{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:13:06Z","timestamp":1785517986002,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100006132","name":"U.S. Department of Energy Office of Science","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,11]]},"DOI":"10.1145\/3828820.3828827","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:20:16Z","timestamp":1785507616000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SetGo: Metadata Readiness for Scientific AI Datasets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1443-7479","authenticated-orcid":false,"given":"Sean R.","family":"Wilkinson","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6761-7326","authenticated-orcid":false,"given":"Polina","family":"Shpilker","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3639-3956","authenticated-orcid":false,"given":"Wesley","family":"Brewer","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2026. WebMCP is available for early preview. https:\/\/developer.chrome.com\/blog\/webmcp-epp. Accessed: 2026-05-07."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Gustaf Ahdritz Nazim Bouatta Christina Floristean Sachin Kadyan Qinghui Xia et\u00a0al. 2024. OpenFold: Retraining AlphaFold2 Yields New Insights into Its Learning Mechanisms and Capacity for Generalization. Nature Methods 21 (2024) 1514\u20131524. 10.1038\/s41592-024-02272-z","DOI":"10.1038\/s41592-024-02272-z"},{"key":"e_1_3_3_2_4_2","unstructured":"Anthropic. 2025. Claude Code. https:\/\/github.com\/anthropics\/claude-code. Accessed: 2026-05-06."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Wesley Brewer Patrick Widener Valentine Anantharaj Feiyi Wang Tom Beck Arjun Shankar and Sarp Oral. 2026. Data Readiness Pipeline Patterns for Scientific AI at Scale: Insights from Climate Fusion Life Sciences and Materials. AI Magazine 47 1 (2026). 10.1002\/aaai.70056","DOI":"10.1002\/aaai.70056"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Timothy Clark Harry Caufield Jillian\u00a0A. Parker Sadnan Al\u00a0Manir Edilberto Amorim James Eddy et\u00a0al. 2024. AI-Readiness for Biomedical Data: Bridge2AI Recommendations. bioRxiv (2024). 10.1101\/2024.10.23.619844","DOI":"10.1101\/2024.10.23.619844"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Anusuriya Devaraju and Robert Huber. 2021. An Automated Solution for Measuring the Progress toward FAIR Research Data. Patterns 2 11 (2021). 10.1016\/j.patter.2021.100370","DOI":"10.1016\/j.patter.2021.100370"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Ove Johan\u00a0Ragnar Gustafsson Sean\u00a0R. Wilkinson Finn Bacall Stian Soiland-Reyes Simone Leo Luca Pireddu Stuart Owen Nick Juty Jos\u00e9M. Fern\u00e1ndez Tom Brown Herv\u00e9 M\u00e9nager Bj\u00f6rn Gr\u00fcning Salvador Capella-Gutierrez Frederik Coppens and Carole Goble. 2025. WorkflowHub: a registry for computational workflows. Scientific Data 12 1 (May 2025). 10.1038\/s41597-025-04786-3","DOI":"10.1038\/s41597-025-04786-3"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Yaroslav\u00a0O. Halchenko Kyle Meyer Benjamin Poldrack Debanjum\u00a0Singh Solanky Adina\u00a0S. Wagner Jason Gors Dave MacFarlane Dorian Pustina Vanessa Sochat Satrajit\u00a0S. Ghosh et\u00a0al. 2021. DataLad: distributed system for joint management of code data and their relationship. Journal of Open Source Software 6 63 (2021) 3262. 10.21105\/joss.03262","DOI":"10.21105\/joss.03262"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Kaveen Hiniduma Suren Byna and Jean\u00a0Luca Bez. 2025. Data Readiness for AI: A 360-Degree Survey. Comput. Surveys (2025). 10.1145\/3722214","DOI":"10.1145\/3722214"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676288.3676296"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Neil\u00a0D. Lawrence. 2017. Data Readiness Levels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1705.02245 (2017). 10.48550\/arXiv.1705.02245","DOI":"10.48550\/arXiv.1705.02245"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Massimiliano Lupo\u00a0Pasini Jong\u00a0Youl Choi Kshitij Mehta Pei Zhang David Rogers et\u00a0al. 2025. Scalable Training of Trustworthy and Energy-Efficient Predictive Graph Foundation Models for Atomistic Materials Modeling: A Case Study with HydraGNN. The Journal of Supercomputing (2025). 10.1007\/s11227-025-07029-9","DOI":"10.1007\/s11227-025-07029-9"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Tung Nguyen Johannes Brandstetter Ashish Kapoor Jayesh\u00a0K. Gupta and Aditya Grover. 2023. ClimaX: A Foundation Model for Weather and Climate. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.10343 (2023). 10.48550\/arXiv.2301.10343","DOI":"10.48550\/arXiv.2301.10343"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/e-Science58273.2023.10254822"},{"key":"e_1_3_3_2_16_2","unstructured":"United States Department of Energy. 2025. Genesis Mission. https:\/\/genesis.energy.gov\/. Accessed: 2026-06-18."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Mark\u00a0D. Wilkinson Michel Dumontier IJsbrand\u00a0Jan Aalbersberg Gabrielle Appleton Myles Axton Arie Baak Niklas Blomberg Jan-Willem Boiten Luiz\u00a0Bonino da Silva Santos Philip\u00a0E. Bourne et\u00a0al. 2016. The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data 3 (2016) 160018. 10.1038\/sdata.2016.18","DOI":"10.1038\/sdata.2016.18"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Sean\u00a0R. Wilkinson Meznah Aloqalaa Khalid Belhajjame Michael\u00a0R. Crusoe Bruno de Paula\u00a0Kinoshita Luiz Gadelha Daniel Garijo Ove Johan\u00a0Ragnar Gustafsson Nick Juty Sehrish Kanwal Farah\u00a0Zaib Khan Johannes K\u00f6ster Karsten Peters-von Gehlen Line Pouchard Randy\u00a0K. Rannow Stian Soiland-Reyes Nicola Soranzo Shoaib Sufi Ziheng Sun Baiba Vilne Merridee\u00a0A. Wouters Denis Yuen and Carole Goble. 2025. Applying the FAIR Principles to computational workflows. Scientific Data 12 (2025) 328. 10.1038\/s41597-025-04451-9","DOI":"10.1038\/s41597-025-04451-9"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Sean\u00a0R. Wilkinson Valentine\u00a0G. Anantharaj Jong\u00a0Youl Choi Ketan Maheshwari Marshall McDonnell Massimiliano Lupo\u00a0Pasini Polina Shpilker Renan Souza Patrick Widener Sarp Oral and Wesley Brewer. 2026. Automated Data Readiness for Scientific AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2607.02771 (2026). 10.48550\/arXiv.2607.02771","DOI":"10.48550\/arXiv.2607.02771"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/eScience55777.2022.00090"},{"key":"e_1_3_3_2_21_2","unstructured":"Matei Zaharia Andrew Chen Aaron Davidson Ali Ghodsi Sue\u00a0Ann Hong Andy Konwinski Siddharth Murching Tomas Nykodym Paul Ogilvie Mani Parkhe et\u00a0al. 2018. Accelerating the Machine Learning Lifecycle with MLflow. IEEE Data Engineering Bulletin 41 4 (2018) 39\u201345."}],"event":{"name":"SSDBM 2026: The International Conference on Scalable Scientific Data Management 2026","location":"San Diego , CA , USA","acronym":"SSDBM 2026"},"container-title":["Proceedings of the 38th International Conference on Scalable Scientific Data Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3828820.3828827","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3828820.3828827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T16:30:52Z","timestamp":1785515452000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3828820.3828827"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":20,"alternative-id":["10.1145\/3828820.3828827","10.1145\/3828820"],"URL":"https:\/\/doi.org\/10.1145\/3828820.3828827","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}