{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7HVLFEGPXRU3I6Q7NUWT2T7XNB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6279febcbb5498c9865fcdc4c46084fefec0b0075304f9bdb351a4eb7fbff522","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-29T17:59:20Z","title_canon_sha256":"0124dc436107adfa019fff20207850315c93c639f2be64b5a6220866c0465ccf"},"schema_version":"1.0","source":{"id":"2606.30642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30642","created_at":"2026-06-30T02:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30642v1","created_at":"2026-06-30T02:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30642","created_at":"2026-06-30T02:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"7HVLFEGPXRU3","created_at":"2026-06-30T02:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"7HVLFEGPXRU3I6Q7","created_at":"2026-06-30T02:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"7HVLFEGP","created_at":"2026-06-30T02:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:8a9f8780304e2381685597df772ecae202166d506a5850139f808da9b93d040a","target":"graph","created_at":"2026-06-30T02:18:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.30642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts. Existing language model-based systems face a structural trade-off: mixed-token modeling preserves vocal-instrument coordination but obscures track-specific details, whereas dual-track prediction improves acoustics but requires longer sequences and weakens global planning. We present LeVo 2, a hybrid LLM-Diffusion framework for controllable full-length song generation. LeVo 2 formulates this trade-off as hierarchical modeling: LeLM first predicts ","authors_text":"Dapeng Wu, Dong Yu, Guangzheng Li, Hangting Chen, Huaicheng Zhang, Jianwei Yu, Lishi Zuo, Shun Lei, Wei Tan, Yaoxun Xu, Zhiyong Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-29T17:59:20Z","title":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30642","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bbc893d9faab648db84c07cfe53e6d5297ed21d8424b313b1d7bb6474899d069","target":"record","created_at":"2026-06-30T02:18:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6279febcbb5498c9865fcdc4c46084fefec0b0075304f9bdb351a4eb7fbff522","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-29T17:59:20Z","title_canon_sha256":"0124dc436107adfa019fff20207850315c93c639f2be64b5a6220866c0465ccf"},"schema_version":"1.0","source":{"id":"2606.30642","kind":"arxiv","version":1}},"canonical_sha256":"f9eab290cfbc69b47a1f6d2d3d4ff7687a9c40fcd117382f0536ede4f3a22776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9eab290cfbc69b47a1f6d2d3d4ff7687a9c40fcd117382f0536ede4f3a22776","first_computed_at":"2026-06-30T02:18:24.055211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:24.055211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fxHJq0Q0ss3KVe8UEnM8sY0dBMrrJIPHGItvDZtTuDiZzBanFDM10jWGtZzrjls7iyhQsBpGxoxmH/K9OAfaDQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:24.055930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbc893d9faab648db84c07cfe53e6d5297ed21d8424b313b1d7bb6474899d069","sha256:8a9f8780304e2381685597df772ecae202166d506a5850139f808da9b93d040a"],"state_sha256":"a91ec610200bb9f496ce55883666b1dd5765599ee0ed40dc6bef044b9f5c43b7"}