{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T08:46:07Z","timestamp":1776847567586,"version":"3.51.2"},"reference-count":13,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Data in Brief"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.dib.2026.112586","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T16:55:59Z","timestamp":1770828959000},"page":"112586","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ASQ-PHI: An adversarial synthetic data benchmark for clinical de-identification and search utility"],"prefix":"10.1016","volume":"65","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5436-7641","authenticated-orcid":false,"given":"James","family":"Weatherhead","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Golovko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4450-8143","authenticated-orcid":false,"given":"Peter","family":"McCaffrey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.dib.2026.112586_bib0001","unstructured":"Amazon Web Services. Amazon comprehend medical DetectPHI API reference. Available from: https:\/\/docs.aws.amazon.com\/comprehend-medical\/latest\/api\/API_DetectPHI.html"},{"key":"10.1016\/j.dib.2026.112586_bib0002","article-title":"ASQ-PHI: an adversarial synthetic benchmark for clinical de-identification and search utility","author":"Weatherhead","year":"2025","journal-title":"Mendel. Data"},{"key":"10.1016\/j.dib.2026.112586_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102845","article-title":"De-identification of clinical free text using natural language processing: a systematic review of current approaches","volume":"151","author":"Kova\u010devi\u0107","year":"2024","journal-title":"Artif. Intell. Med."},{"issue":"3","key":"10.1016\/j.dib.2026.112586_bib0004","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1093\/jamia\/ocaf005","article-title":"Development of secure infrastructure for advancing generative artificial intelligence research in healthcare at an academic medical center","volume":"32","author":"Ng","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.dib.2026.112586_bib0005","unstructured":"Brown T.B., Mann B., Ryder N., et al. Language models are few-shot learners. arXiv:2005.14165. 2020. https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"10.1016\/j.dib.2026.112586_bib0006","series-title":"GPT-4 Technical Report","year":"2023"},{"key":"10.1016\/j.dib.2026.112586_bib0007","unstructured":"U.S. Department of Health and Human Services, Office for Civil Rights. Guidance regarding methods for de-identification of protected health information in accordance with the HIPAA Privacy Rule. 2012. Available from: https:\/\/www.hhs.gov\/hipaa\/for-professionals\/privacy\/special-topics\/de-identification\/index.html"},{"key":"10.1016\/j.dib.2026.112586_bib0008","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/1472-6947-8-32","article-title":"Automated de-identification of free-text medical records","volume":"8","author":"Neamatullah","year":"2008","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.dib.2026.112586_bib0009","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data."},{"key":"10.1016\/j.dib.2026.112586_bib0010","doi-asserted-by":"crossref","first-page":"S4","DOI":"10.1016\/j.jbi.2017.06.011","article-title":"De-identification of psychiatric intake records: overview of 2016 CEGS N-GRID shared tasks track 1","volume":"75S","author":"Stubbs","year":"2017","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.dib.2026.112586_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2025.111796","article-title":"A novel dataset for Sundanese information retrieval","volume":"61","author":"Maesya","year":"2025","journal-title":"Data Brief."},{"issue":"3","key":"10.1016\/j.dib.2026.112586_bib0012","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooaf024","article-title":"Clinical document corpora - real ones, translated and synthetic substitutes, and assorted domain proxies: a survey of diversity in corpus design, with focus on German text data","volume":"8","author":"Hahn","year":"2025","journal-title":"JAMIA Open"},{"key":"10.1016\/j.dib.2026.112586_bib0013","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/s41746-023-00958-w","article-title":"A study of generative large language model for medical research and healthcare","volume":"6","author":"Peng","year":"2023","journal-title":"npj Digit. Med."}],"container-title":["Data in Brief"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352340926001393?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352340926001393?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:48:43Z","timestamp":1776844123000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2352340926001393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":13,"alternative-id":["S2352340926001393"],"URL":"https:\/\/doi.org\/10.1016\/j.dib.2026.112586","relation":{"is-supplemented-by":[{"id-type":"doi","id":"10.17632\/csz5dzp7nx.1","asserted-by":"subject"}]},"ISSN":["2352-3409"],"issn-type":[{"value":"2352-3409","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ASQ-PHI: An adversarial synthetic data benchmark for clinical de-identification and search utility","name":"articletitle","label":"Article Title"},{"value":"Data in Brief","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dib.2026.112586","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"112586"}}