{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KXEDMCIVM2HGD47GPTBLOFRYRQ","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":"32a7bb8b258edb093809ac8dcd428fbc806da353e4c3a7c2ba23890b57847e7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-03T14:29:52Z","title_canon_sha256":"5917b109cee2c47ed7366cb70dd0025b14ed6d3335f7ebf18dd9ad741b25f666"},"schema_version":"1.0","source":{"id":"2606.04939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04939","created_at":"2026-06-04T01:09:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04939v1","created_at":"2026-06-04T01:09:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04939","created_at":"2026-06-04T01:09:56Z"},{"alias_kind":"pith_short_12","alias_value":"KXEDMCIVM2HG","created_at":"2026-06-04T01:09:56Z"},{"alias_kind":"pith_short_16","alias_value":"KXEDMCIVM2HGD47G","created_at":"2026-06-04T01:09:56Z"},{"alias_kind":"pith_short_8","alias_value":"KXEDMCIV","created_at":"2026-06-04T01:09:56Z"}],"graph_snapshots":[{"event_id":"sha256:f77b1b7724eca6484f49b6dc727271eb4773fec6f24866ce595077cfdc619b77","target":"graph","created_at":"2026-06-04T01:09:56Z","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/2606.04939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio generation and audio-to-text understanding remain largely separate, with diffusion models dominating high-fidelity synthesis and autoregressive (AR) language models driving captioning and semantic prediction. Existing unified approaches typically rely on either heterogeneous modules or AR-centric modeling, which can hinder joint optimization and limit acoustic fidelity. We present UAT, to our knowledge, the first diffusion-centric framework that supports unified audio generation, editing, and captioning. UAT couples continuous latent diffusion for audio with masked discrete diffusion for","authors_text":"Bing Han, Cheng Liu, Geng Tu, Hui Wang, Jiaming Zhou, Jinghua Zhao, Long Zhou, Yifan Yang, Yong Qin, Yuhang Jia, Zeyue Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-03T14:29:52Z","title":"UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04939","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:a4eeb43b673e2ac5b1eaaa485f8eb507a8378fa1e230932fe2e6bc6b90106f36","target":"record","created_at":"2026-06-04T01:09:56Z","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":"32a7bb8b258edb093809ac8dcd428fbc806da353e4c3a7c2ba23890b57847e7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-03T14:29:52Z","title_canon_sha256":"5917b109cee2c47ed7366cb70dd0025b14ed6d3335f7ebf18dd9ad741b25f666"},"schema_version":"1.0","source":{"id":"2606.04939","kind":"arxiv","version":1}},"canonical_sha256":"55c8360915668e61f3e67cc2b716388c04dff62ba39fd193f86c453c5d3cca05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55c8360915668e61f3e67cc2b716388c04dff62ba39fd193f86c453c5d3cca05","first_computed_at":"2026-06-04T01:09:56.771545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:56.771545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b9dX36D/MB9N42Zr7+URAVKzl//eLDfWCNzWWTu/7PVgqW78vtv7ujMWUYOkvdkpfE2iNMKpJsxK89IMTtz1Dg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:56.773560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4eeb43b673e2ac5b1eaaa485f8eb507a8378fa1e230932fe2e6bc6b90106f36","sha256:f77b1b7724eca6484f49b6dc727271eb4773fec6f24866ce595077cfdc619b77"],"state_sha256":"1ea9e85ad034a54127ccd96651caed39e8b2fa151d0df9a09a647683c6ab2942"}