{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QDG5SBON3GCSKBHGI4BT5DF5RE","short_pith_number":"pith:QDG5SBON","canonical_record":{"source":{"id":"2608.12951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-13T08:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"ce4d0856796317bf7f0a54a4449948a414ca858ad5f778ebe71546c6ca2316fe","abstract_canon_sha256":"e07ddf70c8d1625b175cb06470ed4678f27e906f9996c8c256adfdcf12d3fcf1"},"schema_version":"1.0"},"canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","source":{"kind":"arxiv","id":"2608.12951","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QDG5SBON3GCSKBHGI4BT5DF5RE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-13T08:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"ce4d0856796317bf7f0a54a4449948a414ca858ad5f778ebe71546c6ca2316fe","abstract_canon_sha256":"e07ddf70c8d1625b175cb06470ed4678f27e906f9996c8c256adfdcf12d3fcf1"},"schema_version":"1.0"},"canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:59:34.340077Z","signature_b64":"5WEv0o1qAxFSxJjmY3J/e68yNrbfz9X/EOYPNAo+bq+s86rfYmZZnUjaqHQTLVqFAT5jE3DSAiWhoCV89fe6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","last_reissued_at":"2026-08-14T00:59:34.327908Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:59:34.327908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12951","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T00:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dLZLZC78MF4EnJA8IXr1bcOAaq0EBXthXWqPe6hCOHIMLcpwDJaNStJn6z61em2FB7p7DvaJpvUJ7voDAvEODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:39:52.909241Z"},"content_sha256":"cca1c747303dd5395e915042cda04b1d137c4f1eb8160a974224d751cb4715a0","schema_version":"1.0","event_id":"sha256:cca1c747303dd5395e915042cda04b1d137c4f1eb8160a974224d751cb4715a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QDG5SBON3GCSKBHGI4BT5DF5RE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Changhao Pan, Fei Wu, Wenxiang Guo, Zhou Zhao, Ziyue Jiang","submitted_at":"2026-08-13T08:27:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12951","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/2608.12951/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T00:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUD6rn59Hu15sDpnbS8MfSdc5PNmw8uKWHLlbNUbGwh8FQAVZ7dZPfd5gGfFM9xI+6jFuwMkeH8H5FLuFrjJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:39:52.931313Z"},"content_sha256":"49af0c7790b357ee8e6eafa0d2926704f6d0c9642afef32239aa91aa98c2693a","schema_version":"1.0","event_id":"sha256:49af0c7790b357ee8e6eafa0d2926704f6d0c9642afef32239aa91aa98c2693a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/bundle.json","state_url":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T22:39:52Z","links":{"resolver":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE","bundle":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/bundle.json","state":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IHCQWfDED8afDDiiF2IY7OEwXmJC2A9zt7TYzIqjoAosC22Dbyz4E30fQB1IypxYURVyFlkzlzluDO2/Bv7LBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:39:52.999186Z","bundle_sha256":"c8b84c27723689715b194e22652e0d66f9c0bc4fd1b8f2158d0cd96546c8cac9"}}