{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZPYKLRHR32UENBXQCUCC52LV3J","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":"0b1d925b4f46598cd1088e37e907fea4ab2fede3f8c8f5ef4f57e34619b58c3e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T02:58:45Z","title_canon_sha256":"33050b4abd630694109e683afde2213f85784b9636d7abd6c4fd5888ddd228a6"},"schema_version":"1.0","source":{"id":"2608.11590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11590","created_at":"2026-08-13T00:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11590v1","created_at":"2026-08-13T00:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11590","created_at":"2026-08-13T00:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZPYKLRHR32UE","created_at":"2026-08-13T00:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZPYKLRHR32UENBXQ","created_at":"2026-08-13T00:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZPYKLRHR","created_at":"2026-08-13T00:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:29b4fc2dc16aaa0c69e399e83adec46e73e911171e1fbf9d2809baacf9fcc61c","target":"graph","created_at":"2026-08-13T00:22:15Z","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/2608.11590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing. However, most existing systems are designed for specific tasks and often rely on task-dependent architectures, control signals, or autoregressive decoding, limiting fine-grained controllability and inference efficiency. In this paper, we propose CookVoice, a unified framework for multimodal, multi-style, and multi-task human voice generation. CookVoice decomposes the human voice into three key factors: content, prosody, and style, enabling both speech and singing voi","authors_text":"Dai Jia, Haowei Lou, Hye-Young Paik, Kai Li, Lina Yao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T02:58:45Z","title":"CookVoice: Unified Framework for Style Controllable Multi-Modal Human Voice Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11590","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:a50871ad46fb6caabb67ebd02b73e3b2a22e67a38c2754926907fb51b69a0cf9","target":"record","created_at":"2026-08-13T00:22:15Z","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":"0b1d925b4f46598cd1088e37e907fea4ab2fede3f8c8f5ef4f57e34619b58c3e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T02:58:45Z","title_canon_sha256":"33050b4abd630694109e683afde2213f85784b9636d7abd6c4fd5888ddd228a6"},"schema_version":"1.0","source":{"id":"2608.11590","kind":"arxiv","version":1}},"canonical_sha256":"cbf0a5c4f1dea84686f015042ee975da4a5532bbe9dcadfe68ccbbc26801d09f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbf0a5c4f1dea84686f015042ee975da4a5532bbe9dcadfe68ccbbc26801d09f","first_computed_at":"2026-08-13T00:22:15.358266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:22:15.358266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLXykIwrW1r32YgTvsJlpbxI1rcwHoZvmdzWRYxFKdZ015R62wWEy4wPhSGYspzsOL3eZtOVNnHXQOtVJAtcAA==","signature_status":"signed_v1","signed_at":"2026-08-13T00:22:15.359721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a50871ad46fb6caabb67ebd02b73e3b2a22e67a38c2754926907fb51b69a0cf9","sha256:29b4fc2dc16aaa0c69e399e83adec46e73e911171e1fbf9d2809baacf9fcc61c"],"state_sha256":"92e4ac33c0b1212bc35ac238a2e7f16688f33b524a8d3d7496889f8f0457e139"}