{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BGOSPCMAVHYYSVAK34AQTRTESO","short_pith_number":"pith:BGOSPCMA","schema_version":"1.0","canonical_sha256":"099d278980a9f189540adf0109c66493b27c4e252849522db46d520a63e9a2d8","source":{"kind":"arxiv","id":"2404.07078","version":2},"attestation_state":"computed","paper":{"title":"VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Alexandros Xenos, Georgios Tzimiropoulos, Ioanna Ntinou, Ioannis Patras, Niki Maria Foteinopoulou","submitted_at":"2024-04-10T15:09:15Z","abstract_excerpt":"Recognising emotions in context involves identifying an individual's apparent emotions while considering contextual cues from the surrounding scene. Previous approaches to this task have typically designed explicit scene-encoding architectures or incorporated external scene-related information, such as captions. However, these methods often utilise limited contextual information or rely on intricate training pipelines to decouple noise from relevant information. In this work, we leverage the capabilities of Vision-and-Large-Language Models (VLLMs) to enhance in-context emotion classification i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.07078","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T15:09:15Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"c8d613d3d1410793f69c593b247003f47d8ed45e0b213f3941ce536d7cfe7b6f","abstract_canon_sha256":"75c228726a3dbab54cc3cd3f030d80c46ddeb09dcf6d35b213a0714599ce0bed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:08.960251Z","signature_b64":"5/mybHBfzV4CgK4aA8yhhOeQJQCltfmftu4DzZC/75jKzDwW9T6KWqpe/BZ5DR9Uzcs2Xq8IUEcL0/miaO3jBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"099d278980a9f189540adf0109c66493b27c4e252849522db46d520a63e9a2d8","last_reissued_at":"2026-07-05T11:37:08.959766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:08.959766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CV","authors_text":"Alexandros Xenos, Georgios Tzimiropoulos, Ioanna Ntinou, Ioannis Patras, Niki Maria Foteinopoulou","submitted_at":"2024-04-10T15:09:15Z","abstract_excerpt":"Recognising emotions in context involves identifying an individual's apparent emotions while considering contextual cues from the surrounding scene. Previous approaches to this task have typically designed explicit scene-encoding architectures or incorporated external scene-related information, such as captions. However, these methods often utilise limited contextual information or rely on intricate training pipelines to decouple noise from relevant information. In this work, we leverage the capabilities of Vision-and-Large-Language Models (VLLMs) to enhance in-context emotion classification i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07078","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.07078/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.07078","created_at":"2026-07-05T11:37:08.959824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07078v2","created_at":"2026-07-05T11:37:08.959824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07078","created_at":"2026-07-05T11:37:08.959824+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGOSPCMAVHYY","created_at":"2026-07-05T11:37:08.959824+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGOSPCMAVHYYSVAK","created_at":"2026-07-05T11:37:08.959824+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGOSPCMA","created_at":"2026-07-05T11:37:08.959824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16816","citing_title":"\"I'm Not Mad, Just Focused'': Understanding Human Emotions in Human-Robot Collaboration","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25255","citing_title":"Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO","json":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO.json","graph_json":"https://pith.science/api/pith-number/BGOSPCMAVHYYSVAK34AQTRTESO/graph.json","events_json":"https://pith.science/api/pith-number/BGOSPCMAVHYYSVAK34AQTRTESO/events.json","paper":"https://pith.science/paper/BGOSPCMA"},"agent_actions":{"view_html":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO","download_json":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO.json","view_paper":"https://pith.science/paper/BGOSPCMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07078&json=true","fetch_graph":"https://pith.science/api/pith-number/BGOSPCMAVHYYSVAK34AQTRTESO/graph.json","fetch_events":"https://pith.science/api/pith-number/BGOSPCMAVHYYSVAK34AQTRTESO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO/action/storage_attestation","attest_author":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO/action/author_attestation","sign_citation":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO/action/citation_signature","submit_replication":"https://pith.science/pith/BGOSPCMAVHYYSVAK34AQTRTESO/action/replication_record"}},"created_at":"2026-07-05T11:37:08.959824+00:00","updated_at":"2026-07-05T11:37:08.959824+00:00"}