{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VHF77FX33WFEIVPLXKYB65ZXR7","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":"bcf4666819bcb01b10c17c0c354ab18d468665fc8a512a83310578c80a2fa257","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T15:37:19Z","title_canon_sha256":"9ec1d205270afe978adbdcd0d347d62f84f7b7eadd6cef56db9bce0ff5bb1fce"},"schema_version":"1.0","source":{"id":"2403.13678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13678","created_at":"2026-07-05T07:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13678v1","created_at":"2026-07-05T07:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13678","created_at":"2026-07-05T07:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"VHF77FX33WFE","created_at":"2026-07-05T07:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"VHF77FX33WFEIVPL","created_at":"2026-07-05T07:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"VHF77FX3","created_at":"2026-07-05T07:58:40Z"}],"graph_snapshots":[{"event_id":"sha256:db7892294d4e7ab59b10d5ace9d6305b74ab8b7194f9c5082294c8758cb119a5","target":"graph","created_at":"2026-07-05T07:58:40Z","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/2403.13678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging the synergy of both audio data and visual data is essential for understanding human emotions and behaviors, especially in in-the-wild setting. Traditional methods for integrating such multimodal information often stumble, leading to less-than-ideal outcomes in the task of facial action unit detection. To overcome these shortcomings, we propose a novel approach utilizing audio-visual multimodal data. This method enhances audio feature extraction by leveraging Mel Frequency Cepstral Coefficients (MFCC) and Log-Mel spectrogram features alongside a pre-trained VGGish network. Moreover, ","authors_text":"Gongpeng Zhao, Guochen Xie, Jichao Zhu, Jun Yu, Wangyuan Zhu, Yongqi Wang, Zerui Zhang, Zhihong Wei, Zhongpeng Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T15:37:19Z","title":"AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13678","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:ed0a574e5c5c5bb359b72b645c69dec40d57326d150c4563d2cb0c2d2af8eb22","target":"record","created_at":"2026-07-05T07:58:40Z","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":"bcf4666819bcb01b10c17c0c354ab18d468665fc8a512a83310578c80a2fa257","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T15:37:19Z","title_canon_sha256":"9ec1d205270afe978adbdcd0d347d62f84f7b7eadd6cef56db9bce0ff5bb1fce"},"schema_version":"1.0","source":{"id":"2403.13678","kind":"arxiv","version":1}},"canonical_sha256":"a9cbff96fbdd8a4455ebbab01f77378fd90f3de7caae9b0fa6d8db52697c554b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9cbff96fbdd8a4455ebbab01f77378fd90f3de7caae9b0fa6d8db52697c554b","first_computed_at":"2026-07-05T07:58:40.283536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:40.283536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JYRaa+I2NkdZvbhzMZHFQnUVv2PS6Rzsyk3dNhPdcNIMcOIya+Flv3CCUZTke87PZvHx2Ba1OnJM0JoSfzJfCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:40.283969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed0a574e5c5c5bb359b72b645c69dec40d57326d150c4563d2cb0c2d2af8eb22","sha256:db7892294d4e7ab59b10d5ace9d6305b74ab8b7194f9c5082294c8758cb119a5"],"state_sha256":"f29d5acd855c6b014fddfc459adf5c1b253fbb917cf090e2c9c3707ef22d5019"}