{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T13:13:47Z","timestamp":1790082827438,"version":"4.0.1"},"posted":{"date-parts":[[2026,9,17]]},"group-title":"Oncology","reference-count":66,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"award":["ME-2024C2-37484"],"award-info":[{"award-number":["ME-2024C2-37484"]}],"id":[{"id":"https:\/\/ror.org\/014q65q44","id-type":"ROR","asserted-by":"publisher"}]},{"award":["U54CA274516-01A1"],"award-info":[{"award-number":["U54CA274516-01A1"]}],"id":[{"id":"https:\/\/ror.org\/040gcmg81","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R01CA294033-01"],"award-info":[{"award-number":["R01CA294033-01"]}],"id":[{"id":"https:\/\/ror.org\/040gcmg81","id-type":"ROR","asserted-by":"publisher"}]},{"award":["2U24CA248010"],"award-info":[{"award-number":["2U24CA248010"]}],"id":[{"id":"https:\/\/ror.org\/040gcmg81","id-type":"ROR","asserted-by":"publisher"}]},{"award":["ASTRO-CSDG-24-1244514-01-CTPS"],"award-info":[{"award-number":["ASTRO-CSDG-24-1244514-01-CTPS"]}],"id":[{"id":"https:\/\/ror.org\/054kfq324","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Woods Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  LLMs are increasingly used to mediate patient communication, yet scalable evaluation of their safety, accuracy, and communication quality remains an open problem. LLM judges have emerged as automated evaluators, but whether they can holistically replicate human expert judgment is unvalidated. Informed consent for clinical trials presents a demanding case for such validation because it requires conveying complex information to lay audiences under ethical and safety constraints. We developed a stakeholder-informed seven-criterion evaluation rubric spanning safety, reliability, and communication quality. Clinician reference ratings showed strong interrater reliability across all criteria. We validated the rubric on the Informed CONsent Benchmark (ICON-Bench) and benchmarked 19 LLM judges across multiple implementation strategies. LLM judges achieved strong clinician agreement for safety screening and factual verification (Spearman\n                  <jats:italic>\u03c1<\/jats:italic>\n                  &gt; 0.80) but weaker agreement for communication quality (\n                  <jats:italic>\u03c1<\/jats:italic>\n                  &lt; 0.60). Safety-specialized guard models underperformed general-purpose models. Patient advocates rated communication quality lower than both clinicians and LLM judges. These findings support LLM judges for scalable patient communication oversight while demonstrating the need for recalibration to patient-centered evaluation standards.\n                <\/jats:p>","DOI":"10.64898\/2026.09.16.26363176","type":"posted-content","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T06:00:14Z","timestamp":1789711214000},"source":"Crossref","is-referenced-by-count":0,"title":["Validating LLM judges for automated oversight of patient communication"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6122-8426","authenticated-orcid":false,"given":"Zidu","family":"Xu","sequence":"first","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0838-9263","authenticated-orcid":false,"given":"Johnathan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Neurology, Massachusetts General Hospital, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Columbia University School of Nursing, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thibault","family":"Heintz","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marion","family":"Tonneau","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arsalan","family":"Yaghoubi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Loyola University Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1696-4248","authenticated-orcid":false,"given":"Bingyang","family":"Ye","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6286-6684","authenticated-orcid":false,"given":"Vikram","family":"Goddla","sequence":"additional","affiliation":[{"name":"Harvard College, Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Lehmann","sequence":"additional","affiliation":[{"name":"Department of Medicine, Mass General Brigham, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Data Science, Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elad","family":"Sharon","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David E.","family":"Kozono","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Revette","sequence":"additional","affiliation":[{"name":"Division of Population Sciences, Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Maues","sequence":"additional","affiliation":[{"name":"Guiding Researchers and Advocates to Scientific Partnerships (GRASP), Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thelma","family":"Brown","sequence":"additional","affiliation":[{"name":"NCI Breast Cancer Steering Committee, National Cancer Institute, Bethesda, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Catalano","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond H.","family":"Mak","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitry","family":"Dligach","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Loyola University Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0345-2232","authenticated-orcid":false,"given":"Danielle S.","family":"Bitterman","sequence":"additional","affiliation":[{"name":"Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA"},{"name":"Department of Radiation Oncology, Brigham and Women\u2019s Hospital\/Dana-Farber Cancer Institute, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026092205401039000_2026.09.16.26363176v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02344-7"},{"key":"2026092205401039000_2026.09.16.26363176v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"2026092205401039000_2026.09.16.26363176v1.3","doi-asserted-by":"crossref","unstructured":"Xiao, Z. , Li, T. W. , Karahalios, K. & Sundaram, H . Inform the uninformed: Improving online informed consent reading with an AI-powered chatbot. in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems vol. 2020 1\u201317 (ACM, New York, NY, USA, 2023).","DOI":"10.1145\/3544548.3581252"},{"key":"2026092205401039000_2026.09.16.26363176v1.4","doi-asserted-by":"crossref","first-page":"e2457879","DOI":"10.1001\/jamanetworkopen.2024.57879","article-title":"Large language models for chatbot health advice studies: A systematic review","volume":"8","year":"2025","journal-title":"JAMA Netw. Open"},{"key":"2026092205401039000_2026.09.16.26363176v1.5","doi-asserted-by":"crossref","unstructured":"Chen, S. et al. When helpfulness backfires: LLMs and the risk of false medical information due to sycophantic behavior. NPJ Digit. Med. 8, 605 (2025).","DOI":"10.1038\/s41746-025-02008-z"},{"key":"2026092205401039000_2026.09.16.26363176v1.6","doi-asserted-by":"publisher","DOI":"10.2196\/87367"},{"key":"2026092205401039000_2026.09.16.26363176v1.7","doi-asserted-by":"publisher","DOI":"10.2196\/55138"},{"key":"2026092205401039000_2026.09.16.26363176v1.8","doi-asserted-by":"crossref","unstructured":"Draelos, R. L. et al. Large language models provide unsafe answers to patient-posed medical questions. NPJ Digit. Med. 1\u20139 (2026).","DOI":"10.1038\/s41746-026-02428-5"},{"key":"2026092205401039000_2026.09.16.26363176v1.9","unstructured":"Ethics and governance of artificial intelligence for health: Guidance on large multi-modal models. https:\/\/www.who.int\/publications\/i\/item\/9789240084759 (2025)."},{"key":"2026092205401039000_2026.09.16.26363176v1.10","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21700"},{"key":"2026092205401039000_2026.09.16.26363176v1.11","doi-asserted-by":"publisher","DOI":"10.2196\/84120"},{"key":"2026092205401039000_2026.09.16.26363176v1.12","doi-asserted-by":"crossref","unstructured":"Abbasian, M. et al. Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI. NPJ Digit. Med. 7, 82 (2024).","DOI":"10.1038\/s41746-024-01074-z"},{"key":"2026092205401039000_2026.09.16.26363176v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03328-5"},{"key":"2026092205401039000_2026.09.16.26363176v1.14","doi-asserted-by":"crossref","unstructured":"Croxford, E. et al. Development of a human evaluation framework and correlation with automated metrics for Natural Language Generation of medical diagnoses. AMIA Annu. Symp. Proc. 2024, 309\u2013318 (2024).","DOI":"10.1101\/2024.03.20.24304620"},{"key":"2026092205401039000_2026.09.16.26363176v1.15","doi-asserted-by":"crossref","unstructured":"Tam, T. Y. C. et al. A framework for human evaluation of large language models in healthcare derived from literature review. NPJ Digit. Med. 7, 258 (2024).","DOI":"10.1038\/s41746-024-01258-7"},{"key":"2026092205401039000_2026.09.16.26363176v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03470-0"},{"key":"2026092205401039000_2026.09.16.26363176v1.17","doi-asserted-by":"crossref","unstructured":"Awasthi, R. et al. Human evaluation of large language models in healthcare: gaps, challenges, and the need for standardization. Npj Health Syst. 2, 40 (2025).","DOI":"10.1038\/s44401-025-00043-2"},{"key":"2026092205401039000_2026.09.16.26363176v1.18","doi-asserted-by":"crossref","unstructured":"Zheng, L. et al. Judging LLM-as-a-judge with MT-bench and Chatbot Arena. in Proceedings of the 37th International Conference on Neural Information Processing Systems 46595\u201346623 (Curran Associates Inc., Red Hook, NY, USA, 2023).","DOI":"10.52202\/075280-2020"},{"key":"2026092205401039000_2026.09.16.26363176v1.19","doi-asserted-by":"crossref","unstructured":"Liu, Y . et al. G-eval: NLG evaluation using gpt-4 with better human alignment. in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (eds. Bouamor, H. , Pino, J. & Bali, K .) 2511\u20132522 (Association for Computational Linguistics, Stroudsburg, PA, USA, 2023).","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"2026092205401039000_2026.09.16.26363176v1.20","doi-asserted-by":"crossref","unstructured":"Croxford, E. et al. Evaluating clinical AI summaries with large language models as judges. NPJ Digit. Med. 8, 640 (2025).","DOI":"10.1038\/s41746-025-02005-2"},{"key":"2026092205401039000_2026.09.16.26363176v1.21","doi-asserted-by":"crossref","unstructured":"Zhou, S. et al. Automating expert-level medical reasoning evaluation of large language models. NPJ Digit. Med. 9, 34 (2025).","DOI":"10.1038\/s41746-025-02208-7"},{"key":"2026092205401039000_2026.09.16.26363176v1.22","doi-asserted-by":"publisher","DOI":"10.1370\/afm.250386"},{"key":"2026092205401039000_2026.09.16.26363176v1.23","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","article-title":"Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum","volume":"183","year":"2023","journal-title":"JAMA Intern. Med"},{"key":"2026092205401039000_2026.09.16.26363176v1.24","unstructured":"45 CFR 46.116 --General requirements for informed consent. https:\/\/www.ecfr.gov\/current\/title-45\/subtitle-A\/subchapter-A\/part-46\/subpart-A\/section-46.116."},{"key":"2026092205401039000_2026.09.16.26363176v1.25","unstructured":"Office of the Commissioner. Protection of Human Subjects; Informed Consent. U.S. Food and Drug Administration https:\/\/www.fda.gov\/science-research\/clinical-trials-and-human-subject-protection\/protection-human-subjects-informed-consent (2019)."},{"key":"2026092205401039000_2026.09.16.26363176v1.26","unstructured":"Faden, R. R. & Beauchamp, T. L . A History and Theory of Informed Consent. (Oxford University Press, New York, NY, 1986)."},{"key":"2026092205401039000_2026.09.16.26363176v1.27","doi-asserted-by":"crossref","first-page":"e71817","DOI":"10.2196\/71817","article-title":"Improving patient engagement in phase 2 clinical trials with a trial-specific patient decision aid: Development and usability study","volume":"27","year":"2025","journal-title":"J. Med. Internet Res"},{"key":"2026092205401039000_2026.09.16.26363176v1.28","doi-asserted-by":"crossref","unstructured":"Bernardi, C. et al. How to improve informed consent processes in clinical trials with cancer patients: a qualitative analysis of multidisciplinary experts\u2019 perspectives. BMC Med. Ethics 26, 171 (2025).","DOI":"10.1186\/s12910-025-01348-5"},{"key":"2026092205401039000_2026.09.16.26363176v1.29","doi-asserted-by":"crossref","unstructured":"Pietrzykowski, T. & Smilowska, K . The reality of informed consent: empirical studies on patient comprehension-systematic review. Trials 22, 57 (2021).","DOI":"10.1186\/s13063-020-04969-w"},{"key":"2026092205401039000_2026.09.16.26363176v1.30","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X19896348"},{"key":"2026092205401039000_2026.09.16.26363176v1.31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231350"},{"key":"2026092205401039000_2026.09.16.26363176v1.32","doi-asserted-by":"crossref","first-page":"e45772","DOI":"10.2196\/45772","article-title":"Examining patient engagement in chatbot development approaches for healthy lifestyle and mental wellness interventions: Scoping review","volume":"15","year":"2023","journal-title":"J. Particip. Med"},{"key":"2026092205401039000_2026.09.16.26363176v1.33","doi-asserted-by":"crossref","unstructured":"Liu, Y. et al. Benchmarking large language model-based agent systems for clinical decision tasks. NPJ Digit. Med. 9, 259 (2026).","DOI":"10.1038\/s41746-026-02443-6"},{"key":"2026092205401039000_2026.09.16.26363176v1.34","doi-asserted-by":"crossref","unstructured":"Zhang, B. & Ren, G.-J. Challenges and remedies of domain-specific classifiers as LLM guardrails: Self-harm as a case study. in Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track) (eds. Chen, W. , Yang, Y. , Kachuee, M. & Fu, X.-Y .) 173\u2013182 (Association for Computational Linguistics, Stroudsburg, PA, USA, 2025).","DOI":"10.18653\/v1\/2025.naacl-industry.15"},{"key":"2026092205401039000_2026.09.16.26363176v1.35","unstructured":"Yang, Y. , et al. Ensuring safety and trust: Analyzing the risks of Large Language Models in medicine. ArXiv (2024)."},{"key":"2026092205401039000_2026.09.16.26363176v1.36","unstructured":"Health AI Developer Foundations Terms of Use. Google for Developers https:\/\/developers.google.com\/health-ai-developer-foundations\/terms."},{"key":"2026092205401039000_2026.09.16.26363176v1.37","doi-asserted-by":"crossref","unstructured":"Zhang, G. et al. Closing the gap between open source and commercial large language models for medical evidence summarization. NPJ Digit. Med. 7, 239 (2024).","DOI":"10.1038\/s41746-024-01239-w"},{"key":"2026092205401039000_2026.09.16.26363176v1.38","first-page":"e0001029","article-title":"Cardiology knowledge assessment of retrieval-augmented open versus proprietary large language models. PLOS Digit","volume":"5","year":"2026","journal-title":"Health"},{"key":"2026092205401039000_2026.09.16.26363176v1.39","doi-asserted-by":"crossref","unstructured":"Wind, S. et al. Multi-step retrieval and reasoning improves radiology question answering with large language models. NPJ Digit. Med. 8, 790 (2025).","DOI":"10.1038\/s41746-025-02250-5"},{"key":"2026092205401039000_2026.09.16.26363176v1.40","doi-asserted-by":"crossref","unstructured":"Arvan M. , Gautam, A. , Zalake, M. & Kochendorfer, K. M. UIC at ArchEHR-QA 2025: Tri-step pipeline for reliable grounded medical question answering. in Proceedings of the 24th Workshop on Biomedical Language Processing (Shared Tasks) (eds. Soni, S. & Demner-Fushman, D .) 110\u2013117 (Association for Computational Linguistics, Stroudsburg, PA, USA, 2025).","DOI":"10.18653\/v1\/2025.bionlp-share.14"},{"key":"2026092205401039000_2026.09.16.26363176v1.41","doi-asserted-by":"crossref","unstructured":"Shao, R . et al. LLM-empowered patient-provider communication: A data-centric survey from a clinical perspective. in Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (eds. Inui, K . et al.) 684\u2013705 (The Asian Federation of Natural Language Processing and The Association for Computational Linguistics, Stroudsburg, PA, USA, 2025).","DOI":"10.18653\/v1\/2025.findings-ijcnlp.40"},{"key":"2026092205401039000_2026.09.16.26363176v1.42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.03642"},{"key":"2026092205401039000_2026.09.16.26363176v1.43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2603.07023"},{"key":"2026092205401039000_2026.09.16.26363176v1.44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.08073"},{"key":"2026092205401039000_2026.09.16.26363176v1.45","doi-asserted-by":"crossref","first-page":"e11371","DOI":"10.2196\/11371","article-title":"Design and development of a person-centered patient portal using participatory stakeholder co-design","volume":"21","year":"2019","journal-title":"J. Med. Internet Res"},{"key":"2026092205401039000_2026.09.16.26363176v1.46","doi-asserted-by":"crossref","unstructured":"Wang, Z. et al. Stakeholder-centric participation in large language models enhanced health systems. Npj Health Syst. 2, 22 (2025).","DOI":"10.1038\/s44401-025-00024-5"},{"key":"2026092205401039000_2026.09.16.26363176v1.47","unstructured":"Common Cancer Sites -Cancer Stat Facts. SEER https:\/\/seer.cancer.gov\/statfacts\/html\/common.html?utm_source=chatgpt.com."},{"key":"2026092205401039000_2026.09.16.26363176v1.48","unstructured":"Cervical cancer. https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cervical-cancer?utm_source=chatgpt.com."},{"key":"2026092205401039000_2026.09.16.26363176v1.49","unstructured":"Doshi, T . Gemini 3 Flash: frontier intelligence built for speed. Google https:\/\/blog.google\/products-and-platforms\/products\/gemini\/gemini-3-flash\/ (2025)."},{"key":"2026092205401039000_2026.09.16.26363176v1.50","doi-asserted-by":"publisher","DOI":"10.1200\/oa-25-00137"},{"key":"2026092205401039000_2026.09.16.26363176v1.51","doi-asserted-by":"publisher","DOI":"10.2471\/BLT.14.141390"},{"key":"2026092205401039000_2026.09.16.26363176v1.52","unstructured":"Introducing GPT-5.4. OpenAI https:\/\/openai.com\/index\/introducing-gpt-5-4\/."},{"key":"2026092205401039000_2026.09.16.26363176v1.53","unstructured":"Introducing GPT-5.2. OpenAI https:\/\/openai.com\/index\/introducing-gpt-5-2."},{"key":"2026092205401039000_2026.09.16.26363176v1.54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2601.03267"},{"key":"2026092205401039000_2026.09.16.26363176v1.55","unstructured":"Introducing Sonnet 4.6. https:\/\/www.anthropic.com\/news\/claude-sonnet-4-6."},{"key":"2026092205401039000_2026.09.16.26363176v1.56","unstructured":"Pichai, S . A new era of intelligence with Gemini 3. Google https:\/\/blog.google\/products-and-platforms\/products\/gemini\/gemini-3\/ (2025)."},{"key":"2026092205401039000_2026.09.16.26363176v1.57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.21783"},{"key":"2026092205401039000_2026.09.16.26363176v1.58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.09388"},{"key":"2026092205401039000_2026.09.16.26363176v1.59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.19786"},{"key":"2026092205401039000_2026.09.16.26363176v1.60","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"2026092205401039000_2026.09.16.26363176v1.61","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12671"},{"key":"2026092205401039000_2026.09.16.26363176v1.62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.05201"},{"key":"2026092205401039000_2026.09.16.26363176v1.63","unstructured":"aaditya\/Llama3-OpenBioLLM-70B \u00b7 Hugging Face. https:\/\/huggingface.co\/aaditya\/Llama3-OpenBioLLM-70B#."},{"key":"2026092205401039000_2026.09.16.26363176v1.64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.16079"},{"key":"2026092205401039000_2026.09.16.26363176v1.65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.06180"},{"key":"2026092205401039000_2026.09.16.26363176v1.66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.17887"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.16.26363176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T12:40:36Z","timestamp":1790080836000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.09.16.26363176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":66,"URL":"https:\/\/doi.org\/10.64898\/2026.09.16.26363176","relation":{},"subject":[],"published":{"date-parts":[[2026,9,17]]},"subtype":"preprint"}}