{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:59:10Z","timestamp":1787003950160,"version":"3.56.0"},"reference-count":10,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-02104-0","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T10:03:28Z","timestamp":1762941808000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Reasoning red teaming in healthcare not all paths to a desired outcome are desirable"],"prefix":"10.1038","volume":"8","author":[{"given":"Vera","family":"Sorin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panagiotis","family":"Korfiatis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Girish N.","family":"Nadkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eyal","family":"Klang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"2104_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01542-0","volume":"8","author":"CT Chang","year":"2025","unstructured":"Chang, C. T. et al. Red teaming ChatGPT in medicine to yield real-world insights on model behavior. npj Digit. Med. 8, 149 (2025).","journal-title":"npj Digit. Med."},{"key":"2104_CR2","doi-asserted-by":"publisher","unstructured":"Baker, B. et al. Monitoring reasoning models for misbehavior and the risks of promoting obfuscation. https:\/\/doi.org\/10.48550\/arXiv.2503.11926 (2025).","DOI":"10.48550\/arXiv.2503.11926"},{"key":"2104_CR3","doi-asserted-by":"publisher","unstructured":"Sorin, V. et al. Socio-demographic modifiers shape large language models\u2019 ethical decisions. J. Healthc. Inform. Res. https:\/\/doi.org\/10.1007\/s41666-025-00211- (2025).","DOI":"10.1007\/s41666-025-00211-"},{"key":"2104_CR4","unstructured":"OpenAI o1 System Card. https:\/\/openai.com\/index\/openai-o1-system-card\/."},{"key":"2104_CR5","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI, et al. DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.2501.12948 (2025).","DOI":"10.48550\/arXiv.2501.12948"},{"key":"2104_CR6","unstructured":"Google. Gemini 2.5 Pro. https:\/\/deepmind.google\/technologies\/gemini\/pro\/."},{"key":"2104_CR7","unstructured":"Anthropic. Claude 3.7 Sonnet. https:\/\/www.anthropic.com\/claude\/sonnet."},{"key":"2104_CR8","doi-asserted-by":"publisher","unstructured":"Muennighoff, N. et al. s1: Simple test-time scaling. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2501.19393 (2025).","DOI":"10.48550\/arXiv.2501.19393"},{"key":"2104_CR9","doi-asserted-by":"publisher","unstructured":"Snell C., Lee J., Xu K. & Kumar A. Scaling llm test-time compute optimally can be more effective than scaling model parameters. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2408.03314.","DOI":"10.48550\/arXiv.2408.03314"},{"key":"2104_CR10","doi-asserted-by":"publisher","first-page":"AIP2400559","DOI":"10.1056\/AIp2400559","volume":"1","author":"E Klang","year":"2024","unstructured":"Klang, E., Tessler, I., Freeman, R., Sorin, V. & Nadkarni, G. N. If Machines Exceed Us: Health Care at an Inflection Point. NEJM AI 1, AIP2400559 (2024).","journal-title":"NEJM AI"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02104-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02104-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02104-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T06:34:18Z","timestamp":1763015658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02104-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":10,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2104"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02104-0","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"2 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"V.S., P.K., and E.K. declare no financial or non-financial competing interests. G.N.N. serves as associate editor of this journal and had no role in the peer review or decision to publish this manuscript.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"649"}}