{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U7E6GFOLUEIB4VG4ULN447HQ3X","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":"cc14009c14f5f8f9747a880d8d3440fb58e21d49ff1f6268c16ddb55cbb97952","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T08:22:34Z","title_canon_sha256":"122927b1f062c0f2c634e52866d4e7a76746b15e42a33511730ea1440e8bc3a6"},"schema_version":"1.0","source":{"id":"2309.07509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07509","created_at":"2026-07-05T06:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07509v1","created_at":"2026-07-05T06:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07509","created_at":"2026-07-05T06:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"U7E6GFOLUEIB","created_at":"2026-07-05T06:50:44Z"},{"alias_kind":"pith_short_16","alias_value":"U7E6GFOLUEIB4VG4","created_at":"2026-07-05T06:50:44Z"},{"alias_kind":"pith_short_8","alias_value":"U7E6GFOL","created_at":"2026-07-05T06:50:44Z"}],"graph_snapshots":[{"event_id":"sha256:59e340bab0801b4a9df99397a61e6aa60c95b76ebeaa5ab19197e5db2417b893","target":"graph","created_at":"2026-07-05T06:50:44Z","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/2309.07509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating realistic talking faces is a complex and widely discussed task with numerous applications. In this paper, we present DiffTalker, a novel model designed to generate lifelike talking faces through audio and landmark co-driving. DiffTalker addresses the challenges associated with directly applying diffusion models to audio control, which are traditionally trained on text-image pairs. DiffTalker consists of two agent networks: a transformer-based landmarks completion network for geometric accuracy and a diffusion-based face generation network for texture details. Landmarks play a pivota","authors_text":"Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Zipeng Qi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T08:22:34Z","title":"DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07509","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":"sha256:6b8de142e94d153c55f7525d1348d222c3793b155562ce28a943345c19e2c5fb","target":"record","created_at":"2026-07-05T06:50:44Z","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":"cc14009c14f5f8f9747a880d8d3440fb58e21d49ff1f6268c16ddb55cbb97952","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T08:22:34Z","title_canon_sha256":"122927b1f062c0f2c634e52866d4e7a76746b15e42a33511730ea1440e8bc3a6"},"schema_version":"1.0","source":{"id":"2309.07509","kind":"arxiv","version":1}},"canonical_sha256":"a7c9e315cba1101e54dca2dbce7cf0dddcac3914ca78f524bc6dab8f0e932e72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7c9e315cba1101e54dca2dbce7cf0dddcac3914ca78f524bc6dab8f0e932e72","first_computed_at":"2026-07-05T06:50:44.057002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:44.057002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3f8r+PCtaHb4EgBDM1umrVIDrN0PnaSXGwbi2dXmDVTvBAn+L8n04/XY3TrRUzT0e8IES94pEm9jZU9/ytMHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:44.057435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b8de142e94d153c55f7525d1348d222c3793b155562ce28a943345c19e2c5fb","sha256:59e340bab0801b4a9df99397a61e6aa60c95b76ebeaa5ab19197e5db2417b893"],"state_sha256":"3f199caa0115337bf7519ca2f0652b6334b9a3b64930307a7f6b9bafa6fa5e8c"}