{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PVB2T7DMR4ZADA3M3MGTNS436G","short_pith_number":"pith:PVB2T7DM","schema_version":"1.0","canonical_sha256":"7d43a9fc6c8f3201836cdb0d36cb9bf1aaf85f1455998a006d6591194368c276","source":{"kind":"arxiv","id":"2608.17492","version":1},"attestation_state":"computed","paper":{"title":"FireRedTTS3: Unified Speech Generation and Editing with Semantically Enriched Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Feiyu Shen, Fenglong Xie, Junjie Li, Kun Xie, Lei Xie, Xuelong Geng, Xu Tang, Yao Hu, Yichen Han, Yichen Wu, Ziqi Dai","submitted_at":"2026-08-18T08:19:46Z","abstract_excerpt":"Recent continuous autoregressive TTS models operate directly on continuous speech representations, preserving rich acoustic details while leveraging the instruction-following capabilities of text LLMs. This paradigm opens new possibilities for voice cloning, instruction-controlled voice design, and speech editing, but remains susceptible to error accumulation during autoregressive generation. Existing solutions often require additional semantic modules, multi-stage tokenizer training pipelines, or complex autoregressive architectures. In this work, we propose FireRedTTS3, a simple yet effectiv"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.17492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-18T08:19:46Z","cross_cats_sorted":[],"title_canon_sha256":"886317fc8b4cf7792e03477a98dd61539faec9029c8a02346ebf8ce44c176427","abstract_canon_sha256":"6480f18893d83f29f5501206d7bd8a37eb3dba6d91023c16c02a11031470c65d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-19T01:31:12.626480Z","signature_b64":"rwK43W8gv9P3RJz21PG2Mmpm4X/tbJnGJtbrXd1GaiNRMFZXTBW1R6iCBL0dVMA3+Q2TGuanKBknwxQcv0KZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d43a9fc6c8f3201836cdb0d36cb9bf1aaf85f1455998a006d6591194368c276","last_reissued_at":"2026-08-19T01:31:12.624077Z","signature_status":"signed_v1","first_computed_at":"2026-08-19T01:31:12.624077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireRedTTS3: Unified Speech Generation and Editing with Semantically Enriched Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Feiyu Shen, Fenglong Xie, Junjie Li, Kun Xie, Lei Xie, Xuelong Geng, Xu Tang, Yao Hu, Yichen Han, Yichen Wu, Ziqi Dai","submitted_at":"2026-08-18T08:19:46Z","abstract_excerpt":"Recent continuous autoregressive TTS models operate directly on continuous speech representations, preserving rich acoustic details while leveraging the instruction-following capabilities of text LLMs. This paradigm opens new possibilities for voice cloning, instruction-controlled voice design, and speech editing, but remains susceptible to error accumulation during autoregressive generation. Existing solutions often require additional semantic modules, multi-stage tokenizer training pipelines, or complex autoregressive architectures. In this work, we propose FireRedTTS3, a simple yet effectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.17492","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/2608.17492/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.17492","created_at":"2026-08-19T01:31:12.626589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.17492v1","created_at":"2026-08-19T01:31:12.626589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.17492","created_at":"2026-08-19T01:31:12.626589+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVB2T7DMR4ZA","created_at":"2026-08-19T01:31:12.626589+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVB2T7DMR4ZADA3M","created_at":"2026-08-19T01:31:12.626589+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVB2T7DM","created_at":"2026-08-19T01:31:12.626589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G","json":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G.json","graph_json":"https://pith.science/api/pith-number/PVB2T7DMR4ZADA3M3MGTNS436G/graph.json","events_json":"https://pith.science/api/pith-number/PVB2T7DMR4ZADA3M3MGTNS436G/events.json","paper":"https://pith.science/paper/PVB2T7DM"},"agent_actions":{"view_html":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G","download_json":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G.json","view_paper":"https://pith.science/paper/PVB2T7DM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.17492&json=true","fetch_graph":"https://pith.science/api/pith-number/PVB2T7DMR4ZADA3M3MGTNS436G/graph.json","fetch_events":"https://pith.science/api/pith-number/PVB2T7DMR4ZADA3M3MGTNS436G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G/action/storage_attestation","attest_author":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G/action/author_attestation","sign_citation":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G/action/citation_signature","submit_replication":"https://pith.science/pith/PVB2T7DMR4ZADA3M3MGTNS436G/action/replication_record"}},"created_at":"2026-08-19T01:31:12.626589+00:00","updated_at":"2026-08-19T01:31:12.626589+00:00"}