{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RDMSKUXLPUEDVGKFM2G7ZY27W4","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":"e70ec382c26713c2b395e87e0d317c15691b4cba90dc80384b73c600c14ab790","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T16:43:07Z","title_canon_sha256":"54e2633deecae30afac340d3c1f1cb29ddd38e00c81e099be63f50e1fae82bda"},"schema_version":"1.0","source":{"id":"2605.31530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31530","created_at":"2026-06-01T02:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31530v1","created_at":"2026-06-01T02:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31530","created_at":"2026-06-01T02:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"RDMSKUXLPUED","created_at":"2026-06-01T02:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"RDMSKUXLPUEDVGKF","created_at":"2026-06-01T02:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"RDMSKUXL","created_at":"2026-06-01T02:04:11Z"}],"graph_snapshots":[{"event_id":"sha256:db0599986481432c90ff71cb3daf45ee5907f7656e61f9e6e3756fe2dea75531","target":"graph","created_at":"2026-06-01T02:04:11Z","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/2605.31530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providin","authors_text":"Haoning Xu, Haoxuan Che, Huimeng Wang, Jiajun Deng, Jingran Su, Rui Liu, Tianzi Wang, Xunying Liu, Yaofang Liu, Zengrui Jin, Zhaoqing Li, Zhefan Rao","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T16:43:07Z","title":"UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31530","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":"sha256:507f51c687c83efb56fe07bdd44c80ede95da22372eef0a809c8d3a80eab6574","target":"record","created_at":"2026-06-01T02:04:11Z","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":"e70ec382c26713c2b395e87e0d317c15691b4cba90dc80384b73c600c14ab790","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T16:43:07Z","title_canon_sha256":"54e2633deecae30afac340d3c1f1cb29ddd38e00c81e099be63f50e1fae82bda"},"schema_version":"1.0","source":{"id":"2605.31530","kind":"arxiv","version":1}},"canonical_sha256":"88d92552eb7d083a9945668dfce35fb73e306e403102bf96456cbdab09e641fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88d92552eb7d083a9945668dfce35fb73e306e403102bf96456cbdab09e641fe","first_computed_at":"2026-06-01T02:04:11.267347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:04:11.267347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/hKwZi9T+vg9qQ6HNKpsyvkQ8K7nqLlRDfW7r+RR5trIVP4vf8CG4AKt3KstKIPO1TeGt6WvYDg7oD5mOqy/Dw==","signature_status":"signed_v1","signed_at":"2026-06-01T02:04:11.268272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:507f51c687c83efb56fe07bdd44c80ede95da22372eef0a809c8d3a80eab6574","sha256:db0599986481432c90ff71cb3daf45ee5907f7656e61f9e6e3756fe2dea75531"],"state_sha256":"1460bb13ef9426817c265f70559ae7c3699cfc35d7faa9f51d5b053f93290459"}