{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YLLEDNKZ3ZO5FBKFNFVCG2PRJK","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":"89eb722b47af528139a02642260c15c8a3d11a307e87e8bdb14a4de981fe098d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T04:48:29Z","title_canon_sha256":"9a24b0abaae47a59f584192d5ab595a6fc35bcaf688bc3526ab147567eb14537"},"schema_version":"1.0","source":{"id":"2608.11650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11650","created_at":"2026-08-13T01:27:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11650v1","created_at":"2026-08-13T01:27:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11650","created_at":"2026-08-13T01:27:13Z"},{"alias_kind":"pith_short_12","alias_value":"YLLEDNKZ3ZO5","created_at":"2026-08-13T01:27:13Z"},{"alias_kind":"pith_short_16","alias_value":"YLLEDNKZ3ZO5FBKF","created_at":"2026-08-13T01:27:13Z"},{"alias_kind":"pith_short_8","alias_value":"YLLEDNKZ","created_at":"2026-08-13T01:27:13Z"}],"graph_snapshots":[{"event_id":"sha256:7ca13eee5c105d822a39411731e0983b443e9b00b85b1debc72052f11da563a3","target":"graph","created_at":"2026-08-13T01:27:13Z","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/2608.11650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time. This dependency limits cross-lingual voice cloning, since in-the-wild reference audio is often untranscribed. In this technical report, we present Confucius4-TTS, a multilingual zero-shot TTS system that supports 14 languages and performs both intra-lingual and cross-lingual reference cloning without requiring transcripts of audio prompts. Confucius4-TTS follows a two-stage archit","authors_text":"Huaxuan Wang, Huimin Wang, Ruiyu Zhang, Yingjie Li, Yitao Duan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T04:48:29Z","title":"Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11650","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:f681edf3294d2aef8b2878dfc2836bc4a2a21cabe4e273dd92a49d894e74112d","target":"record","created_at":"2026-08-13T01:27:13Z","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":"89eb722b47af528139a02642260c15c8a3d11a307e87e8bdb14a4de981fe098d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T04:48:29Z","title_canon_sha256":"9a24b0abaae47a59f584192d5ab595a6fc35bcaf688bc3526ab147567eb14537"},"schema_version":"1.0","source":{"id":"2608.11650","kind":"arxiv","version":1}},"canonical_sha256":"c2d641b559de5dd28545696a2369f14ab24b996bf4bd5c86f491e6c3a43bf0a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2d641b559de5dd28545696a2369f14ab24b996bf4bd5c86f491e6c3a43bf0a9","first_computed_at":"2026-08-13T01:27:13.169647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:27:13.169647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toeYuDbN/cnKW9VtAdo/WfTNhfrOUOjSNWg1rZM5QttJL7/l8PwqF9ScUCDGINT0/UvjV658FyIWcJsSd2SBBA==","signature_status":"signed_v1","signed_at":"2026-08-13T01:27:13.172291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f681edf3294d2aef8b2878dfc2836bc4a2a21cabe4e273dd92a49d894e74112d","sha256:7ca13eee5c105d822a39411731e0983b443e9b00b85b1debc72052f11da563a3"],"state_sha256":"0513bae74de00e4cd1e313d9651d35681da30a6d6b89a1fc436f52706394364b"}