{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A5BA7QKL6CHV3YRDP6QTQOH2BA","short_pith_number":"pith:A5BA7QKL","schema_version":"1.0","canonical_sha256":"07420fc14bf08f5de2237fa13838fa080bb6f8bb34690ab1749b28bf46e2b5bc","source":{"kind":"arxiv","id":"2403.10378","version":1},"attestation_state":"computed","paper":{"title":"EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dimitar Iliyanov Dimitrov, Haonan Li, Ivan Koychev, Preslav Nakov, Rocktim Jyoti Das, Simeon Emilov Hristov","submitted_at":"2024-03-15T15:08:39Z","abstract_excerpt":"We introduce EXAMS-V, a new challenging multi-discipline multimodal multilingual exam benchmark for evaluating vision language models. It consists of 20,932 multiple-choice questions across 20 school disciplines covering natural science, social science, and other miscellaneous studies, e.g., religion, fine arts, business, etc. EXAMS-V includes a variety of multimodal features such as text, images, tables, figures, diagrams, maps, scientific symbols, and equations. The questions come in 11 languages from 7 language families. Unlike existing benchmarks, EXAMS-V is uniquely curated by gathering s"},"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":"2403.10378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-15T15:08:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b98373230aa65854352f0d57d95e431d59843c9f3c45a2fb9ac8165ea0bb2adb","abstract_canon_sha256":"24a7c42cba2f78ab2e7e61dea78c3616841bfd7c6959072848a5f48b99819e99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:34.525791Z","signature_b64":"mjBBshQ6+aypccXrxf3dQxjd98n21Xj0l7aCzO51q8Wss69/HmkeqZNnM0bWLiXkfqSERFmH8q5nBB+9vPr8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07420fc14bf08f5de2237fa13838fa080bb6f8bb34690ab1749b28bf46e2b5bc","last_reissued_at":"2026-07-05T07:56:34.525267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:34.525267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dimitar Iliyanov Dimitrov, Haonan Li, Ivan Koychev, Preslav Nakov, Rocktim Jyoti Das, Simeon Emilov Hristov","submitted_at":"2024-03-15T15:08:39Z","abstract_excerpt":"We introduce EXAMS-V, a new challenging multi-discipline multimodal multilingual exam benchmark for evaluating vision language models. It consists of 20,932 multiple-choice questions across 20 school disciplines covering natural science, social science, and other miscellaneous studies, e.g., religion, fine arts, business, etc. EXAMS-V includes a variety of multimodal features such as text, images, tables, figures, diagrams, maps, scientific symbols, and equations. The questions come in 11 languages from 7 language families. Unlike existing benchmarks, EXAMS-V is uniquely curated by gathering s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10378","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/2403.10378/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":"2403.10378","created_at":"2026-07-05T07:56:34.525334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10378v1","created_at":"2026-07-05T07:56:34.525334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10378","created_at":"2026-07-05T07:56:34.525334+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5BA7QKL6CHV","created_at":"2026-07-05T07:56:34.525334+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5BA7QKL6CHV3YRD","created_at":"2026-07-05T07:56:34.525334+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5BA7QKL","created_at":"2026-07-05T07:56:34.525334+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/A5BA7QKL6CHV3YRDP6QTQOH2BA","json":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA.json","graph_json":"https://pith.science/api/pith-number/A5BA7QKL6CHV3YRDP6QTQOH2BA/graph.json","events_json":"https://pith.science/api/pith-number/A5BA7QKL6CHV3YRDP6QTQOH2BA/events.json","paper":"https://pith.science/paper/A5BA7QKL"},"agent_actions":{"view_html":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA","download_json":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA.json","view_paper":"https://pith.science/paper/A5BA7QKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10378&json=true","fetch_graph":"https://pith.science/api/pith-number/A5BA7QKL6CHV3YRDP6QTQOH2BA/graph.json","fetch_events":"https://pith.science/api/pith-number/A5BA7QKL6CHV3YRDP6QTQOH2BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA/action/storage_attestation","attest_author":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA/action/author_attestation","sign_citation":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA/action/citation_signature","submit_replication":"https://pith.science/pith/A5BA7QKL6CHV3YRDP6QTQOH2BA/action/replication_record"}},"created_at":"2026-07-05T07:56:34.525334+00:00","updated_at":"2026-07-05T07:56:34.525334+00:00"}