{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DB6MP5OSXHWICWDGTY7TFD4XYQ","short_pith_number":"pith:DB6MP5OS","schema_version":"1.0","canonical_sha256":"187cc7f5d2b9ec8158669e3f328f97c434afa00dad81bff6e492e8eb705555f7","source":{"kind":"arxiv","id":"2402.06015","version":2},"attestation_state":"computed","paper":{"title":"Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Antonia Karamolegkou, Daniel Hershcovich, Jiaang Li, Wenyan Li, Yifei Yuan, Yong Cao","submitted_at":"2024-02-08T19:25:40Z","abstract_excerpt":"Pretrained large Vision-Language models have drawn considerable interest in recent years due to their remarkable performance. Despite considerable efforts to assess these models from diverse perspectives, the extent of visual cultural awareness in the state-of-the-art GPT-4V model remains unexplored. To tackle this gap, we extensively probed GPT-4V using the MaRVL benchmark dataset, aiming to investigate its capabilities and limitations in visual understanding with a focus on cultural aspects. Specifically, we introduced three visual related tasks, i.e. caption classification, pairwise caption"},"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":"2402.06015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T19:25:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"25ae5f3587c20ae03304a14bba4502a4919525bcb8899a1050bc5deccdc341e5","abstract_canon_sha256":"15e2afea449e1f32d1d8d6e21c89363fab214d676168abe3b1bf9cadad9383f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:33.346447Z","signature_b64":"AmaztJVQDIg2FKOZEwjXpoCFXWneSON5zaqIJ67h+zVCXOhWHOmwCUjdwvXcdXL8YD+cKmTq2nGOQaF+6V5gCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"187cc7f5d2b9ec8158669e3f328f97c434afa00dad81bff6e492e8eb705555f7","last_reissued_at":"2026-07-05T07:45:33.345882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:33.345882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Antonia Karamolegkou, Daniel Hershcovich, Jiaang Li, Wenyan Li, Yifei Yuan, Yong Cao","submitted_at":"2024-02-08T19:25:40Z","abstract_excerpt":"Pretrained large Vision-Language models have drawn considerable interest in recent years due to their remarkable performance. Despite considerable efforts to assess these models from diverse perspectives, the extent of visual cultural awareness in the state-of-the-art GPT-4V model remains unexplored. To tackle this gap, we extensively probed GPT-4V using the MaRVL benchmark dataset, aiming to investigate its capabilities and limitations in visual understanding with a focus on cultural aspects. Specifically, we introduced three visual related tasks, i.e. caption classification, pairwise caption"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06015","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/2402.06015/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":"2402.06015","created_at":"2026-07-05T07:45:33.345943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06015v2","created_at":"2026-07-05T07:45:33.345943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06015","created_at":"2026-07-05T07:45:33.345943+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB6MP5OSXHWI","created_at":"2026-07-05T07:45:33.345943+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB6MP5OSXHWICWDG","created_at":"2026-07-05T07:45:33.345943+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB6MP5OS","created_at":"2026-07-05T07:45:33.345943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ","json":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ.json","graph_json":"https://pith.science/api/pith-number/DB6MP5OSXHWICWDGTY7TFD4XYQ/graph.json","events_json":"https://pith.science/api/pith-number/DB6MP5OSXHWICWDGTY7TFD4XYQ/events.json","paper":"https://pith.science/paper/DB6MP5OS"},"agent_actions":{"view_html":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ","download_json":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ.json","view_paper":"https://pith.science/paper/DB6MP5OS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06015&json=true","fetch_graph":"https://pith.science/api/pith-number/DB6MP5OSXHWICWDGTY7TFD4XYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DB6MP5OSXHWICWDGTY7TFD4XYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ/action/storage_attestation","attest_author":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ/action/author_attestation","sign_citation":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ/action/citation_signature","submit_replication":"https://pith.science/pith/DB6MP5OSXHWICWDGTY7TFD4XYQ/action/replication_record"}},"created_at":"2026-07-05T07:45:33.345943+00:00","updated_at":"2026-07-05T07:45:33.345943+00:00"}