{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GMPLL7XY7PUQ2DPY3YUGUAYLV7","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":"928df71286ff53368ac4c5eb52dd2ade45d136e5b0fc0c6de8ec96b43912d056","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-27T02:30:15Z","title_canon_sha256":"a4a8406d6d9224effbc997ed9eafc60e83608c9fd1ae06c63bdd5357e21f8e58"},"schema_version":"1.0","source":{"id":"2607.23938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23938","created_at":"2026-07-28T01:23:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23938v1","created_at":"2026-07-28T01:23:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23938","created_at":"2026-07-28T01:23:36Z"},{"alias_kind":"pith_short_12","alias_value":"GMPLL7XY7PUQ","created_at":"2026-07-28T01:23:36Z"},{"alias_kind":"pith_short_16","alias_value":"GMPLL7XY7PUQ2DPY","created_at":"2026-07-28T01:23:36Z"},{"alias_kind":"pith_short_8","alias_value":"GMPLL7XY","created_at":"2026-07-28T01:23:36Z"}],"graph_snapshots":[{"event_id":"sha256:e4e9ba274dd1247dd48e754adff50c76b0b3e92b9d6ac2fbe770d0314ee105cb","target":"graph","created_at":"2026-07-28T01:23:36Z","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/2607.23938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, audio quality, controllability, multilingual coverage, efficiency, and robustness. It combines a 12.5~Hz low-frame-rate speech tokenizer for reduced inference latency with a five-stage progressive training paradigm for coordinated language model (LM) and flow-matching model (FM) optimization. The model provides production-level control through free-style natural-language instructions and fine-grained inline tags, while","authors_text":"Bajian Xiang, Cheng Wen, Han Zhao, Hao Wang, Haoxu Wang, Jiawei Jin, Jiayan Cui, Jie Chen, Mengxi Nie, Tianyu Zhao, Weiqin Li, Xiangang Li, Xiang Lv, Yang Xiang, Yang Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-27T02:30:15Z","title":"Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23938","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":"sha256:3631c01e3a976c3e3faea2a233a33253d7054f726512a8c8b7849aa470d963ee","target":"record","created_at":"2026-07-28T01:23:36Z","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":"928df71286ff53368ac4c5eb52dd2ade45d136e5b0fc0c6de8ec96b43912d056","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-27T02:30:15Z","title_canon_sha256":"a4a8406d6d9224effbc997ed9eafc60e83608c9fd1ae06c63bdd5357e21f8e58"},"schema_version":"1.0","source":{"id":"2607.23938","kind":"arxiv","version":1}},"canonical_sha256":"331eb5fef8fbe90d0df8de286a030bafc2932650ff5e5d9f8a3b9c4634de9134","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"331eb5fef8fbe90d0df8de286a030bafc2932650ff5e5d9f8a3b9c4634de9134","first_computed_at":"2026-07-28T01:23:36.762581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:36.762581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xXMFuPnd8433Vg06DSeMEYf/U8GDmCISGoHf8fOhOcEaIPbwikXB/A3WGDpKW7IBYpdgJ2olZRvpH8tpdkihBg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:36.763419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3631c01e3a976c3e3faea2a233a33253d7054f726512a8c8b7849aa470d963ee","sha256:e4e9ba274dd1247dd48e754adff50c76b0b3e92b9d6ac2fbe770d0314ee105cb"],"state_sha256":"7cfad54da819898107a82e711f3bb368cf6c76184f27f278dbda4b070fca76c0"}