{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:I4WK357ACCFZG37RSJFYLIJNJX","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":"d0dd57d3e221c189e9f825fbc56ba96a131d0f9ab54086e35a476a827ac230fb","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-05T10:02:39Z","title_canon_sha256":"439e1933ab0cc11ea1635d1de3af54e3763a92fe67749aa6deb30fc3ec3c4792"},"schema_version":"1.0","source":{"id":"2204.02090","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02090","created_at":"2026-07-05T04:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02090v2","created_at":"2026-07-05T04:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02090","created_at":"2026-07-05T04:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"I4WK357ACCFZ","created_at":"2026-07-05T04:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"I4WK357ACCFZG37R","created_at":"2026-07-05T04:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"I4WK357A","created_at":"2026-07-05T04:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:7cc6933a233d1a9b332e72c7833fb68a98a2bc2a435b0186777e98380b82faf8","target":"graph","created_at":"2026-07-05T04:36:22Z","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/2204.02090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we address the problem of lip-voice synchronisation in videos containing human face and voice. Our approach is based on determining if the lips motion and the voice in a video are synchronised or not, depending on their audio-visual correspondence score. We propose an audio-visual cross-modal transformer-based model that outperforms several baseline models in the audio-visual synchronisation task on the standard lip-reading speech benchmark dataset LRS2. While the existing methods focus mainly on lip synchronisation in speech videos, we also consider the special case of the sing","authors_text":"Gloria Haro, Juan F. Montesinos, Venkatesh S. Kadandale","cross_cats":["cs.IR","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-05T10:02:39Z","title":"VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02090","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":"sha256:0312636191da2028f5971bc15b363a109fdca287c640b2eda93a4d78b102f65a","target":"record","created_at":"2026-07-05T04:36:22Z","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":"d0dd57d3e221c189e9f825fbc56ba96a131d0f9ab54086e35a476a827ac230fb","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-05T10:02:39Z","title_canon_sha256":"439e1933ab0cc11ea1635d1de3af54e3763a92fe67749aa6deb30fc3ec3c4792"},"schema_version":"1.0","source":{"id":"2204.02090","kind":"arxiv","version":2}},"canonical_sha256":"472cadf7e0108b936ff1924b85a12d4df41a98baefa4530ad0895a38a56a5159","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"472cadf7e0108b936ff1924b85a12d4df41a98baefa4530ad0895a38a56a5159","first_computed_at":"2026-07-05T04:36:22.481257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:22.481257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVZy+Mw7wEiEKEQNpJbd6cXRCw7PpSCKsmudjL3bh5vjIjA7CT+Jb4OA22dloCE3KnaGPb4Y0RwRlYJq2z6+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:22.481771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02090","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0312636191da2028f5971bc15b363a109fdca287c640b2eda93a4d78b102f65a","sha256:7cc6933a233d1a9b332e72c7833fb68a98a2bc2a435b0186777e98380b82faf8"],"state_sha256":"f48cdcccf16aa9b7f5f5de4dffb03942679e150bacc940c32be7b2d039637178"}