{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z5APU2M2KTEKHTUB52YVGNWA4A","short_pith_number":"pith:Z5APU2M2","schema_version":"1.0","canonical_sha256":"cf40fa699a54c8a3ce81eeb15336c0e0118c682d28670b60dcd8b2c484db9aed","source":{"kind":"arxiv","id":"2404.16670","version":1},"attestation_state":"computed","paper":{"title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chan-Feng Hsu, Chu-Jun Peng, Hong-Han Shuai, Hongxia Xie, Hung-Jen Chen, Wen-Huang Cheng, Yu-Wen Tseng","submitted_at":"2024-04-25T15:15:36Z","abstract_excerpt":"Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but is still unexplored in vision emotion understanding. In this work, we focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. Initially, we identify key visual clues critical to visual emotion recognition. Subsequently, we introduce a novel GPT-assisted pipeline for generating emotion"},"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":"2404.16670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T15:15:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94c7b64c01299134bb644eecaef80c8f1e7691cda9ff83edd08306681e4b073e","abstract_canon_sha256":"ab543374afa52b3aa42760ac5a73481df3ef709b86413661209a11215a8bbadc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:11.264273Z","signature_b64":"EOvialpqQ/Xs+E05P/hXdGzDNcgzlGTEIeKCXyNN6sBGUqEEjTIgZ6PbMYAusj8z+fbmjR/HMo/u2efMxdfuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf40fa699a54c8a3ce81eeb15336c0e0118c682d28670b60dcd8b2c484db9aed","last_reissued_at":"2026-07-05T08:12:11.263706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:11.263706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chan-Feng Hsu, Chu-Jun Peng, Hong-Han Shuai, Hongxia Xie, Hung-Jen Chen, Wen-Huang Cheng, Yu-Wen Tseng","submitted_at":"2024-04-25T15:15:36Z","abstract_excerpt":"Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but is still unexplored in vision emotion understanding. In this work, we focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. Initially, we identify key visual clues critical to visual emotion recognition. Subsequently, we introduce a novel GPT-assisted pipeline for generating emotion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16670","kind":"arxiv","version":1},"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/2404.16670/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":"2404.16670","created_at":"2026-07-05T08:12:11.263769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16670v1","created_at":"2026-07-05T08:12:11.263769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16670","created_at":"2026-07-05T08:12:11.263769+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5APU2M2KTEK","created_at":"2026-07-05T08:12:11.263769+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5APU2M2KTEKHTUB","created_at":"2026-07-05T08:12:11.263769+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5APU2M2","created_at":"2026-07-05T08:12:11.263769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19950","citing_title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A","json":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A.json","graph_json":"https://pith.science/api/pith-number/Z5APU2M2KTEKHTUB52YVGNWA4A/graph.json","events_json":"https://pith.science/api/pith-number/Z5APU2M2KTEKHTUB52YVGNWA4A/events.json","paper":"https://pith.science/paper/Z5APU2M2"},"agent_actions":{"view_html":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A","download_json":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A.json","view_paper":"https://pith.science/paper/Z5APU2M2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16670&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5APU2M2KTEKHTUB52YVGNWA4A/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5APU2M2KTEKHTUB52YVGNWA4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A/action/storage_attestation","attest_author":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A/action/author_attestation","sign_citation":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A/action/citation_signature","submit_replication":"https://pith.science/pith/Z5APU2M2KTEKHTUB52YVGNWA4A/action/replication_record"}},"created_at":"2026-07-05T08:12:11.263769+00:00","updated_at":"2026-07-05T08:12:11.263769+00:00"}