{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DVPLGTKOK22NXYGIZOCDXGDD4W","short_pith_number":"pith:DVPLGTKO","schema_version":"1.0","canonical_sha256":"1d5eb34d4e56b4dbe0c8cb843b9863e594eaee85e7152ede24fbc82d978b428e","source":{"kind":"arxiv","id":"2608.09035","version":1},"attestation_state":"computed","paper":{"title":"MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Jiahe Lei, Jiaxing Yu, Kejun Zhang, Lei Wang, Shulei Ji, Shuyu Li, Wanying Wu, Zihao Wang","submitted_at":"2026-08-10T02:38:42Z","abstract_excerpt":"Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of generated music implicit and difficult to inspect, control, or revise before audio generation. To address this issue, we introduce MusicLayout, an explicit intermediate representation for controlling musical structure in text-to-music generation. MusicLayout describes a musical piece as a time-aligned layout of sections, textures, repetitions, variations, and instrument-level arrangements, serving as an interpretable planning layer between textu"},"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":"2608.09035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-10T02:38:42Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"9a0a74723187bdae46ebd057e0f8833207a7d9247ea15f99b193795302cd0b6d","abstract_canon_sha256":"46301556de67029e190bd2cbca560d0d2272120181a5fbffc20017a0c022e562"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:21:39.152537Z","signature_b64":"lM3hTPd7qi6YXV+79x9AJxI5/L/LVGegzGTuFxnogJqTA30x0PuBlB48cG3RNG59DCsTF/Skk6AFc3FGpG14Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d5eb34d4e56b4dbe0c8cb843b9863e594eaee85e7152ede24fbc82d978b428e","last_reissued_at":"2026-08-11T02:21:39.150678Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:21:39.150678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MusicLayout: Explicit Structural Planning for Controllable Text-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Jiahe Lei, Jiaxing Yu, Kejun Zhang, Lei Wang, Shulei Ji, Shuyu Li, Wanying Wu, Zihao Wang","submitted_at":"2026-08-10T02:38:42Z","abstract_excerpt":"Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of generated music implicit and difficult to inspect, control, or revise before audio generation. To address this issue, we introduce MusicLayout, an explicit intermediate representation for controlling musical structure in text-to-music generation. MusicLayout describes a musical piece as a time-aligned layout of sections, textures, repetitions, variations, and instrument-level arrangements, serving as an interpretable planning layer between textu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09035","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/2608.09035/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":"2608.09035","created_at":"2026-08-11T02:21:39.151402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09035v1","created_at":"2026-08-11T02:21:39.151402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09035","created_at":"2026-08-11T02:21:39.151402+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVPLGTKOK22N","created_at":"2026-08-11T02:21:39.151402+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVPLGTKOK22NXYGI","created_at":"2026-08-11T02:21:39.151402+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVPLGTKO","created_at":"2026-08-11T02:21:39.151402+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/DVPLGTKOK22NXYGIZOCDXGDD4W","json":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W.json","graph_json":"https://pith.science/api/pith-number/DVPLGTKOK22NXYGIZOCDXGDD4W/graph.json","events_json":"https://pith.science/api/pith-number/DVPLGTKOK22NXYGIZOCDXGDD4W/events.json","paper":"https://pith.science/paper/DVPLGTKO"},"agent_actions":{"view_html":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W","download_json":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W.json","view_paper":"https://pith.science/paper/DVPLGTKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09035&json=true","fetch_graph":"https://pith.science/api/pith-number/DVPLGTKOK22NXYGIZOCDXGDD4W/graph.json","fetch_events":"https://pith.science/api/pith-number/DVPLGTKOK22NXYGIZOCDXGDD4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W/action/storage_attestation","attest_author":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W/action/author_attestation","sign_citation":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W/action/citation_signature","submit_replication":"https://pith.science/pith/DVPLGTKOK22NXYGIZOCDXGDD4W/action/replication_record"}},"created_at":"2026-08-11T02:21:39.151402+00:00","updated_at":"2026-08-11T02:21:39.151402+00:00"}