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-17T08:18:55Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"512b64a4302447b8bcfec732ebf1dbad6fa6959d4f485da73aef449e645a129c","abstract_canon_sha256":"26f0bc7852f5a286f51c24bcc89b33fc211294236d9a0297a1e2b92291b1570b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:32.825125Z","signature_b64":"ZshB2uWEYpO9GSNVG5irldLxswjO3i5h4olcEH8hSlqR+EI29wjEwpnbhY0cg7qoa937UvqGkag8N0cZd4bECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c07b6242b49baf05039c7191be1cc7d9f76e15028c048e1baa81775cef2bb34","last_reissued_at":"2026-07-05T11:42:32.824567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:32.824567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunbo Hao, Guobin Ma, Huakang Chen, Jian Luan, Jixun Yao, Lei Xie, Meng Meng, Shuai Wang, Yuepeng Jiang, Ziqian Ning","submitted_at":"2025-07-17T08:18:55Z","abstract_excerpt":"Songs, as a central form of musical art, exemplify the richness of human intelligence and creativity. While recent advances in generative modeling have enabled notable progress in long-form song generation, current systems for full-length song synthesis still face major challenges, including data imbalance, insufficient controllability, and inconsistent musical quality. DiffRhythm, a pioneering diffusion-based model, advanced the field by generating full-length songs with expressive vocals and accompaniment. However, its performance was constrained by an unbalanced model training dataset and l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12890","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/2507.12890/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":"2507.12890","created_at":"2026-07-05T11:42:32.824650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12890v2","created_at":"2026-07-05T11:42:32.824650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12890","created_at":"2026-07-05T11:42:32.824650+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQD3MJBLJG5P","created_at":"2026-07-05T11:42:32.824650+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQD3MJBLJG5PAUBZ","created_at":"2026-07-05T11:42:32.824650+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQD3MJBL","created_at":"2026-07-05T11:42:32.824650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06986","citing_title":"MMGenre: Benchmarking Singing Voice Synthesis across Multiple Musical Genres","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07015","citing_title":"Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30642","citing_title":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02797","citing_title":"SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW","json":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW.json","graph_json":"https://pith.science/api/pith-number/FQD3MJBLJG5PAUBZY4MRXYOMPW/graph.json","events_json":"https://pith.science/api/pith-number/FQD3MJBLJG5PAUBZY4MRXYOMPW/events.json","paper":"https://pith.science/paper/FQD3MJBL"},"agent_actions":{"view_html":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW","download_json":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW.json","view_paper":"https://pith.science/paper/FQD3MJBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12890&json=true","fetch_graph":"https://pith.science/api/pith-number/FQD3MJBLJG5PAUBZY4MRXYOMPW/graph.json","fetch_events":"https://pith.science/api/pith-number/FQD3MJBLJG5PAUBZY4MRXYOMPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW/action/storage_attestation","attest_author":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW/action/author_attestation","sign_citation":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW/action/citation_signature","submit_replication":"https://pith.science/pith/FQD3MJBLJG5PAUBZY4MRXYOMPW/action/replication_record"}},"created_at":"2026-07-05T11:42:32.824650+00:00","updated_at":"2026-07-05T11:42:32.824650+00:00"}