{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BFG67OQHNZZDMY5LEKAFNSBOZO","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":"85d3c7a70a5bdf729d268ee5a93a2dffd5cc582fea359bed3aeae1e30b84e4af","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T08:27:17Z","title_canon_sha256":"5f4065b7522457850918f4e236fb16fd0a55319879fe10e5202bd5090154cd52"},"schema_version":"1.0","source":{"id":"2606.05852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05852","created_at":"2026-06-05T01:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05852v1","created_at":"2026-06-05T01:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05852","created_at":"2026-06-05T01:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"BFG67OQHNZZD","created_at":"2026-06-05T01:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"BFG67OQHNZZDMY5L","created_at":"2026-06-05T01:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"BFG67OQH","created_at":"2026-06-05T01:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:63a5040676d1833a83c59bbaf86c812308fd3cd3781ccd55ea5e766c17f2e655","target":"graph","created_at":"2026-06-05T01:15:05Z","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/2606.05852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirements on the generation process. Speech generation relies on flexible, language-driven prosody, whereas singing generation requires explicit melody control and accurate rhythmic alignment. This mismatch makes it challenging to train a single model that can generate both natural speech and controllable singing, since melody-related conditions should strongly constrain singing but should not restrict speech prosody. We present UniVoice, a unified sp","authors_text":"Chaofan Ding, Hao Liu, Huixin Xue, Junjie Zheng, Shihong Ren, Zihao Chen","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T08:27:17Z","title":"UniVoice: A Unified Model for Speech and Singing Voice Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05852","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":"sha256:48e1755142f640030dfe4be1da200113b3d8302d2a9729bea1441aa59d35a390","target":"record","created_at":"2026-06-05T01:15:05Z","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":"85d3c7a70a5bdf729d268ee5a93a2dffd5cc582fea359bed3aeae1e30b84e4af","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T08:27:17Z","title_canon_sha256":"5f4065b7522457850918f4e236fb16fd0a55319879fe10e5202bd5090154cd52"},"schema_version":"1.0","source":{"id":"2606.05852","kind":"arxiv","version":1}},"canonical_sha256":"094defba076e723663ab228056c82ecbac0249aee1c179ea1453896c1fb9b92e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"094defba076e723663ab228056c82ecbac0249aee1c179ea1453896c1fb9b92e","first_computed_at":"2026-06-05T01:15:05.667395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:05.667395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I+fSYfCpdDl3a5Aimrq7Lvxp67XSD/k3EO3WDb5g5XUhVqNm6728PymIjCJuITG2lUhgxD4/YViR8YB5qgKjDQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:05.667925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48e1755142f640030dfe4be1da200113b3d8302d2a9729bea1441aa59d35a390","sha256:63a5040676d1833a83c59bbaf86c812308fd3cd3781ccd55ea5e766c17f2e655"],"state_sha256":"0e304395a47f42704a42969af3ba30cd8aa69a79e2cd90dc98acc5139e02b9d0"}