{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V6CSI35D7XCVL5R5WL34YENAEZ","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":"7477656faf0c17b75caf7bfea6fb0c8f5b9e17faa485d2db03a1c823c66ec4ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T03:26:30Z","title_canon_sha256":"4876b8e49f2a5fd05d252fb2800e41fb465396409b74cc48ba6eeabc4e9d18fa"},"schema_version":"1.0","source":{"id":"2504.17224","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17224","created_at":"2026-07-05T11:35:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17224v3","created_at":"2026-07-05T11:35:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17224","created_at":"2026-07-05T11:35:13Z"},{"alias_kind":"pith_short_12","alias_value":"V6CSI35D7XCV","created_at":"2026-07-05T11:35:13Z"},{"alias_kind":"pith_short_16","alias_value":"V6CSI35D7XCVL5R5","created_at":"2026-07-05T11:35:13Z"},{"alias_kind":"pith_short_8","alias_value":"V6CSI35D","created_at":"2026-07-05T11:35:13Z"}],"graph_snapshots":[{"event_id":"sha256:de76f62ac666d0d58d15f76beba6fa2d5b63f8fceeba538abb0b99c750541a54","target":"graph","created_at":"2026-07-05T11:35:13Z","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/2504.17224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Large Language Models (VLLMs) exhibit promising potential for multi-modal understanding, yet their application to video-based emotion recognition remains limited by insufficient spatial and contextual awareness. Traditional approaches, which prioritize isolated facial features, often neglect critical non-verbal cues such as body language, environmental context, and social interactions, leading to reduced robustness in real-world scenarios. To address this gap, we propose Set-of-Vision-Text Prompting (SoVTP), a novel framework that enhances zero-shot emotion recognition by integrating sp","authors_text":"Kaihao Zhang, Peter Zhang, Qixuan Zhang, Ramesh Sankaranarayana, Sabrina Caldwell, Tom Gedeon, Wenjia Niu, Zhifeng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T03:26:30Z","title":"Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17224","kind":"arxiv","version":3},"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":"sha256:0e2cc04284c36524a0d694145cea167ba202850d3582471e57ca29987b427f0c","target":"record","created_at":"2026-07-05T11:35:13Z","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":"7477656faf0c17b75caf7bfea6fb0c8f5b9e17faa485d2db03a1c823c66ec4ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T03:26:30Z","title_canon_sha256":"4876b8e49f2a5fd05d252fb2800e41fb465396409b74cc48ba6eeabc4e9d18fa"},"schema_version":"1.0","source":{"id":"2504.17224","kind":"arxiv","version":3}},"canonical_sha256":"af85246fa3fdc555f63db2f7cc11a02675d05fd6cc6f518ab16d55d22cb87eee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af85246fa3fdc555f63db2f7cc11a02675d05fd6cc6f518ab16d55d22cb87eee","first_computed_at":"2026-07-05T11:35:13.360515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:13.360515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4UWQgLJm5Px+qgypyzIq1QY3Vv1717EFy2QLFnCdR3dZx24i60GdIix1fkYvtiLHTQOwGkmMfQPbXro7dtvEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:13.360999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17224","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e2cc04284c36524a0d694145cea167ba202850d3582471e57ca29987b427f0c","sha256:de76f62ac666d0d58d15f76beba6fa2d5b63f8fceeba538abb0b99c750541a54"],"state_sha256":"af9225e1833a04917abf8c0e89fb486a7b6056360cc37a7c36f53a221859c702"}