{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D6NUUOH526EYIZHIMLSFDUJ2RH","short_pith_number":"pith:D6NUUOH5","schema_version":"1.0","canonical_sha256":"1f9b4a38fdd7898464e862e451d13a89eecfd2f23b70436ac5d2b17c0c4202c7","source":{"kind":"arxiv","id":"2606.02638","version":1},"attestation_state":"computed","paper":{"title":"SegTune: Structured and Fine-Grained Control for Song Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Haorui Zheng, Pengfei Cai, Pengfei Wan, Xu Li, Yuejiao Wang, Zewen Song, Zhongliang Liu, Zihao Ji","submitted_at":"2026-05-31T06:01:15Z","abstract_excerpt":"Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts. However, most systems fail to model temporally varying attributes of songs, severely limiting fine-grained control over musical structure and dynamics. To address this, we propose SegTune, a Diffusion Transformer-based framework enabling structured and fine-grained controllability by allowing users or large language models (LLMs) to specify local musical descriptions aligned to song segments. These segment prompts are temporally broadcast to corresponding time windows, while gl"},"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":"2606.02638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-31T06:01:15Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5096e74ba7fe4d84450f16a5c6fbcf0b093ad66e210f79addd6eb0f7558f6d17","abstract_canon_sha256":"0769f315212f8756a3dcbdbe2678622cc6519ee7207eaee8ace27ba7e827dab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T00:05:05.338151Z","signature_b64":"d0gjqpJYuiogsrCNYj4mAgMBaglsJj1R/a8NX9ty8zNKlWpujvgRJZE/uUiVqgJXRjeNHa4JI8tF/hHEqW9LCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f9b4a38fdd7898464e862e451d13a89eecfd2f23b70436ac5d2b17c0c4202c7","last_reissued_at":"2026-06-03T00:05:05.337752Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T00:05:05.337752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SegTune: Structured and Fine-Grained Control for Song Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Haorui Zheng, Pengfei Cai, Pengfei Wan, Xu Li, Yuejiao Wang, Zewen Song, Zhongliang Liu, Zihao Ji","submitted_at":"2026-05-31T06:01:15Z","abstract_excerpt":"Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts. However, most systems fail to model temporally varying attributes of songs, severely limiting fine-grained control over musical structure and dynamics. To address this, we propose SegTune, a Diffusion Transformer-based framework enabling structured and fine-grained controllability by allowing users or large language models (LLMs) to specify local musical descriptions aligned to song segments. These segment prompts are temporally broadcast to corresponding time windows, while gl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02638","kind":"arxiv","version":1},"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/2606.02638/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":"2606.02638","created_at":"2026-06-03T00:05:05.337807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02638v1","created_at":"2026-06-03T00:05:05.337807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02638","created_at":"2026-06-03T00:05:05.337807+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6NUUOH526EY","created_at":"2026-06-03T00:05:05.337807+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6NUUOH526EYIZHI","created_at":"2026-06-03T00:05:05.337807+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6NUUOH5","created_at":"2026-06-03T00:05:05.337807+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/D6NUUOH526EYIZHIMLSFDUJ2RH","json":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH.json","graph_json":"https://pith.science/api/pith-number/D6NUUOH526EYIZHIMLSFDUJ2RH/graph.json","events_json":"https://pith.science/api/pith-number/D6NUUOH526EYIZHIMLSFDUJ2RH/events.json","paper":"https://pith.science/paper/D6NUUOH5"},"agent_actions":{"view_html":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH","download_json":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH.json","view_paper":"https://pith.science/paper/D6NUUOH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02638&json=true","fetch_graph":"https://pith.science/api/pith-number/D6NUUOH526EYIZHIMLSFDUJ2RH/graph.json","fetch_events":"https://pith.science/api/pith-number/D6NUUOH526EYIZHIMLSFDUJ2RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH/action/storage_attestation","attest_author":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH/action/author_attestation","sign_citation":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH/action/citation_signature","submit_replication":"https://pith.science/pith/D6NUUOH526EYIZHIMLSFDUJ2RH/action/replication_record"}},"created_at":"2026-06-03T00:05:05.337807+00:00","updated_at":"2026-06-03T00:05:05.337807+00:00"}