{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5KA5W7L4YELJLBM3MPLE5MAR4V","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":"2d3cc83d0b1110bc4a966dbfc35110241fd92d12cf2f38f30fa110c826d2f381","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-13T05:38:34Z","title_canon_sha256":"ce75b6a06e94713a76eeb278558eccc2bdd0d65aff4330539b3adf7fdc376f3f"},"schema_version":"1.0","source":{"id":"2306.07547","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07547","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07547v6","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07547","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"5KA5W7L4YELJ","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"5KA5W7L4YELJLBM3","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"5KA5W7L4","created_at":"2026-07-05T08:01:30Z"}],"graph_snapshots":[{"event_id":"sha256:bd380d85608cd5df4309fdddbb97de784b156aeadcdbeece54e0235c54c4ccf1","target":"graph","created_at":"2026-07-05T08:01:30Z","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/2306.07547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS) synthesis. Recent popular models, such as VALL-E and SPEAR-TTS, allow zero-shot speaker adaptation through auto-regressive (AR) continuation of acoustic tokens extracted from a short speech prompt. However, these AR models are restricted to generate speech only in a left-to-right direction, making them unsuitable for speech editing where both preceding and following ","authors_text":"Chenpeng Du, Feiyu Shen, Hui Zhang, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo, Zheng Liang, Zhijun Liu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-13T05:38:34Z","title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07547","kind":"arxiv","version":6},"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":"sha256:9caceefd031e4b272445afddb8ec9c9c12b881672224406dd2d9fd6e3d9ef6b4","target":"record","created_at":"2026-07-05T08:01:30Z","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":"2d3cc83d0b1110bc4a966dbfc35110241fd92d12cf2f38f30fa110c826d2f381","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-13T05:38:34Z","title_canon_sha256":"ce75b6a06e94713a76eeb278558eccc2bdd0d65aff4330539b3adf7fdc376f3f"},"schema_version":"1.0","source":{"id":"2306.07547","kind":"arxiv","version":6}},"canonical_sha256":"ea81db7d7cc11695859b63d64eb011e572c19098725ed733cc27fa8e5299222b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea81db7d7cc11695859b63d64eb011e572c19098725ed733cc27fa8e5299222b","first_computed_at":"2026-07-05T08:01:30.587969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:30.587969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IN8BsHzDH+B8zq8s5aC72g25pbmicMxUE8kLeieP9CQeXp8zHbO3C+bYBGGnDeG6llqIw639oO3Mmn7fK1g9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:30.588416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07547","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9caceefd031e4b272445afddb8ec9c9c12b881672224406dd2d9fd6e3d9ef6b4","sha256:bd380d85608cd5df4309fdddbb97de784b156aeadcdbeece54e0235c54c4ccf1"],"state_sha256":"48fe81ef551cc39d1ff9b7e3ac988d204dc081e83e7dbaf37b2e8beaf87f8b07"}