{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HRQ2DNVQ724XG7D74O4VHRIIHZ","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":"cc155e7fc949f5337c2154af90ad6886b2c2dea3971f2359caaa3101489c8042","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T09:48:13Z","title_canon_sha256":"9260f54e352eea1213af124fb7eff4cc78119b09af3e07409d1009bf4d265160"},"schema_version":"1.0","source":{"id":"2504.02433","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02433","created_at":"2026-07-05T11:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02433v2","created_at":"2026-07-05T11:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02433","created_at":"2026-07-05T11:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"HRQ2DNVQ724X","created_at":"2026-07-05T11:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"HRQ2DNVQ724XG7D7","created_at":"2026-07-05T11:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"HRQ2DNVQ","created_at":"2026-07-05T11:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:0da2cc989eff34f5a7a43d7773fe395da3c4bad444b48e1bc640065ccc8ae9e2","target":"graph","created_at":"2026-07-05T11:14:57Z","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/2504.02433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although significant progress has been made in audio-driven talking head generation, text-driven methods remain underexplored. In this work, we present OmniTalker, a unified framework that jointly generates synchronized talking audio-video content from input text while emulating the speaking and facial movement styles of the target identity, including speech characteristics, head motion, and facial dynamics. Our framework adopts a dual-branch diffusion transformer (DiT) architecture, with one branch dedicated to audio generation and the other to video synthesis. At the shallow layers, cross-mo","authors_text":"Bang Zhang, Chaonan Ji, Guangyuan Wang, Jinwei Qi, Liefeng Bo, Peng Zhang, Sheng Xu, Zhongjian Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T09:48:13Z","title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02433","kind":"arxiv","version":2},"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":"sha256:23f88f96f4813104d775da8b89cf179290f8947ef7c2b1648305ce32613ec283","target":"record","created_at":"2026-07-05T11:14:57Z","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":"cc155e7fc949f5337c2154af90ad6886b2c2dea3971f2359caaa3101489c8042","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T09:48:13Z","title_canon_sha256":"9260f54e352eea1213af124fb7eff4cc78119b09af3e07409d1009bf4d265160"},"schema_version":"1.0","source":{"id":"2504.02433","kind":"arxiv","version":2}},"canonical_sha256":"3c61a1b6b0feb9737c7fe3b953c5083e484e9a830de8fa25eed53549e3812a87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c61a1b6b0feb9737c7fe3b953c5083e484e9a830de8fa25eed53549e3812a87","first_computed_at":"2026-07-05T11:14:57.609610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:57.609610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xxKs1Ph2JlSRYT6HSOlJF4SfWHWYdGbYr9shwz8+uFNXO0FNdIzudt9v21e5yXy12bMjIGCv8kRcYjG5jSo9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:57.610096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02433","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23f88f96f4813104d775da8b89cf179290f8947ef7c2b1648305ce32613ec283","sha256:0da2cc989eff34f5a7a43d7773fe395da3c4bad444b48e1bc640065ccc8ae9e2"],"state_sha256":"4c7f8f8478c9e92c047fdcb842cc94f896bbd097c71902ab4b73cc618e285e11"}