{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YLLEDNKZ3ZO5FBKFNFVCG2PRJK","short_pith_number":"pith:YLLEDNKZ","canonical_record":{"source":{"id":"2608.11650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T04:48:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9a24b0abaae47a59f584192d5ab595a6fc35bcaf688bc3526ab147567eb14537","abstract_canon_sha256":"89eb722b47af528139a02642260c15c8a3d11a307e87e8bdb14a4de981fe098d"},"schema_version":"1.0"},"canonical_sha256":"c2d641b559de5dd28545696a2369f14ab24b996bf4bd5c86f491e6c3a43bf0a9","source":{"kind":"arxiv","id":"2608.11650","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YLLEDNKZ3ZO5FBKFNFVCG2PRJK","target":"record","payload":{"canonical_record":{"source":{"id":"2608.11650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T04:48:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9a24b0abaae47a59f584192d5ab595a6fc35bcaf688bc3526ab147567eb14537","abstract_canon_sha256":"89eb722b47af528139a02642260c15c8a3d11a307e87e8bdb14a4de981fe098d"},"schema_version":"1.0"},"canonical_sha256":"c2d641b559de5dd28545696a2369f14ab24b996bf4bd5c86f491e6c3a43bf0a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:27:13.172291Z","signature_b64":"toeYuDbN/cnKW9VtAdo/WfTNhfrOUOjSNWg1rZM5QttJL7/l8PwqF9ScUCDGINT0/UvjV658FyIWcJsSd2SBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2d641b559de5dd28545696a2369f14ab24b996bf4bd5c86f491e6c3a43bf0a9","last_reissued_at":"2026-08-13T01:27:13.169647Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:27:13.169647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.11650","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-13T01:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vsWTecbwM42KHrcqyQ5+vIXyZ+DHWIpnZIJE+M3Z6yGL5yWuRt/KEyNPmySjRrx5jwjm0QuHYOWtpvUlGJ+qAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:25:11.091542Z"},"content_sha256":"f681edf3294d2aef8b2878dfc2836bc4a2a21cabe4e273dd92a49d894e74112d","schema_version":"1.0","event_id":"sha256:f681edf3294d2aef8b2878dfc2836bc4a2a21cabe4e273dd92a49d894e74112d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YLLEDNKZ3ZO5FBKFNFVCG2PRJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Huaxuan Wang, Huimin Wang, Ruiyu Zhang, Yingjie Li, Yitao Duan","submitted_at":"2026-08-12T04:48:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11650","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.11650/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-13T01:27:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grrVKb1bOplU36X+kGd7jvxOzj6eMyDI/V+MuyfAxxtRLPrtiMspwUzDCrkOlEPMtatJqL9kD9dez6BFLQFEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:25:11.092005Z"},"content_sha256":"7ca13eee5c105d822a39411731e0983b443e9b00b85b1debc72052f11da563a3","schema_version":"1.0","event_id":"sha256:7ca13eee5c105d822a39411731e0983b443e9b00b85b1debc72052f11da563a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK/bundle.json","state_url":"https://pith.science/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T13:25:11Z","links":{"resolver":"https://pith.science/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK","bundle":"https://pith.science/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK/bundle.json","state":"https://pith.science/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLLEDNKZ3ZO5FBKFNFVCG2PRJK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4S3v6o9KFUcFbsTLM6mTssQ8f2LQpMqF4M7GK6QtqgxeDiEAsIPMLrnndUwJ/pmFSh327ozJM1WWfD7k9LFBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:25:11.095281Z","bundle_sha256":"99ab62e70428fc9f2dd72ed295d40f99a29c23b4918eb530e2e40b06fe6a28ed"}}