{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NH2LNOSZ7SK7HRZ6YAMOKGPNAT","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":"89cba74872ef0fc039faa1b29328dc6b5c0b8fac1b567271ca5678812b4d7bf2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:21:41Z","title_canon_sha256":"cdfa02880346011ae4c25ac59b85be7ea699f8b1d09cf95b869c5ea78c702040"},"schema_version":"1.0","source":{"id":"2407.10920","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10920","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10920v3","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10920","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"NH2LNOSZ7SK7","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"pith_short_16","alias_value":"NH2LNOSZ7SK7HRZ6","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"pith_short_8","alias_value":"NH2LNOSZ","created_at":"2026-07-05T09:20:01Z"}],"graph_snapshots":[{"event_id":"sha256:cf20d35a41f600e3f3d27d54c2863311111d0b6085825f01a1f7970441d3d4d4","target":"graph","created_at":"2026-07-05T09:20:01Z","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/2407.10920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aishwarya Agrawal, Kanishk Jain, Karolina Sta\\'nczak, Lisa Anne Hendricks, Rabiul Awal, Shravan Nayak, Siva Reddy, Sjoerd van Steenkiste","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:21:41Z","title":"Benchmarking Vision Language Models for Cultural Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10920","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":"sha256:1e764351031072571c1ac09f1a19c24193c294db72cf54e02aa62facd87bab00","target":"record","created_at":"2026-07-05T09:20:01Z","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":"89cba74872ef0fc039faa1b29328dc6b5c0b8fac1b567271ca5678812b4d7bf2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T17:21:41Z","title_canon_sha256":"cdfa02880346011ae4c25ac59b85be7ea699f8b1d09cf95b869c5ea78c702040"},"schema_version":"1.0","source":{"id":"2407.10920","kind":"arxiv","version":3}},"canonical_sha256":"69f4b6ba59fc95f3c73ec018e519ed04ed3055d617dc3b9af36f90b3d1e885fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69f4b6ba59fc95f3c73ec018e519ed04ed3055d617dc3b9af36f90b3d1e885fc","first_computed_at":"2026-07-05T09:20:01.131162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:01.131162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lXV6M2vLuh4SLx7E5n0e4gQgkqIro4LREpOmwWiMZF9pPNYd/701b6wZCY326E7N6o05nA2EvRX58W5nrs8rBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:01.131600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10920","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e764351031072571c1ac09f1a19c24193c294db72cf54e02aa62facd87bab00","sha256:cf20d35a41f600e3f3d27d54c2863311111d0b6085825f01a1f7970441d3d4d4"],"state_sha256":"2b2bd17e7a0bd86a499c04bcf9f754ba2115ed50d74266c9d4b45bddbfce12c8"}