{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AKSPIIEMLOY54UM2LCAPCM5BN5","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":"51feb7da21e5749c6ec781fbd44ad5a1fde4e647a57670bb381dd98d847d5b6c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-23T03:13:46Z","title_canon_sha256":"32e7565923a157e1384493d62f4ae73df59589555b7277fd32ecc1ba3c4acdd8"},"schema_version":"1.0","source":{"id":"2505.17426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17426","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17426v1","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17426","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"AKSPIIEMLOY5","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"AKSPIIEMLOY54UM2","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"AKSPIIEM","created_at":"2026-07-05T11:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:71b19ac6503d52f113559277667b4a9d4b8a6cae214b495f1d8b98f221ebd3e1","target":"graph","created_at":"2026-07-05T11:08:26Z","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/2505.17426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of multi-codebook neutral audio codecs such as Residual Vector Quantization (RVQ) and Group Vector Quantization (GVQ) has significantly advanced Large-Language-Model (LLM) based Text-to-Speech (TTS) systems. These codecs are crucial in separating semantic and acoustic information while efficiently harnessing semantic priors. However, since semantic and acoustic information cannot be fully aligned, a significant drawback of these methods when applied to LLM-based TTS is that large language models may have limited access to comprehensive audio information. To address this limitatio","authors_text":"Jiaxing Zhang, Junlong Wu, Qianguo Sun, Rui Wang, Tianrong Chen, Zhiyun Zeng","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-23T03:13:46Z","title":"UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17426","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:faf529f801be3e5b8fe5b6f118ec3254c2711d3b2039beb30c8b0350dc41c95b","target":"record","created_at":"2026-07-05T11:08:26Z","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":"51feb7da21e5749c6ec781fbd44ad5a1fde4e647a57670bb381dd98d847d5b6c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-23T03:13:46Z","title_canon_sha256":"32e7565923a157e1384493d62f4ae73df59589555b7277fd32ecc1ba3c4acdd8"},"schema_version":"1.0","source":{"id":"2505.17426","kind":"arxiv","version":1}},"canonical_sha256":"02a4f4208c5bb1de519a5880f133a16f463506eaad39d1db0092c9f87cde7042","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02a4f4208c5bb1de519a5880f133a16f463506eaad39d1db0092c9f87cde7042","first_computed_at":"2026-07-05T11:08:26.002803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:26.002803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uVwPgzqlnmpePnsf5t8ZI78hV0+5nNBMm8H4MWdCRvRdxRYMSyH7D7Ka3UFCOXHMc9USC7Cxpkf+TofoqBttCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:26.003210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faf529f801be3e5b8fe5b6f118ec3254c2711d3b2039beb30c8b0350dc41c95b","sha256:71b19ac6503d52f113559277667b4a9d4b8a6cae214b495f1d8b98f221ebd3e1"],"state_sha256":"c48ca7eee7bd8a18d29fa91512e39c16f2338e5a01546f34e69a1557f723c8b4"}