{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QDG5SBON3GCSKBHGI4BT5DF5RE","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":"e07ddf70c8d1625b175cb06470ed4678f27e906f9996c8c256adfdcf12d3fcf1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-13T08:27:22Z","title_canon_sha256":"ce4d0856796317bf7f0a54a4449948a414ca858ad5f778ebe71546c6ca2316fe"},"schema_version":"1.0","source":{"id":"2608.12951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12951","created_at":"2026-08-14T00:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12951v1","created_at":"2026-08-14T00:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12951","created_at":"2026-08-14T00:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"QDG5SBON3GCS","created_at":"2026-08-14T00:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"QDG5SBON3GCSKBHG","created_at":"2026-08-14T00:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"QDG5SBON","created_at":"2026-08-14T00:59:34Z"}],"graph_snapshots":[{"event_id":"sha256:49af0c7790b357ee8e6eafa0d2926704f6d0c9642afef32239aa91aa98c2693a","target":"graph","created_at":"2026-08-14T00:59:34Z","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/2608.12951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vocalized audio synthesis, the task of generating audio in which intelligible speech is embedded within an environmental soundscape, underpins applications such as podcast production and video dubbing. Existing Text-to-Audio (T2A) systems either reduce quoted speech to unintelligible vocal murmur or delegate it to a separate TTS model with post-hoc mixing, which forfeits control over when speech occurs and how it interacts with the scene. We present VoxAudio, a causal autoregressive flow matching model that addresses this problem from three complementary aspects. At the architecture level, chu","authors_text":"Changhao Pan, Fei Wu, Wenxiang Guo, Zhou Zhao, Ziyue Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-13T08:27:22Z","title":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12951","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:cca1c747303dd5395e915042cda04b1d137c4f1eb8160a974224d751cb4715a0","target":"record","created_at":"2026-08-14T00:59:34Z","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":"e07ddf70c8d1625b175cb06470ed4678f27e906f9996c8c256adfdcf12d3fcf1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-13T08:27:22Z","title_canon_sha256":"ce4d0856796317bf7f0a54a4449948a414ca858ad5f778ebe71546c6ca2316fe"},"schema_version":"1.0","source":{"id":"2608.12951","kind":"arxiv","version":1}},"canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","first_computed_at":"2026-08-14T00:59:34.327908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:59:34.327908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5WEv0o1qAxFSxJjmY3J/e68yNrbfz9X/EOYPNAo+bq+s86rfYmZZnUjaqHQTLVqFAT5jE3DSAiWhoCV89fe6BQ==","signature_status":"signed_v1","signed_at":"2026-08-14T00:59:34.340077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cca1c747303dd5395e915042cda04b1d137c4f1eb8160a974224d751cb4715a0","sha256:49af0c7790b357ee8e6eafa0d2926704f6d0c9642afef32239aa91aa98c2693a"],"state_sha256":"476a06edeeb8972857449fa5df28f5c207f6953a237c88e648c3182cf94914ed"}