{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QC2ACACPF2BAC5R6GYKDXYB3BS","short_pith_number":"pith:QC2ACACP","schema_version":"1.0","canonical_sha256":"80b401004f2e8201763e36143be03b0cb54a7d50633ee89d98eebaf630ded9dc","source":{"kind":"arxiv","id":"2506.15594","version":1},"attestation_state":"computed","paper":{"title":"WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Angelika Romanou, Julian Martin Eisenschlos, Karl Aberer, Matin Ansaripour, Negar Foroutan, R\\'emi Lebret","submitted_at":"2025-06-18T16:09:18Z","abstract_excerpt":"Documents are fundamental to preserving and disseminating information, often incorporating complex layouts, tables, and charts that pose significant challenges for automatic document understanding (DU). While vision-language large models (VLLMs) have demonstrated improvements across various tasks, their effectiveness in processing long-context vision inputs remains unclear. This paper introduces WikiMixQA, a benchmark comprising 1,000 multiple-choice questions (MCQs) designed to evaluate cross-modal reasoning over tables and charts extracted from 4,000 Wikipedia pages spanning seven distinct t"},"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":"2506.15594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T16:09:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"10595674f93cb4216072565ded2215124ff0d70b6c7c6dbe06e0ca3bde46a1eb","abstract_canon_sha256":"c937a3192a1598a04e2252ff4849375e5c017459a5507e0f4a95663a25b96fa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:46.697490Z","signature_b64":"I9xmCDSIbk/Hp2n8xQ6u+MF5HMq/SZwh6x7+73c1YdTtyvTivNE29mP0zF47no++AV4+L++HRnCvZk+t6AaUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80b401004f2e8201763e36143be03b0cb54a7d50633ee89d98eebaf630ded9dc","last_reissued_at":"2026-07-05T11:23:46.696945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:46.696945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Angelika Romanou, Julian Martin Eisenschlos, Karl Aberer, Matin Ansaripour, Negar Foroutan, R\\'emi Lebret","submitted_at":"2025-06-18T16:09:18Z","abstract_excerpt":"Documents are fundamental to preserving and disseminating information, often incorporating complex layouts, tables, and charts that pose significant challenges for automatic document understanding (DU). While vision-language large models (VLLMs) have demonstrated improvements across various tasks, their effectiveness in processing long-context vision inputs remains unclear. This paper introduces WikiMixQA, a benchmark comprising 1,000 multiple-choice questions (MCQs) designed to evaluate cross-modal reasoning over tables and charts extracted from 4,000 Wikipedia pages spanning seven distinct t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15594","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/2506.15594/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":"2506.15594","created_at":"2026-07-05T11:23:46.697006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15594v1","created_at":"2026-07-05T11:23:46.697006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15594","created_at":"2026-07-05T11:23:46.697006+00:00"},{"alias_kind":"pith_short_12","alias_value":"QC2ACACPF2BA","created_at":"2026-07-05T11:23:46.697006+00:00"},{"alias_kind":"pith_short_16","alias_value":"QC2ACACPF2BAC5R6","created_at":"2026-07-05T11:23:46.697006+00:00"},{"alias_kind":"pith_short_8","alias_value":"QC2ACACP","created_at":"2026-07-05T11:23:46.697006+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/QC2ACACPF2BAC5R6GYKDXYB3BS","json":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS.json","graph_json":"https://pith.science/api/pith-number/QC2ACACPF2BAC5R6GYKDXYB3BS/graph.json","events_json":"https://pith.science/api/pith-number/QC2ACACPF2BAC5R6GYKDXYB3BS/events.json","paper":"https://pith.science/paper/QC2ACACP"},"agent_actions":{"view_html":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS","download_json":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS.json","view_paper":"https://pith.science/paper/QC2ACACP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15594&json=true","fetch_graph":"https://pith.science/api/pith-number/QC2ACACPF2BAC5R6GYKDXYB3BS/graph.json","fetch_events":"https://pith.science/api/pith-number/QC2ACACPF2BAC5R6GYKDXYB3BS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS/action/storage_attestation","attest_author":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS/action/author_attestation","sign_citation":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS/action/citation_signature","submit_replication":"https://pith.science/pith/QC2ACACPF2BAC5R6GYKDXYB3BS/action/replication_record"}},"created_at":"2026-07-05T11:23:46.697006+00:00","updated_at":"2026-07-05T11:23:46.697006+00:00"}