{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NH2LNOSZ7SK7HRZ6YAMOKGPNAT","short_pith_number":"pith:NH2LNOSZ","schema_version":"1.0","canonical_sha256":"69f4b6ba59fc95f3c73ec018e519ed04ed3055d617dc3b9af36f90b3d1e885fc","source":{"kind":"arxiv","id":"2407.10920","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking Vision Language Models for Cultural Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Kanishk Jain, Karolina Sta\\'nczak, Lisa Anne Hendricks, Rabiul Awal, Shravan Nayak, Siva Reddy, Sjoerd van Steenkiste","submitted_at":"2024-07-15T17:21:41Z","abstract_excerpt":"Foundation models and vision-language pre-training have notably advanced Vision Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their performance has been typically assessed on general scene understanding - recognizing objects, attributes, and actions - rather than cultural comprehension. This study introduces CulturalVQA, a visual question-answering benchmark aimed at assessing VLM's geo-diverse cultural understanding. We curate a collection of 2,378 image-question pairs with 1-5 answers per question representing cultures from 11 countries across"},"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":"2407.10920","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:21:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cdfa02880346011ae4c25ac59b85be7ea699f8b1d09cf95b869c5ea78c702040","abstract_canon_sha256":"89cba74872ef0fc039faa1b29328dc6b5c0b8fac1b567271ca5678812b4d7bf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:01.131600Z","signature_b64":"lXV6M2vLuh4SLx7E5n0e4gQgkqIro4LREpOmwWiMZF9pPNYd/701b6wZCY326E7N6o05nA2EvRX58W5nrs8rBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69f4b6ba59fc95f3c73ec018e519ed04ed3055d617dc3b9af36f90b3d1e885fc","last_reissued_at":"2026-07-05T09:20:01.131162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:01.131162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Vision Language Models for Cultural Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Kanishk Jain, Karolina Sta\\'nczak, Lisa Anne Hendricks, Rabiul Awal, Shravan Nayak, Siva Reddy, Sjoerd van Steenkiste","submitted_at":"2024-07-15T17:21:41Z","abstract_excerpt":"Foundation models and vision-language pre-training have notably advanced Vision Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their performance has been typically assessed on general scene understanding - recognizing objects, attributes, and actions - rather than cultural comprehension. This study introduces CulturalVQA, a visual question-answering benchmark aimed at assessing VLM's geo-diverse cultural understanding. We curate a collection of 2,378 image-question pairs with 1-5 answers per question representing cultures from 11 countries across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10920","kind":"arxiv","version":3},"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/2407.10920/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":"2407.10920","created_at":"2026-07-05T09:20:01.131218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10920v3","created_at":"2026-07-05T09:20:01.131218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10920","created_at":"2026-07-05T09:20:01.131218+00:00"},{"alias_kind":"pith_short_12","alias_value":"NH2LNOSZ7SK7","created_at":"2026-07-05T09:20:01.131218+00:00"},{"alias_kind":"pith_short_16","alias_value":"NH2LNOSZ7SK7HRZ6","created_at":"2026-07-05T09:20:01.131218+00:00"},{"alias_kind":"pith_short_8","alias_value":"NH2LNOSZ","created_at":"2026-07-05T09:20:01.131218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03330","citing_title":"Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT","json":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT.json","graph_json":"https://pith.science/api/pith-number/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/graph.json","events_json":"https://pith.science/api/pith-number/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/events.json","paper":"https://pith.science/paper/NH2LNOSZ"},"agent_actions":{"view_html":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT","download_json":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT.json","view_paper":"https://pith.science/paper/NH2LNOSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10920&json=true","fetch_graph":"https://pith.science/api/pith-number/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/graph.json","fetch_events":"https://pith.science/api/pith-number/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/action/storage_attestation","attest_author":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/action/author_attestation","sign_citation":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/action/citation_signature","submit_replication":"https://pith.science/pith/NH2LNOSZ7SK7HRZ6YAMOKGPNAT/action/replication_record"}},"created_at":"2026-07-05T09:20:01.131218+00:00","updated_at":"2026-07-05T09:20:01.131218+00:00"}