{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5TN4BNQDYGAFP4UUF2IR26AVMS","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":"3a34cc9880f96e00f0597143db49e3766e74a4508d0c742526e7f19369ee67e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T15:35:44Z","title_canon_sha256":"53b9b0ea9f5e239801b470ecefe92233a17fa85ea02d04cc50eb46e345010563"},"schema_version":"1.0","source":{"id":"2408.00644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00644","created_at":"2026-07-05T08:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00644v1","created_at":"2026-07-05T08:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00644","created_at":"2026-07-05T08:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"5TN4BNQDYGAF","created_at":"2026-07-05T08:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"5TN4BNQDYGAFP4UU","created_at":"2026-07-05T08:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"5TN4BNQD","created_at":"2026-07-05T08:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:c670452eb7080165dbc7ddd4b4fd88d5f165dbc799eaccfb7aea6ac95bbddc47","target":"graph","created_at":"2026-07-05T08:51:07Z","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/2408.00644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Facial action units (AUs), as defined in the Facial Action Coding System (FACS), have received significant research interest owing to their diverse range of applications in facial state analysis. Current mainstream FAU recognition models have a notable limitation, i.e., focusing only on the accuracy of AU recognition and overlooking explanations of corresponding AU states. In this paper, we propose an end-to-end Vision-Language joint learning network for explainable FAU recognition (termed VL-FAU), which aims to reinforce AU representation capability and language interpretability through the i","authors_text":"Fuhai Chen, Joemon M. Jose, Junchen Fu, Nicu Sebe, Shan An, Xuri Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T15:35:44Z","title":"Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00644","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":"sha256:24e33065c6ad14aca53ee277ea836d9496c1ca792c15df52aab7da3fc14083aa","target":"record","created_at":"2026-07-05T08:51:07Z","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":"3a34cc9880f96e00f0597143db49e3766e74a4508d0c742526e7f19369ee67e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T15:35:44Z","title_canon_sha256":"53b9b0ea9f5e239801b470ecefe92233a17fa85ea02d04cc50eb46e345010563"},"schema_version":"1.0","source":{"id":"2408.00644","kind":"arxiv","version":1}},"canonical_sha256":"ecdbc0b603c18057f2942e911d781564bfb3f25cf3ecaa0c00df30f4123ad951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecdbc0b603c18057f2942e911d781564bfb3f25cf3ecaa0c00df30f4123ad951","first_computed_at":"2026-07-05T08:51:07.021521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:07.021521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4IpdE4ExzK7taYSJJ5XSVujJ5uqW1uhSjx3tBMC8FlKc38CkUuiSQIXap/dA1+JTTupp05DL19SudtHvgsmvAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:07.021987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24e33065c6ad14aca53ee277ea836d9496c1ca792c15df52aab7da3fc14083aa","sha256:c670452eb7080165dbc7ddd4b4fd88d5f165dbc799eaccfb7aea6ac95bbddc47"],"state_sha256":"732bf5f9c21e36f6e114fbed9f4afc42472839af8607e1d8c62a97e9c0d39aff"}