{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JTJLBNYZACWTZMRIW5NQKHDGC4","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":"32df9454fe35391a40d5625f3ccef4d8cb783c52a9a2dc61ccd948b0cf63d506","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-12T14:42:10Z","title_canon_sha256":"b8ec476e508eea25e98f102541bdf95cb2d56603da3db012832a1959b70f604c"},"schema_version":"1.0","source":{"id":"2412.09317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09317","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09317v1","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09317","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"JTJLBNYZACWT","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"JTJLBNYZACWTZMRI","created_at":"2026-07-05T09:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"JTJLBNYZ","created_at":"2026-07-05T09:48:23Z"}],"graph_snapshots":[{"event_id":"sha256:d863eec8c11b190e70d8555aecfd5f1890885309cd024f96b082e0e01dbfe107","target":"graph","created_at":"2026-07-05T09:48:23Z","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/2412.09317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the abundance of current researches working on the sentiment analysis from videos and audios, finding the best model that gives the highest accuracy rate is still considered a challenge for researchers in this field. The main objective of this paper is to prove the usability of emotion recognition models that take video and audio inputs. The datasets used to train the models are the CREMA-D dataset for audio and the RAVDESS dataset for video. The fine-tuned models that been used are: Facebook/wav2vec2-large for audio and the Google/vivit-b-16x2-kinetics400 for video. The avarage of the","authors_text":"Antonio Fernandez, Suzan Awinat","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-12T14:42:10Z","title":"Multimodal Sentiment Analysis based on Video and Audio Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09317","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":"sha256:004a171c05045db0cb55d16e8e2bb734c5fe9b4f0d963ead6e908240b473a14d","target":"record","created_at":"2026-07-05T09:48:23Z","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":"32df9454fe35391a40d5625f3ccef4d8cb783c52a9a2dc61ccd948b0cf63d506","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-12T14:42:10Z","title_canon_sha256":"b8ec476e508eea25e98f102541bdf95cb2d56603da3db012832a1959b70f604c"},"schema_version":"1.0","source":{"id":"2412.09317","kind":"arxiv","version":1}},"canonical_sha256":"4cd2b0b71900ad3cb228b75b051c661729f99a79b5105b3b8fb739fe517feff8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cd2b0b71900ad3cb228b75b051c661729f99a79b5105b3b8fb739fe517feff8","first_computed_at":"2026-07-05T09:48:23.160263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:23.160263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H52ykZLQsIGO9aojpdXowh5pwcPLBAkks0pUfvPZWnTV/oAGO+3lizPpPWNxlsyDQwangpqIYmRLLucY/NhNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:23.160758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:004a171c05045db0cb55d16e8e2bb734c5fe9b4f0d963ead6e908240b473a14d","sha256:d863eec8c11b190e70d8555aecfd5f1890885309cd024f96b082e0e01dbfe107"],"state_sha256":"8ee7bf41e8daa52b61b9226156fc20a9c6ecee862f214bc8687cd7e69c7d37ab"}