{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PVB2T7DMR4ZADA3M3MGTNS436G","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":"6480f18893d83f29f5501206d7bd8a37eb3dba6d91023c16c02a11031470c65d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-18T08:19:46Z","title_canon_sha256":"886317fc8b4cf7792e03477a98dd61539faec9029c8a02346ebf8ce44c176427"},"schema_version":"1.0","source":{"id":"2608.17492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.17492","created_at":"2026-08-19T01:31:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.17492v1","created_at":"2026-08-19T01:31:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.17492","created_at":"2026-08-19T01:31:12Z"},{"alias_kind":"pith_short_12","alias_value":"PVB2T7DMR4ZA","created_at":"2026-08-19T01:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"PVB2T7DMR4ZADA3M","created_at":"2026-08-19T01:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"PVB2T7DM","created_at":"2026-08-19T01:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:4b22840540af1c2af29a1ea86c0401ae95bc0b207f256c2fbaadacca7d62d146","target":"graph","created_at":"2026-08-19T01:31:12Z","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/2608.17492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Feiyu Shen, Fenglong Xie, Junjie Li, Kun Xie, Lei Xie, Xuelong Geng, Xu Tang, Yao Hu, Yichen Han, Yichen Wu, Ziqi Dai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-18T08:19:46Z","title":"FireRedTTS3: Unified Speech Generation and Editing with Semantically Enriched Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.17492","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:b3fa54ecf84bcfa193b481596259334222749d10a7f32539d88dbfeaac33155b","target":"record","created_at":"2026-08-19T01:31:12Z","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":"6480f18893d83f29f5501206d7bd8a37eb3dba6d91023c16c02a11031470c65d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-18T08:19:46Z","title_canon_sha256":"886317fc8b4cf7792e03477a98dd61539faec9029c8a02346ebf8ce44c176427"},"schema_version":"1.0","source":{"id":"2608.17492","kind":"arxiv","version":1}},"canonical_sha256":"7d43a9fc6c8f3201836cdb0d36cb9bf1aaf85f1455998a006d6591194368c276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d43a9fc6c8f3201836cdb0d36cb9bf1aaf85f1455998a006d6591194368c276","first_computed_at":"2026-08-19T01:31:12.624077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-19T01:31:12.624077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rwK43W8gv9P3RJz21PG2Mmpm4X/tbJnGJtbrXd1GaiNRMFZXTBW1R6iCBL0dVMA3+Q2TGuanKBknwxQcv0KZCQ==","signature_status":"signed_v1","signed_at":"2026-08-19T01:31:12.626480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.17492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3fa54ecf84bcfa193b481596259334222749d10a7f32539d88dbfeaac33155b","sha256:4b22840540af1c2af29a1ea86c0401ae95bc0b207f256c2fbaadacca7d62d146"],"state_sha256":"067734b4af132e54cc7de5e42180d4d7d04e89a4107ce67320ef6acd3cef5db0"}