{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T03:21:03Z","timestamp":1772853663170,"version":"3.50.1"},"reference-count":81,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"crossref","award":["DE-SC0012704"],"award-info":[{"award-number":["DE-SC0012704"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users\/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the <jats:underline>Vi<\/jats:underline>rtual <jats:underline>S<\/jats:underline>cientific Compan<jats:underline>ion<\/jats:underline> by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an x-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instruments and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex\u2014a synthetic extension to the cognition of scientists\u2014may radically transform scientific practice and discovery.<\/jats:p>","DOI":"10.1088\/2632-2153\/add9e4","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T18:53:31Z","timestamp":1747421611000},"page":"025051","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0244-9517","authenticated-orcid":false,"given":"Shray","family":"Mathur","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7600-5428","authenticated-orcid":true,"given":"Noah van","family":"der Vleuten","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7745-2513","authenticated-orcid":true,"given":"Kevin G","family":"Yager","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5885-6317","authenticated-orcid":true,"given":"Esther H R","family":"Tsai","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"mlstadd9e4bib1","doi-asserted-by":"publisher","author":"Noack","year":"2024","DOI":"10.1201\/9781003359593"},{"key":"mlstadd9e4bib2","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1021\/acs.chemmater.2c03118","article-title":"The autonomous formulation laboratory: an open liquid handling platform for formulation discovery using x-ray and neutron scattering","volume":"35","author":"Beaucage","year":"2023","journal-title":"Chem. Mater."},{"key":"mlstadd9e4bib3","doi-asserted-by":"publisher","first-page":"eaax1566","DOI":"10.1126\/science.aax1566","article-title":"A robotic platform for flow synthesis of organic compounds informed by AI planning","volume":"365","author":"Coley","year":"2019","journal-title":"Science"},{"key":"mlstadd9e4bib4","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41586-023-06734-w","article-title":"An autonomous laboratory for the accelerated synthesis of novel materials","volume":"624","author":"Szymanski","year":"2023","journal-title":"Nature"},{"key":"mlstadd9e4bib5","doi-asserted-by":"publisher","first-page":"3046","DOI":"10.1021\/acs.chemmater.2c03593","article-title":"Self-driving laboratory for polymer electronics","volume":"35","author":"Vriza","year":"2023","journal-title":"Chem. Mater."},{"key":"mlstadd9e4bib6","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1038\/s41467-024-55655-3","article-title":"Autonomous platform for solution processing of electronic polymers","volume":"16","author":"Wang","year":"2025","journal-title":"Nat. Commun."},{"key":"mlstadd9e4bib7","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1039\/D4DD00277F","article-title":"Scientific exploration with expert knowledge (seek) in autonomous scanning probe microscopy with active learning","volume":"4","author":"Pratiush","year":"2025","journal-title":"Digit. Discovery"},{"key":"mlstadd9e4bib8","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6528\/acd25a","article-title":"Autonomous x-ray scattering","volume":"34","author":"Yager","year":"2023","journal-title":"Nanotechnology"},{"key":"mlstadd9e4bib9","doi-asserted-by":"publisher","first-page":"eadd3687","DOI":"10.1126\/sciadv.add3687","article-title":"Autonomous discovery of emergent morphologies in directed self-assembly of block copolymer blends","volume":"9","author":"Doerk","year":"2023","journal-title":"Sci. Adv."},{"key":"mlstadd9e4bib10","doi-asserted-by":"publisher","DOI":"10.1063\/5.0082956","article-title":"On-the-fly autonomous control of neutron diffraction via physics-informed bayesian active learning","volume":"9","author":"McDannald","year":"2022","journal-title":"Appl. Phys. Rev."},{"key":"mlstadd9e4bib11","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1107\/S1600577524008993","article-title":"A general Bayesian algorithm for the autonomous alignment of beamlines","volume":"31","author":"Morris","year":"2024","journal-title":"Synchrotron Radiat."},{"key":"mlstadd9e4bib12","doi-asserted-by":"publisher","author":"Willmott","year":"2019","DOI":"10.1002\/9781119280453"},{"key":"mlstadd9e4bib13","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1080\/08940886.2023.2207449","article-title":"x-ray scattering for soft matter research at nsls-ii","volume":"36","author":"Barbour","year":"2023","journal-title":"Synchrotron Radiat. News"},{"key":"mlstadd9e4bib14","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1038\/s41928-019-0309-z","article-title":"Three-dimensional imaging of integrated circuits with macro-to nanoscale zoom","volume":"2","author":"Holler","year":"2019","journal-title":"Nat. Electron."},{"key":"mlstadd9e4bib15","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1038\/s41586-024-07615-6","article-title":"High-performance 4-nm-resolution x-ray tomography using burst ptychography","volume":"632","author":"Aidukas","year":"2024","journal-title":"Nature"},{"key":"mlstadd9e4bib16","doi-asserted-by":"publisher","first-page":"eaba4171","DOI":"10.1126\/sciadv.aba4171","article-title":"Mapping the 3D orientation of nanocrystals and nanostructures in human bone: indications of novel structural features","volume":"6","author":"Gr\u00fcnewald","year":"2020","journal-title":"Sci. Adv."},{"key":"mlstadd9e4bib17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-05587-4","article-title":"Three-dimensional imaging of biological tissue by cryo x-ray ptychography","volume":"7","author":"Shahmoradian","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstadd9e4bib18","doi-asserted-by":"publisher","first-page":"34776","DOI":"10.1021\/acsnano.4c11725","article-title":"Structural, electrochemical and (de) lithiation mechanism investigation of cation-disordered rocksalt and spinel hybrid nanomaterials in lithium-ion batteries","volume":"18","author":"Kingan","year":"2024","journal-title":"ACS Nano"},{"key":"mlstadd9e4bib19","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1126\/science.abq6993","article-title":"Two-dimensional perovskite templates for durable, efficient formamidinium perovskite solar cells","volume":"384","author":"Sidhik","year":"2024","journal-title":"Science"},{"key":"mlstadd9e4bib20","doi-asserted-by":"publisher","first-page":"13123","DOI":"10.1021\/acs.chemrev.7b00007","article-title":"Synchrotron x-ray analytical techniques for studying materials electrochemistry in rechargeable batteries","volume":"117","author":"Lin","year":"2017","journal-title":"Chem. Rev."},{"key":"mlstadd9e4bib21","doi-asserted-by":"publisher","author":"Ghaoui","year":"2005","DOI":"10.5555\/2826087"},{"key":"mlstadd9e4bib22","doi-asserted-by":"crossref","DOI":"10.1101\/2024.11.11.623004","article-title":"The virtual lab: AI agents design new SARS-CoV-2 nanobodies with experimental validation","author":"Swanson","year":"2024"},{"key":"mlstadd9e4bib23","article-title":"From intention to implementation: automating biomedical research via LLMs","author":"Luo","year":"2024"},{"key":"mlstadd9e4bib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109713","article-title":"The application of large language models in medicine: A scoping review","volume":"27","author":"Meng","year":"2024","journal-title":"iScience"},{"key":"mlstadd9e4bib25","article-title":"Large language model-guided prediction toward quantum materials synthesis","author":"Okabe","year":"2024"},{"key":"mlstadd9e4bib26","doi-asserted-by":"publisher","first-page":"2110","DOI":"10.1021\/acs.jpclett.4c03137","article-title":"DiffractGPT: Atomic structure determination from x-ray diffraction patterns using a generative pretrained transformer","volume":"16","author":"Choudhary","year":"2025","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstadd9e4bib27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41586-025-08628-5","article-title":"A generative model for inorganic materials design","volume":"639","author":"Zeni","year":"2025","journal-title":"Nature"},{"key":"mlstadd9e4bib28","article-title":"LLMatDesign: autonomous materials discovery with large language models","author":"Jia","year":"2024"},{"key":"mlstadd9e4bib29","doi-asserted-by":"publisher","first-page":"6909","DOI":"10.1021\/acs.jpclett.4c01126","article-title":"AtomGPT: atomistic generative pretrained transformer for forward and inverse materials design","volume":"15","author":"Choudhary","year":"2024","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstadd9e4bib30","article-title":"Rapid and automated alloy design with graph neural network-powered llm-driven multi-agent systems","author":"Ghafarollahi","year":"2024"},{"key":"mlstadd9e4bib31","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1038\/s42256-023-00788-1","article-title":"Leveraging large language models for predictive chemistry","volume":"6","author":"Maik Jablonka","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"mlstadd9e4bib32","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1038\/s41524-024-01449-6","article-title":"Large language models design sequence-defined macromolecules via evolutionary optimization","volume":"10","author":"Reinhart","year":"2024","journal-title":"npj Comput. Mater."},{"key":"mlstadd9e4bib33","article-title":"Virtual scientific companion for synchrotron beamlines: a prototype","author":"Potemkin","year":"2023"},{"key":"mlstadd9e4bib34","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1038\/s41524-024-01423-2","article-title":"Opportunities for retrieval and tool augmented large language models in scientific facilities","volume":"10","author":"Prince","year":"2024","journal-title":"npj Comput. Mater."},{"key":"mlstadd9e4bib35","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4993185","article-title":"Esac (eq-sans assisting chatbot): application of large language models and retrieval-augmented generation for enhanced user experience at eq-sans","author":"Do","year":"2024"},{"key":"mlstadd9e4bib36","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1088\/2632-2153\/ad52e9","article-title":"Synergizing human expertise and AI efficiency with language model for microscopy operation and automated experiment design","volume":"5","author":"Liu","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstadd9e4bib37","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1088\/2632-2153\/ad7228","article-title":"Accelerating scientific discovery with generative knowledge extraction, graph-based representation and multimodal intelligent graph reasoning","volume":"5","author":"Buehler","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstadd9e4bib38","article-title":"Aviary: training language agents on challenging scientific tasks","author":"Narayanan","year":"2024"},{"key":"mlstadd9e4bib39","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1039\/D2DD00087C","article-title":"Assessment of chemistry knowledge in large language models that generate code","volume":"2","author":"White","year":"2023","journal-title":"Digit. Discovery"},{"key":"mlstadd9e4bib40","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1038\/s42256-024-00832-8","article-title":"Augmenting large language models with chemistry tools","volume":"6","author":"Bran","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"mlstadd9e4bib41","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1039\/d4sc03921a","article-title":"A review of large language models and autonomous agents in chemistry","volume":"16","author":"Caldas Ramos","year":"2025","journal-title":"Chem. Sci."},{"key":"mlstadd9e4bib42","article-title":"Paperqa: retrieval-augmented generative agent for scientific research","author":"L\u00e1la","year":"2023"},{"key":"mlstadd9e4bib43","doi-asserted-by":"publisher","first-page":"1850","DOI":"10.1039\/D3DD00112A","article-title":"Domain-specific chatbots for science using embeddings","volume":"2","author":"Yager","year":"2023","journal-title":"Digit. Discovery"},{"key":"mlstadd9e4bib44","article-title":"Language agents achieve superhuman synthesis of scientific knowledge","author":"Skarlinski","year":"2024"},{"key":"mlstadd9e4bib45","doi-asserted-by":"publisher","first-page":"18048","DOI":"10.1021\/jacs.3c05819","article-title":"Chatgpt chemistry assistant for text mining and the prediction of mof synthesis","volume":"145","author":"Zheng","year":"2023","journal-title":"J. Am. Chem. Soc."},{"key":"mlstadd9e4bib46","article-title":"LLaMP: large language model made powerful for high-fidelity materials knowledge retrieval and distillation","author":"Chiang","year":"2024"},{"key":"mlstadd9e4bib47","article-title":"Litllm: a toolkit for scientific literature review","author":"Agarwal","year":"2024"},{"key":"mlstadd9e4bib48","article-title":"Ai-driven review systems: evaluating llms in scalable and bias-aware academic reviews","author":"Tyser","year":"2024"},{"key":"mlstadd9e4bib49","article-title":"Generation and human-expert evaluation of interesting research ideas using knowledge graphs and large language models","author":"Gu","year":"2024"},{"key":"mlstadd9e4bib50","doi-asserted-by":"publisher","first-page":"74","DOI":"10.18653\/v1\/2024.langmol-1.9","article-title":"Knowledge graph extraction from total synthesis documents","author":"Bran","year":"2024"},{"key":"mlstadd9e4bib51","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.nlp4science-1.10","article-title":"Hypothesis generation with large language models","author":"Zhou","year":"2024"},{"key":"mlstadd9e4bib52","article-title":"Large language models as biomedical hypothesis generators: a comprehensive evaluation","author":"Qi","year":"2024"},{"key":"mlstadd9e4bib53","article-title":"Data interpreter: an llm agent for data science","author":"Hong"},{"key":"mlstadd9e4bib54","article-title":"Scienceagentbench: toward rigorous assessment of language agents for data-driven scientific discovery","author":"Chen","year":"2024"},{"key":"mlstadd9e4bib55","article-title":"Agent laboratory: using llm agents as research assistants","author":"Schmidgall","year":"2025"},{"key":"mlstadd9e4bib56","article-title":"Dolphin: closed-loop open-ended auto-research through thinking, practice, and feedback","author":"Yuan","year":"2025"},{"key":"mlstadd9e4bib57","article-title":"Curie: toward rigorous and automated scientific experimentation with AI agents","author":"Tser Jern Kon","year":"2025"},{"key":"mlstadd9e4bib58","doi-asserted-by":"publisher","DOI":"10.1016\/j.matt.2024.10.015","article-title":"Organa: a robotic assistant for automated chemistry experimentation and characterization","volume":"8","author":"Darvish","year":"2025","journal-title":"Matter"},{"key":"mlstadd9e4bib59","doi-asserted-by":"publisher","first-page":"20009","DOI":"10.1021\/jacs.4c03849","article-title":"Accelerating computational materials discovery with machine learning and cloud high-performance computing: from large-scale screening to experimental validation","volume":"146","author":"Chen","year":"2024","journal-title":"J. Am. Chem. Soc."},{"key":"mlstadd9e4bib60","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","article-title":"Autonomous chemical research with large language models","volume":"624","author":"Boiko","year":"2023","journal-title":"Nature"},{"key":"mlstadd9e4bib61","article-title":"Specifications: the missing link to making the development of llm systems an engineering discipline","author":"Stoica","year":"2024"},{"key":"mlstadd9e4bib62","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/N19-1423","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"mlstadd9e4bib63","doi-asserted-by":"publisher","first-page":"1933","DOI":"10.1039\/D4DD00178H","article-title":"Towards a science exocortex","volume":"3","author":"Yager","year":"2024","journal-title":"Digit. Discovery"},{"key":"mlstadd9e4bib64","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1080\/08940886.2019.1608121","article-title":"Bluesky\u2019s ahead: a multi-facility collaboration for an a la Carte software project for data acquisition and management","volume":"32","author":"Allan","year":"2019","journal-title":"Synchrotron Radiat. News"},{"key":"mlstadd9e4bib65","author":"SciAnalysis","year":"2024"},{"key":"mlstadd9e4bib66","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2024"},{"key":"mlstadd9e4bib67","article-title":"The claude 3 model family: opus, sonnet, haiku","author":"AI Anthropic","year":"2024"},{"key":"mlstadd9e4bib68","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"mlstadd9e4bib69","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"mlstadd9e4bib70","article-title":"Qwen2.5-Coder technical report","author":"Hui","year":"2024"},{"key":"mlstadd9e4bib71","first-page":"1877","article-title":"Language models are few-shot learners","volume":"vol 33","author":"Brown","year":"2020"},{"key":"mlstadd9e4bib72","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"mlstadd9e4bib73","author":"Tsuchinoko","year":"2024"},{"key":"mlstadd9e4bib74","article-title":"Whisper: automatic speech recognition","author":"OpenAI","year":"2022"},{"key":"mlstadd9e4bib75","author":"Xi-cam","year":"2024"},{"key":"mlstadd9e4bib76","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1107\/S1600577518005787","article-title":"Xi-cam: a versatile interface for data visualization and analysis","volume":"25","author":"Pandolfi","year":"2018","journal-title":"J. Synchrotron Radiat."},{"key":"mlstadd9e4bib77","article-title":"Codebleu: a method for automatic evaluation of code synthesis","author":"Ren","year":"2020"},{"key":"mlstadd9e4bib78","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"mlstadd9e4bib79","article-title":"Rlaif vs. RLHF: scaling reinforcement learning from human feedback with AI feedback","author":"Lee","year":"2024"},{"key":"mlstadd9e4bib80","first-page":"10935","article-title":"RRHF: rank responses to align language models with human feedback","volume":"vol 36","author":"Yuan","year":"2023"},{"key":"mlstadd9e4bib81","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/978-3-031-38165-2_77","article-title":"An operating system for cloud manufacturing (OSCM)","author":"Toro Santamaira","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T08:15:08Z","timestamp":1752135308000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add9e4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":81,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6,4]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/add9e4","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"assertion":[{"value":"VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-01-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-16","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-06-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}