{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.24636", "kind": "paper", "url": "https://arxiv.org/abs/2605.24636"}], "authors": ["Junjie Zhao", "Jingyi Liang", "Zhenyang Cai", "Jiaming Zhang", "Zhenwei Wen", "Shuzhi Deng", "Wenjing Yi", "Chunfeng Luo", "Hexian Zhang", "Junying Chen", "Tianrui Liu", "Zhuhui Bai", "Zixu Zhang", "Pradeep Singh", "Xiang Liu", "Jianquan Li", "Nhan L Tran", "Falk Schwendicke", "Zuolin Jin", "Lijian Jin", "Liangyi Chen", "Wei-fa Yang", "Benyou Wang", "Junwen Wang", "Shan Jiang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.24636", "source_url": "https://arxiv.org/abs/2605.24636"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "Reasoning"], "description": {"en": "GlobalDentBench evaluates LLM clinical reasoning in dentistry with 8,978 expert-validated questions across 14 specialties and 88 countries, covering multiple-choice, short-answer, and case-based formats at three reasoning levels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.24636", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.24636", "title": "GlobalDentBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.24636", "modality": null, "name": "GlobalDentBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_globaldentbench_f42d9d35", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "5a8467af3f41938645f96185fa1ebdb692f86c0bef7c64f3c5418a91bb506cfc", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.24636"}, "publisher": null, "released": "2026-05-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.24636", "source_url": "https://arxiv.org/abs/2605.24636"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-24636", "source": "claire_radar", "source_benchmark_id": "2605.24636", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2605.24636", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b3bfc579c8c91cd9b50169e0a1580df569385a8933a4ee21a87069f1b071b5a2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GlobalDentBench evaluates LLM clinical reasoning in dentistry with 8,978 expert-validated questions across 14 specialties and 88 countries, covering multiple-choice, short-answer, and case-based formats at three reasoning levels.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "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."}, "familyId": "bmf_6790f75fc2f9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_globaldentbench_f42d9d35", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.24636", "paper": "https://arxiv.org/abs/2605.24636", "pdf": "https://arxiv.org/pdf/2605.24636", "project": null, "report": "https://arxiv.org/abs/2605.24636"}, "metrics": [], "motivation": "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.", "name": "GlobalDentBench", "oneLine": "GlobalDentBench evaluates LLM clinical reasoning in dentistry with 8,978 expert-validated questions across 14 specialties and 88 countries, covering multiple-choice, short-answer, and case-based formats at three reasoning levels.", "paperTitle": "GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.24636", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "GlobalDentBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2605.24636"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-05-23", "source": {"authors": ["Junjie Zhao and Jingyi Liang and Zhenyang Cai and Jiaming Zhang and Zhenwei Wen and Shuzhi Deng and Wenjing Yi and Chunfeng Luo and Hexian Zhang and Junying Chen and Tianrui Liu and Zhuhui Bai and Zixu Zhang and Pradeep Singh and Xiang Liu and Jianquan Li and Nhan L Tran and Falk Schwendicke and Zuolin Jin and Lijian Jin and Liangyi Chen and Wei-fa Yang and Benyou Wang and Junwen Wang and Shan Jiang"], "categories": ["cs.AI", "cs.CL"], "id": "2605.24636", "title": "GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration", "type": "arxiv", "url": "https://arxiv.org/abs/2605.24636"}, "sourceUpdatedAt": "2026-05-26T17:07:57Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "It provides a multinational dental benchmark with expert calibration to assess knowledge recall, routine and individualized reasoning, revealing safety risks in LLM clinical recommendations and supporting rigorous validation before deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
