{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O5UKZ2ZEY22554M5VDWO6FT6MS","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"98b61e4159f1c3c00045858d68369dd2e9c4126583378490f258ca3f97cb5928","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:58:24Z","title_canon_sha256":"26bf2a64465456a7cce5839c63f1d4cb1d69434d778b042eb9d53457899ec69e"},"schema_version":"1.0","source":{"id":"2605.21479","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21479","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21479v1","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21479","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"O5UKZ2ZEY225","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"O5UKZ2ZEY22554M5","created_at":"2026-05-21T02:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"O5UKZ2ZE","created_at":"2026-05-21T02:05:39Z"}],"graph_snapshots":[{"event_id":"sha256:d9b64fd2dace2db0ba3b9f3a5bc832035ebbfe21306858942f2b4b8931383d3c","target":"graph","created_at":"2026-05-21T02:05:39Z","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/2605.21479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce WikiVQABench, a human-curated knowledge-grounded VQA benchmark constructed by systematically combining Wikipedia images, their associated article captions, and structured knowledge from Wikidata. Our pipeline uses large language models (LLMs) to generate candidate multiple-choice image-question-answer sets. All genera","authors_text":"Anna Lisa Gentile, Basel Shbita, Pengyuan Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:58:24Z","title":"WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21479","kind":"arxiv","version":1},"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":"sha256:80f7855c11ca843bf7c4d6a520a4674d0f673707d80471efd6929686f571dc16","target":"record","created_at":"2026-05-21T02:05:39Z","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":"98b61e4159f1c3c00045858d68369dd2e9c4126583378490f258ca3f97cb5928","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:58:24Z","title_canon_sha256":"26bf2a64465456a7cce5839c63f1d4cb1d69434d778b042eb9d53457899ec69e"},"schema_version":"1.0","source":{"id":"2605.21479","kind":"arxiv","version":1}},"canonical_sha256":"7768aceb24c6b5def19da8ecef167e648d402fc227f674876f380a86385727c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7768aceb24c6b5def19da8ecef167e648d402fc227f674876f380a86385727c1","first_computed_at":"2026-05-21T02:05:39.200055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:39.200055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IktsWhzwcD3l4v6ra6sCxDt13I+5yc0L/x8yGX/wBVn6vWnkrfslI+Z1fwU7/oz2cpzhW3Y5Ia6XEAocSHvZDA==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:39.200852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21479","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:3af3f8fcebff9709a31fd2d05674c2e00fff7a35e53c0c3f0cc93a62731f819e","sha256:c8959443cf85314bd91ca006ed9a87bbda80810e8e3d054aa3917995969e465a"]}],"invalid_events":[],"applied_event_ids":["sha256:80f7855c11ca843bf7c4d6a520a4674d0f673707d80471efd6929686f571dc16","sha256:d9b64fd2dace2db0ba3b9f3a5bc832035ebbfe21306858942f2b4b8931383d3c"],"state_sha256":"1254cbc98177d1bb527bd8c5f30aaa934dbb31502bbf4726ce25ea574d918bfa"}