{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:45:45Z","timestamp":1789159545797,"version":"build-2803163510"},"reference-count":22,"publisher":"International Union of Crystallography (IUCr)","issue":"4","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100006192","name":"Office of Science, Advanced Scientific Computing Research","doi-asserted-by":"publisher","award":["ERKJ388"],"award-info":[{"award-number":["ERKJ388"]}],"id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006228","name":"Oak Ridge National Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006228","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["iucr.org","wiley.com","iucrj.org"],"crossmark-restriction":true},"short-container-title":["J Appl Crystallogr","J Appl Cryst"],"accepted":{"date-parts":[[2026,4,28]]},"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:p>\n                    Large-scale facilities increasingly face analysis and reporting latency as a limiting step in scientific throughput, particularly for structural studies that require iterative reduction, integration, refinement and validation. To improve the time to result and analysis efficiency, NeuDiff Agent is introduced as a governed, tool-using AI workflow for TOPAZ at the Spallation Neutron Source. NeuDiff Agent takes instrument data through reduction, integration, refinement and validation to a validated crystal structure and a publication-ready CIF. NeuDiff Agent coordinates established crystallographic tools under explicit governance by restricting actions to allowlisted tools, enforcing fail-closed verification gates at key workflow boundaries, and capturing complete provenance for inspection, auditing and controlled replay. The present benchmark is limited to structural crystallography for periodic structures; magnetic structure analysis and incommensurate or superspace refinement are outside the scope of the current workflow. Performance is assessed using a fixed prompt protocol and repeated end-to-end runs with two large language model backends, with user and machine time partitioned and intervention burden and recovery behaviors quantified under gating. In a reference-case benchmark, NeuDiff Agent reduces wall time from 435\u2005min (manual) to 86.5\u2005\u00b1\u20054.7 to 94.4\u2005\u00b1\u20053.5\u2005min (4.6\u20135.0\u00d7 faster) while producing a validated CIF with no\n                    <jats:italic>checkCIF<\/jats:italic>\n                    level A or B alerts. These results establish a practical route to deploy agentic AI in facility crystallography while preserving traceability and publication-facing validation requirements.\n                  <\/jats:p>","DOI":"10.1107\/s1600576726004474","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:01:06Z","timestamp":1780920066000},"page":"1102-1111","update-policy":"https:\/\/doi.org\/10.1107\/cm_01","source":"Crossref","is-referenced-by-count":1,"title":["NeuDiff Agent: a governed AI workflow for single-crystal neutron crystallography"],"prefix":"10.1107","volume":"59","author":[{"given":"Zhongcan","family":"Xiao","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01qz5mb56","id-type":"ROR","asserted-by":"publisher"}],"department":["Neutron Scattering Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leyi","family":"Zhang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01qz5mb56","id-type":"ROR","asserted-by":"publisher"}],"department":["Neutron Scattering Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guannan","family":"Zhang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01qz5mb56","id-type":"ROR","asserted-by":"publisher"}],"department":["Computer Science and Mathematics Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7143-8112","authenticated-orcid":true,"given":"Xiaoping","family":"Wang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/01qz5mb56","id-type":"ROR","asserted-by":"publisher"}],"department":["Neutron Scattering Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"329","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"oz5013_bb20","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.nima.2014.07.029","volume":"764","author":"Arnold","year":"2014","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"oz5013_bb1","doi-asserted-by":"crossref","first-page":"3781","DOI":"10.1016\/j.procs.2024.09.178","volume":"246","author":"Arslan","year":"2024","journal-title":"Procedia Comput. Sci."},{"key":"oz5013_bb2","doi-asserted-by":"crossref","first-page":"092802","DOI":"10.1063\/1.5030896","volume":"89","author":"Coates","year":"2018","journal-title":"Rev. Sci. Instrum."},{"key":"oz5013_bb3","doi-asserted-by":"crossref","first-page":"092803","DOI":"10.1063\/1.5031798","volume":"89","author":"Fancher","year":"2018","journal-title":"Rev. Sci. Instrum."},{"key":"oz5013_bb4","doi-asserted-by":"crossref","unstructured":"Godoy, W. F., Peterson, P. F., Hahn, S. E. & Billings, J. J. (2020). 8th IEEE International Conference on Big Data (Big Data), pp. 2674-2680. IEEE.","DOI":"10.1109\/BigData50022.2020.9377836"},{"key":"oz5013_bb5","first-page":"250308979","author":"Gridach","year":"2025","journal-title":"arXiv"},{"key":"oz5013_bb6","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1107\/S2053273314015599","volume":"70","author":"J\u00f8rgensen","year":"2014","journal-title":"Acta Cryst. A"},{"key":"oz5013_bb7","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/MCG.2025.3540264","volume":"45","author":"Jourdain","year":"2025","journal-title":"IEEE Comput. Graph. Appl."},{"key":"oz5013_bb8","unstructured":"Kinhult, P., Ringvik, M., S\u00f6derberg, D. & Paulsson, K. M. (2025). Bottlenecks That Delay the Benefits of Large-Scale Research Infrastructure. Report, Swedish Research Council."},{"key":"oz5013_bb9","first-page":"240806292","author":"Lu","year":"2024","journal-title":"arXiv"},{"key":"oz5013_bb10","first-page":"240206196","author":"Minaee","year":"2024","journal-title":"arXiv"},{"key":"oz5013_bb11","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1107\/S0021889811038970","volume":"44","author":"Momma","year":"2011","journal-title":"J. Appl. Cryst."},{"key":"oz5013_bb12","doi-asserted-by":"crossref","first-page":"e2401238121","DOI":"10.1073\/pnas.2401238121","volume":"122","author":"Musslick","year":"2025","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"oz5013_bb13","doi-asserted-by":"crossref","first-page":"7443","DOI":"10.1109\/ACCESS.2026.3652325","volume":"14","author":"Otoum","year":"2026","journal-title":"IEEE Access"},{"key":"oz5013_bb14","first-page":"250324047","author":"Ren","year":"2025","journal-title":"arXiv"},{"key":"oz5013_bb21","first-page":"333","volume":"3","author":"Robertson","year":"2009","journal-title":"Found. Trends Inf. Retrieval"},{"key":"oz5013_bb15","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1107\/S1600576714006372","volume":"47","author":"Schultz","year":"2014","journal-title":"J. Appl. Cryst."},{"key":"oz5013_bb16","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1107\/S2053229614024218","volume":"71","author":"Sheldrick","year":"2015","journal-title":"Acta Cryst. C"},{"key":"oz5013_bb17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1107\/S2056989019016244","volume":"76","author":"Spek","year":"2020","journal-title":"Acta Cryst. E"},{"key":"oz5013_bb22","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N. & Zhou, M. (2020). MiniLM: Deep Self-attention Distillation for Task-Agnostic Compression of Pre-trained Transformers, Advances in Neural Information Processing Systems, Vol. 33, pp. 5776-5788. Curran Associates."},{"key":"oz5013_bb18","doi-asserted-by":"crossref","first-page":"43550","DOI":"10.1021\/jacs.5c12764","volume":"147","author":"Wang","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"oz5013_bb19","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1107\/S0021889811007102","volume":"44","author":"Zikovsky","year":"2011","journal-title":"J. Appl. Cryst."}],"container-title":["Journal of Applied Crystallography"],"original-title":[],"link":[{"URL":"https:\/\/journals.iucr.org\/j\/issues\/2026\/04\/00\/oz5013\/oz5013.pdf","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.iucr.org\/j\/issues\/2026\/04\/00\/oz5013\/oz5013.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T14:21:49Z","timestamp":1786026109000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.iucr.org\/paper?S1600576726004474"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,24]]},"references-count":22,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["S1600576726004474"],"URL":"https:\/\/doi.org\/10.1107\/s1600576726004474","relation":{"is-supplemented-by":[{"id-type":"doi","id":"10.1107\/S1600576726004474\/oz5013sup1.pdf","asserted-by":"subject"}]},"ISSN":["1600-5767"],"issn-type":[{"value":"1600-5767","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,24]]},"assertion":[{"value":"Journal of Applied Crystallography","order":0,"name":"journal","label":"Publication","explanation":{"URL":"https:\/\/journals.iucr.org\/j"},"group":{"name":"general","label":"General"}},{"value":"research papers","order":1,"name":"content_type","label":"Content type","explanation":{"URL":"https:\/\/journals.iucr.org\/j\/services\/notesforauthors.html"},"group":{"name":"general","label":"General"}},{"value":"Available","URL":"https:\/\/scripts.iucr.org\/cgi-bin\/citedin?oz5013","order":2,"name":"article_metrics","label":"Article metrics","group":{"name":"general","label":"General"}},{"value":"Yes","order":0,"name":"peer_reviewed","label":"Peer reviewed","group":{"name":"peer_review","label":"Peer review"}},{"value":"Single blind","order":1,"name":"review_process","label":"Review process","group":{"name":"peer_review","label":"Peer review"}},{"value":"2 February 2026","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication history"}},{"value":"28 April 2026","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication history"}},{"value":"24 June 2026","order":2,"name":"published_online","label":"Published online","group":{"name":"publication_history","label":"Publication history"}},{"value":"This article has supporting information","name":"supplementary_materials","label":"Supplementary materials","explanation":{"URL":"https:\/\/scripts.iucr.org\/cgi-bin\/sendsup?oz5013"}},{"value":"\u00a9 2026 Zhongcan Xiao\n                      et al.","order":0,"name":"copyright","label":"Copyright","explanation":{"URL":"https:\/\/journals.iucr.org\/services\/copyrightpolicy.html"},"group":{"name":"copyright_and_licencing","label":"Copyright and licencing"}},{"value":"Creative Commons Attribution (CC-BY)","order":1,"name":"license","label":"Licence","explanation":{"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},"group":{"name":"copyright_and_licencing","label":"Copyright and licencing"}}]}}