{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MEX3P4DBU57DVOXN72OBWFKTCJ","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":"83fc82bae1f4b0e4214d70ff8df8ff7dd4aa103bc42c5e3a05389844205166da","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-17T14:56:52Z","title_canon_sha256":"7c4c5a8b1ff5d1bb6ef5e111ece3f8e50f459d678226e10b3640219221fe9225"},"schema_version":"1.0","source":{"id":"2605.17488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17488","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17488v1","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17488","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"MEX3P4DBU57D","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"MEX3P4DBU57DVOXN","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"MEX3P4DB","created_at":"2026-05-20T00:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:b653778b17e38b2f1a86c4f6e7ba387ac16c60c90d20eb0a6d9b6f84fc9b3eef","target":"graph","created_at":"2026-05-20T00:04:41Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.683495Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.644042Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17488/integrity.json","findings":[],"snapshot_sha256":"4ec22888210f0d7017a23904800ec58d536f89734a8b7dc002745225c78f4341","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides, achieving cohesive multimodal customization for the simultaneous preservation of visual identities and vocal timbres across multiple interacting subjects remains largely underexplored. To bridge this gap, we present Omni-Customizer, an end-to-end framework targeted at the precise binding and seamless fusion of multimodal identity information. Specifically, we introduce an Omni-Context Fusion (OCF) module that effectively enriches the base text","authors_text":"Jiangning Zhang, Lizhuang Ma, Qingdong He, Teng Hu, Yabiao Wang, Yuheng Chen, Yuji Wang","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-17T14:56:52Z","title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17488","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":"sha256:14e114bb1714cd563717cb39b5d29d240389685ed3ad5223a3089178a89441e2","target":"record","created_at":"2026-05-20T00:04:41Z","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":"83fc82bae1f4b0e4214d70ff8df8ff7dd4aa103bc42c5e3a05389844205166da","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-17T14:56:52Z","title_canon_sha256":"7c4c5a8b1ff5d1bb6ef5e111ece3f8e50f459d678226e10b3640219221fe9225"},"schema_version":"1.0","source":{"id":"2605.17488","kind":"arxiv","version":1}},"canonical_sha256":"612fb7f061a77e3abaedfe9c1b15531268c8c078eb9372dc34652c5ae77b0591","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"612fb7f061a77e3abaedfe9c1b15531268c8c078eb9372dc34652c5ae77b0591","first_computed_at":"2026-05-20T00:04:41.650666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:41.650666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xgyEKWHk+yzREjP+AV4IpA3UDl7aE+vCZ2Xt5n+y05GSYhscMpIIBLxh1VgLXY6JmhUG1jK4rH/x3xLza7TiCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:41.651348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14e114bb1714cd563717cb39b5d29d240389685ed3ad5223a3089178a89441e2","sha256:b653778b17e38b2f1a86c4f6e7ba387ac16c60c90d20eb0a6d9b6f84fc9b3eef"],"state_sha256":"d2168bf5d018c4238fe6ce673bc9e8f583ca5b660733374242e841257995a0bc"}