{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LRXZVLLQNHHZ5U5JR3F6S4JHVS","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":"f844719a4b4187af6639bf4b67ec4b387c01ce8a5d5c177a1707658e7607cfd2","cross_cats_sorted":["cs.AI","cs.GR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T16:32:46Z","title_canon_sha256":"377cbb70541c95df2f8ce90bc3e2cf81a533b04206ff03e275debe7e19a34e39"},"schema_version":"1.0","source":{"id":"2212.04970","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04970","created_at":"2026-07-05T05:23:54Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04970v1","created_at":"2026-07-05T05:23:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04970","created_at":"2026-07-05T05:23:54Z"},{"alias_kind":"pith_short_12","alias_value":"LRXZVLLQNHHZ","created_at":"2026-07-05T05:23:54Z"},{"alias_kind":"pith_short_16","alias_value":"LRXZVLLQNHHZ5U5J","created_at":"2026-07-05T05:23:54Z"},{"alias_kind":"pith_short_8","alias_value":"LRXZVLLQ","created_at":"2026-07-05T05:23:54Z"}],"graph_snapshots":[{"event_id":"sha256:9d7565ca42607f3833811f12ade1e852f725675f88e9a7723c40f3fb637dbcab","target":"graph","created_at":"2026-07-05T05:23:54Z","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/2212.04970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous studies have explored generating accurately lip-synced talking faces for arbitrary targets given audio conditions. However, most of them deform or generate the whole facial area, leading to non-realistic results. In this work, we delve into the formulation of altering only the mouth shapes of the target person. This requires masking a large percentage of the original image and seamlessly inpainting it with the aid of audio and reference frames. To this end, we propose the Audio-Visual Context-Aware Transformer (AV-CAT) framework, which produces accurate lip-sync with photo-realistic q","authors_text":"Errui Ding, Hang Zhou, Hideki Koike, Jingdong Wang, Jingtuo Liu, Kaisiyuan Wang, Qianyi Wu, Yasheng Sun, Zhibin Hong, Ziwei Liu","cross_cats":["cs.AI","cs.GR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T16:32:46Z","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04970","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":"sha256:530eea84fc2c741efb1d725b4e2beeb6321ffc8d3a577cabd82637afe4f7e1c4","target":"record","created_at":"2026-07-05T05:23:54Z","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":"f844719a4b4187af6639bf4b67ec4b387c01ce8a5d5c177a1707658e7607cfd2","cross_cats_sorted":["cs.AI","cs.GR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T16:32:46Z","title_canon_sha256":"377cbb70541c95df2f8ce90bc3e2cf81a533b04206ff03e275debe7e19a34e39"},"schema_version":"1.0","source":{"id":"2212.04970","kind":"arxiv","version":1}},"canonical_sha256":"5c6f9aad7069cf9ed3a98ecbe97127ac880cc26119183168c150a1e23adbb753","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c6f9aad7069cf9ed3a98ecbe97127ac880cc26119183168c150a1e23adbb753","first_computed_at":"2026-07-05T05:23:54.430447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:54.430447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LvqbTsKNHWEdltakLQnx/Sbf/EfQkImdzBlFm+8Td/QICoiV2KubgMJAAWD1I+OeXgsATD9EgO8KJuOvxHINAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:54.431042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.04970","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:530eea84fc2c741efb1d725b4e2beeb6321ffc8d3a577cabd82637afe4f7e1c4","sha256:9d7565ca42607f3833811f12ade1e852f725675f88e9a7723c40f3fb637dbcab"],"state_sha256":"26df97dcd23e8c9ab66cb39b3bfa226714067adb3b5852316f9afbbbd456935f"}