{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O5UKZ2ZEY22554M5VDWO6FT6MS","short_pith_number":"pith:O5UKZ2ZE","schema_version":"1.0","canonical_sha256":"7768aceb24c6b5def19da8ecef167e648d402fc227f674876f380a86385727c1","source":{"kind":"arxiv","id":"2605.21479","version":1},"attestation_state":"computed","paper":{"title":"WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Lisa Gentile, Basel Shbita, Pengyuan Li","submitted_at":"2026-05-20T17:58:24Z","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"},"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":"2605.21479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:58:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26bf2a64465456a7cce5839c63f1d4cb1d69434d778b042eb9d53457899ec69e","abstract_canon_sha256":"98b61e4159f1c3c00045858d68369dd2e9c4126583378490f258ca3f97cb5928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:39.200852Z","signature_b64":"IktsWhzwcD3l4v6ra6sCxDt13I+5yc0L/x8yGX/wBVn6vWnkrfslI+Z1fwU7/oz2cpzhW3Y5Ia6XEAocSHvZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7768aceb24c6b5def19da8ecef167e648d402fc227f674876f380a86385727c1","last_reissued_at":"2026-05-21T02:05:39.200055Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:39.200055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Lisa Gentile, Basel Shbita, Pengyuan Li","submitted_at":"2026-05-20T17:58:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21479","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/2605.21479/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":"2605.21479","created_at":"2026-05-21T02:05:39.200189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21479v1","created_at":"2026-05-21T02:05:39.200189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21479","created_at":"2026-05-21T02:05:39.200189+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5UKZ2ZEY225","created_at":"2026-05-21T02:05:39.200189+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5UKZ2ZEY22554M5","created_at":"2026-05-21T02:05:39.200189+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5UKZ2ZE","created_at":"2026-05-21T02:05:39.200189+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/O5UKZ2ZEY22554M5VDWO6FT6MS","json":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS.json","graph_json":"https://pith.science/api/pith-number/O5UKZ2ZEY22554M5VDWO6FT6MS/graph.json","events_json":"https://pith.science/api/pith-number/O5UKZ2ZEY22554M5VDWO6FT6MS/events.json","paper":"https://pith.science/paper/O5UKZ2ZE"},"agent_actions":{"view_html":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS","download_json":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS.json","view_paper":"https://pith.science/paper/O5UKZ2ZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21479&json=true","fetch_graph":"https://pith.science/api/pith-number/O5UKZ2ZEY22554M5VDWO6FT6MS/graph.json","fetch_events":"https://pith.science/api/pith-number/O5UKZ2ZEY22554M5VDWO6FT6MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS/action/storage_attestation","attest_author":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS/action/author_attestation","sign_citation":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS/action/citation_signature","submit_replication":"https://pith.science/pith/O5UKZ2ZEY22554M5VDWO6FT6MS/action/replication_record"}},"created_at":"2026-05-21T02:05:39.200189+00:00","updated_at":"2026-05-21T02:05:39.200189+00:00"}