{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K4WM3U5LYUVSFCIIS436DUT7CV","short_pith_number":"pith:K4WM3U5L","schema_version":"1.0","canonical_sha256":"572ccdd3abc52b2289089737e1d27f157eaec2de6fcf18f26e68fda7aa041ae3","source":{"kind":"arxiv","id":"2605.24636","version":1},"attestation_state":"computed","paper":{"title":"GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Benyou Wang, Chunfeng Luo, Falk Schwendicke, Hexian Zhang, Jiaming Zhang, Jianquan Li, Jingyi Liang, Junjie Zhao, Junwen Wang, Junying Chen, Liangyi Chen, Lijian Jin, Nhan L Tran, Pradeep Singh, Shan Jiang, Shuzhi Deng, Tianrui Liu, Wei-fa Yang, Wenjing Yi, Xiang Liu, Zhenwei Wen, Zhenyang Cai, Zhuhui Bai, Zixu Zhang, Zuolin Jin","submitted_at":"2026-05-23T15:53:44Z","abstract_excerpt":"While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge r"},"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":"2605.24636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T15:53:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1b81f1f3d3de105c6dec2308d129207765bc18ef7007d1bcd05a6b73192ffa7","abstract_canon_sha256":"b050070d09ee6d5f2126669709c82ce5d49a3189648a701c62cc800d53ff1882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:50.469846Z","signature_b64":"I99N/tURtddiI9JCryFJ5ufdd/Wl3z9lUU8GicYTvCQIX1wFS915BCCSCBthJRhCKI67RVDm63V6zstlZw6OCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572ccdd3abc52b2289089737e1d27f157eaec2de6fcf18f26e68fda7aa041ae3","last_reissued_at":"2026-05-26T01:03:50.469207Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:50.469207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Benyou Wang, Chunfeng Luo, Falk Schwendicke, Hexian Zhang, Jiaming Zhang, Jianquan Li, Jingyi Liang, Junjie Zhao, Junwen Wang, Junying Chen, Liangyi Chen, Lijian Jin, Nhan L Tran, Pradeep Singh, Shan Jiang, Shuzhi Deng, Tianrui Liu, Wei-fa Yang, Wenjing Yi, Xiang Liu, Zhenwei Wen, Zhenyang Cai, Zhuhui Bai, Zixu Zhang, Zuolin Jin","submitted_at":"2026-05-23T15:53:44Z","abstract_excerpt":"While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24636","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/2605.24636/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":"2605.24636","created_at":"2026-05-26T01:03:50.469326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24636v1","created_at":"2026-05-26T01:03:50.469326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24636","created_at":"2026-05-26T01:03:50.469326+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4WM3U5LYUVS","created_at":"2026-05-26T01:03:50.469326+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4WM3U5LYUVSFCII","created_at":"2026-05-26T01:03:50.469326+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4WM3U5L","created_at":"2026-05-26T01:03:50.469326+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/K4WM3U5LYUVSFCIIS436DUT7CV","json":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV.json","graph_json":"https://pith.science/api/pith-number/K4WM3U5LYUVSFCIIS436DUT7CV/graph.json","events_json":"https://pith.science/api/pith-number/K4WM3U5LYUVSFCIIS436DUT7CV/events.json","paper":"https://pith.science/paper/K4WM3U5L"},"agent_actions":{"view_html":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV","download_json":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV.json","view_paper":"https://pith.science/paper/K4WM3U5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24636&json=true","fetch_graph":"https://pith.science/api/pith-number/K4WM3U5LYUVSFCIIS436DUT7CV/graph.json","fetch_events":"https://pith.science/api/pith-number/K4WM3U5LYUVSFCIIS436DUT7CV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV/action/storage_attestation","attest_author":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV/action/author_attestation","sign_citation":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV/action/citation_signature","submit_replication":"https://pith.science/pith/K4WM3U5LYUVSFCIIS436DUT7CV/action/replication_record"}},"created_at":"2026-05-26T01:03:50.469326+00:00","updated_at":"2026-05-26T01:03:50.469326+00:00"}