{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JXZMQBVZRYKD6JWNWSDRSIN4GH","short_pith_number":"pith:JXZMQBVZ","schema_version":"1.0","canonical_sha256":"4df2c806b98e143f26cdb4871921bc31fb33a60e19162e52266637b9e68e1ce1","source":{"kind":"arxiv","id":"2510.18416","version":2},"attestation_state":"computed","paper":{"title":"SegTune: Structured and Fine-Grained Control for Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Haorui Zheng, Joanna Wang, Pengfei Cai, Pengfei Wan, Teng Ma, Xu Li, Zhongliang Liu, Zihao Ji","submitted_at":"2025-10-21T08:48:04Z","abstract_excerpt":"Recent advancements in song generation have shown promising results in generating songs from lyrics and/or global text prompts. However, most existing systems lack the ability to model the temporally varying attributes of songs, limiting fine-grained control over musical structure and dynamics. In this paper, we propose SegTune, a non-autoregressive framework for structured and controllable song generation. SegTune enables segment-level control by allowing users or large language models to specify local musical descriptions aligned to song sections.The segmental prompts are injected into the m"},"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":"2510.18416","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-21T08:48:04Z","cross_cats_sorted":[],"title_canon_sha256":"5096e74ba7fe4d84450f16a5c6fbcf0b093ad66e210f79addd6eb0f7558f6d17","abstract_canon_sha256":"8ce83456296d709a1fe0776f4090f6072a0f385774653f682ae94a15b584f970"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:37.257731Z","signature_b64":"Dc99c/lQK+L+LLH9EReBwx2xYaOZuI/P0WOgRiIxN7tIFJ65VoigqsCIjnpZM2hCvbbe9OlwxQtBC22KdsEcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df2c806b98e143f26cdb4871921bc31fb33a60e19162e52266637b9e68e1ce1","last_reissued_at":"2026-05-29T02:05:37.257195Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:37.257195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegTune: Structured and Fine-Grained Control for Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Haorui Zheng, Joanna Wang, Pengfei Cai, Pengfei Wan, Teng Ma, Xu Li, Zhongliang Liu, Zihao Ji","submitted_at":"2025-10-21T08:48:04Z","abstract_excerpt":"Recent advancements in song generation have shown promising results in generating songs from lyrics and/or global text prompts. However, most existing systems lack the ability to model the temporally varying attributes of songs, limiting fine-grained control over musical structure and dynamics. In this paper, we propose SegTune, a non-autoregressive framework for structured and controllable song generation. SegTune enables segment-level control by allowing users or large language models to specify local musical descriptions aligned to song sections.The segmental prompts are injected into the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18416","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/2510.18416/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":"2510.18416","created_at":"2026-05-29T02:05:37.257263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.18416v2","created_at":"2026-05-29T02:05:37.257263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18416","created_at":"2026-05-29T02:05:37.257263+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXZMQBVZRYKD","created_at":"2026-05-29T02:05:37.257263+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXZMQBVZRYKD6JWN","created_at":"2026-05-29T02:05:37.257263+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXZMQBVZ","created_at":"2026-05-29T02:05:37.257263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH","json":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH.json","graph_json":"https://pith.science/api/pith-number/JXZMQBVZRYKD6JWNWSDRSIN4GH/graph.json","events_json":"https://pith.science/api/pith-number/JXZMQBVZRYKD6JWNWSDRSIN4GH/events.json","paper":"https://pith.science/paper/JXZMQBVZ"},"agent_actions":{"view_html":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH","download_json":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH.json","view_paper":"https://pith.science/paper/JXZMQBVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.18416&json=true","fetch_graph":"https://pith.science/api/pith-number/JXZMQBVZRYKD6JWNWSDRSIN4GH/graph.json","fetch_events":"https://pith.science/api/pith-number/JXZMQBVZRYKD6JWNWSDRSIN4GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH/action/storage_attestation","attest_author":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH/action/author_attestation","sign_citation":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH/action/citation_signature","submit_replication":"https://pith.science/pith/JXZMQBVZRYKD6JWNWSDRSIN4GH/action/replication_record"}},"created_at":"2026-05-29T02:05:37.257263+00:00","updated_at":"2026-05-29T02:05:37.257263+00:00"}