{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B765MWWUXIL76I7VAKQFL3DLLM","short_pith_number":"pith:B765MWWU","schema_version":"1.0","canonical_sha256":"0ffdd65ad4ba17ff23f502a055ec6b5b2be4c3db0a9f27544fb9436b2fba578e","source":{"kind":"arxiv","id":"2506.11114","version":1},"attestation_state":"computed","paper":{"title":"KokushiMD-10: Benchmark for Evaluating Large Language Models on Ten Japanese National Healthcare Licensing Examinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junyu Liu, Kaiqi Yan, Momoko Nagai-Tanima, Qian Niu, Tianyang Wang, Tomoki Aoyama","submitted_at":"2025-06-09T02:26:02Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated notable performance in medical licensing exams. However, comprehensive evaluation of LLMs across various healthcare roles, particularly in high-stakes clinical scenarios, remains a challenge. Existing benchmarks are typically text-based, English-centric, and focus primarily on medicines, which limits their ability to assess broader healthcare knowledge and multimodal reasoning. To address these gaps, we introduce KokushiMD-10, the first multimodal benchmark constructed from ten Japanese national healthcare licensing exams. This "},"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":"2506.11114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T02:26:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33d1ed39ed447397e590f5e04f55512bf0405214dc45c2f86309584409764b3e","abstract_canon_sha256":"7bdcdd6149167104c9e69d9dde88c0c02b6dbf27499842020de6b4e77be91580"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:59.651533Z","signature_b64":"pY1QH3mWHYu5EDiF1vZVQlX129Zf2kKHybG+Hv9ARoQpXKaXE1suz16RWrrp9aILWsFWrfCDR835creyh/f3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ffdd65ad4ba17ff23f502a055ec6b5b2be4c3db0a9f27544fb9436b2fba578e","last_reissued_at":"2026-07-05T11:20:59.651106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:59.651106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KokushiMD-10: Benchmark for Evaluating Large Language Models on Ten Japanese National Healthcare Licensing Examinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junyu Liu, Kaiqi Yan, Momoko Nagai-Tanima, Qian Niu, Tianyang Wang, Tomoki Aoyama","submitted_at":"2025-06-09T02:26:02Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated notable performance in medical licensing exams. However, comprehensive evaluation of LLMs across various healthcare roles, particularly in high-stakes clinical scenarios, remains a challenge. Existing benchmarks are typically text-based, English-centric, and focus primarily on medicines, which limits their ability to assess broader healthcare knowledge and multimodal reasoning. To address these gaps, we introduce KokushiMD-10, the first multimodal benchmark constructed from ten Japanese national healthcare licensing exams. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11114","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/2506.11114/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":"2506.11114","created_at":"2026-07-05T11:20:59.651161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11114v1","created_at":"2026-07-05T11:20:59.651161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11114","created_at":"2026-07-05T11:20:59.651161+00:00"},{"alias_kind":"pith_short_12","alias_value":"B765MWWUXIL7","created_at":"2026-07-05T11:20:59.651161+00:00"},{"alias_kind":"pith_short_16","alias_value":"B765MWWUXIL76I7V","created_at":"2026-07-05T11:20:59.651161+00:00"},{"alias_kind":"pith_short_8","alias_value":"B765MWWU","created_at":"2026-07-05T11:20:59.651161+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/B765MWWUXIL76I7VAKQFL3DLLM","json":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM.json","graph_json":"https://pith.science/api/pith-number/B765MWWUXIL76I7VAKQFL3DLLM/graph.json","events_json":"https://pith.science/api/pith-number/B765MWWUXIL76I7VAKQFL3DLLM/events.json","paper":"https://pith.science/paper/B765MWWU"},"agent_actions":{"view_html":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM","download_json":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM.json","view_paper":"https://pith.science/paper/B765MWWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11114&json=true","fetch_graph":"https://pith.science/api/pith-number/B765MWWUXIL76I7VAKQFL3DLLM/graph.json","fetch_events":"https://pith.science/api/pith-number/B765MWWUXIL76I7VAKQFL3DLLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM/action/storage_attestation","attest_author":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM/action/author_attestation","sign_citation":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM/action/citation_signature","submit_replication":"https://pith.science/pith/B765MWWUXIL76I7VAKQFL3DLLM/action/replication_record"}},"created_at":"2026-07-05T11:20:59.651161+00:00","updated_at":"2026-07-05T11:20:59.651161+00:00"}