{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T18:21:59Z","timestamp":1761157319413,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030964979"},{"type":"electronic","value":"9783030964986"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-96498-6_14","type":"book-chapter","created":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T11:03:04Z","timestamp":1646823784000},"page":"247-261","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Braid-DB: Toward AI-Driven Science with Machine Learning Provenance"],"prefix":"10.1007","author":[{"given":"Justin M.","family":"Wozniak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengchun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Vescovi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan","family":"Chard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Nicolae","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"Foster","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"unstructured":"NeXpy: A Python GUI to analyze NeXus data. http:\/\/nexpy.github.io\/nexpy","key":"14_CR1"},{"doi-asserted-by":"crossref","unstructured":"Abeykoon, V., Liu, Z., Kettimuthu, R., Fox, G., Foster, I.: Scientific image restoration anywhere. In: IEEE\/ACM 1st Annual Workshop on Large-scale Experiment-in-the-Loop Computing (XLOOP), pp. 8\u201313. IEEE (2019)","key":"14_CR2","DOI":"10.1109\/XLOOP49562.2019.00007"},{"doi-asserted-by":"crossref","unstructured":"Ananthakrishnan, R., et al.: Globus platform services for data publication. In: Proceedings of the Practice and Experience on Advanced Research Computing, pp. 1\u20137 (2018)","key":"14_CR3","DOI":"10.1145\/3219104.3219127"},{"doi-asserted-by":"crossref","unstructured":"Babuji, Y., et al.: Parsl: pervasive parallel programming in Python. In: Proceedings of the HPDC (2019)","key":"14_CR4","DOI":"10.1145\/3332186.3332231"},{"doi-asserted-by":"crossref","unstructured":"Baker, N.: Basic research needs workshop for scientific machine learning, core technologies for artificial intelligence (2019)","key":"14_CR5","DOI":"10.2172\/1478744"},{"issue":"8","key":"14_CR6","first-page":"2045","volume":"68","author":"B Blaiszik","year":"2016","unstructured":"Blaiszik, B., Chard, K., Pruyne, J., Ananthakrishnan, R., Tuecke, S., Foster, I.: The materials data facility: data services to advance materials science research. J. Mater. 68(8), 2045\u20132052 (2016)","journal-title":"J. Mater."},{"issue":"4","key":"14_CR7","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1557\/mrc.2019.118","volume":"9","author":"B Blaiszik","year":"2019","unstructured":"Blaiszik, B., et al.: A data ecosystem to support machine learning in materials science. MRS Commun. 9(4), 1125\u20131133 (2019). https:\/\/doi.org\/10.1557\/mrc.2019.118","journal-title":"MRS Commun."},{"issue":"1\u20132","key":"14_CR8","first-page":"71","volume":"40","author":"J Borycz","year":"2020","unstructured":"Borycz, J., Carroll, B.: Implementing FAIR data for people and machines: impacts and implications - results of a research data community workshop. Inf. Serv. Use 40(1\u20132), 71\u201385 (2020)","journal-title":"Inf. Serv. Use"},{"doi-asserted-by":"crossref","unstructured":"Chard, K., et al.: I\u2019ll take that to go: big data bags and minimal identifiers for exchange of large, complex datasets. In: International Conference on Big Data (Big Data), pp. 319\u2013328. IEEE (2016)","key":"14_CR9","DOI":"10.1109\/BigData.2016.7840618"},{"doi-asserted-by":"crossref","unstructured":"Fagnan, K., Nashed, Y., Perdue, G., Ratner, D., Shankar, A., Yoo, S.: Data and models: a framework for advancing AI in science. Report of the Office of Science Roundtable on Data for AI (2019). https:\/\/www.osti.gov\/servlets\/purl\/1579323","key":"14_CR10","DOI":"10.2172\/1579323"},{"key":"14_CR11","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1162\/dint_a_00025","volume":"2","author":"N Juty","year":"2020","unstructured":"Juty, N., et al.: Unique, persistent, resolvable: identifiers as the foundation of FAIR. Data Intell. 2, 30\u201339 (2020)","journal-title":"Data Intell."},{"doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, C., Cao, Q., Qi, C., Huang, J., Xie, C.: An experimental study on deep learning based on different hardware configurations. In: 2017 International Conference on Networking, Architecture, and Storage (NAS), pp. 1\u20136. IEEE (2017)","key":"14_CR12","DOI":"10.1109\/NAS.2017.8026843"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Bridge data center AI systems with edge computing for actionable information retrieval. arXiv preprint arXiv:2105.13967 (2021)","key":"14_CR13","DOI":"10.1109\/XLOOP54565.2021.00008"},{"unstructured":"Liu, Z., et al.: BraggNN: fast X-ray Bragg peak analysis using deep learning. arXiv preprint arXiv:2008.08198 (2020)","key":"14_CR14"},{"unstructured":"Machine Learning Schema Community Group: W3C machine learning schema (2017). https:\/\/github.com\/ML-Schema\/","key":"14_CR15"},{"issue":"4","key":"14_CR16","doi-asserted-by":"publisher","first-page":"e0213013","DOI":"10.1371\/journal.pone.0213013","volume":"14","author":"R Madduri","year":"2019","unstructured":"Madduri, R., et al.: Reproducible big data science: a case study in continuous fairness. PLoS ONE 14(4), e0213013 (2019)","journal-title":"PLoS ONE"},{"doi-asserted-by":"crossref","unstructured":"Moreau, L., et al.: The open provenance model core specification (v1.1). Future Gener. Comput. Syst. 27(6), 743\u2013756 (2011)","key":"14_CR17","DOI":"10.1016\/j.future.2010.07.005"},{"doi-asserted-by":"publisher","unstructured":"Polyzotis, N., Roy, S., Whang, S.E., Zinkevich, M.: Data management challenges in production machine learning. In: 2017 ACM International Conference on Management of Data, SIGMOD 2017, pp. 1723\u20131726. Association for Computing Machinery, New York (2017). https:\/\/doi.org\/10.1145\/3035918.3054782","key":"14_CR18","DOI":"10.1145\/3035918.3054782"},{"unstructured":"Schelter, S., B\u00f6se, J.H., Kirschnick, J., Klein, T., Seufert, S.: Automatically tracking metadata and provenance of machine learning experiments. In: Machine Learning Systems Workshop at NIPS (2017)","key":"14_CR19"},{"issue":"3","key":"14_CR20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/1084805.1084812","volume":"34","author":"YL Simmhan","year":"2005","unstructured":"Simmhan, Y.L., Plale, B., Gannon, D.: A survey of data provenance in e-science. ACM SIGMOD Rec. 34(3), 31\u201336 (2005)","journal-title":"ACM SIGMOD Rec."},{"doi-asserted-by":"publisher","unstructured":"Souza, R., et al.: Provenance data in the machine learning lifecycle in computational science and engineering. In: Workshop on Workflows in Support of Large-Scale Science at SC, pp. 1\u201310 (11 2019). https:\/\/doi.org\/10.1109\/WORKS49585.2019.00006","key":"14_CR21","DOI":"10.1109\/WORKS49585.2019.00006"},{"doi-asserted-by":"crossref","unstructured":"Stevens, R., Nichols, J., Yelick, K.: AI for Science Report on the Department of Energy (DOE) Town Halls on Artificial Intelligence (AI) for Science (2020)","key":"14_CR22","DOI":"10.2172\/1604756"},{"doi-asserted-by":"crossref","unstructured":"Tuecke, S., et al.: Globus auth: a research identity and access management platform. In: 12th International Conference on e-Science, pp. 203\u2013212. IEEE (2016)","key":"14_CR23","DOI":"10.1109\/eScience.2016.7870901"},{"doi-asserted-by":"publisher","unstructured":"Vartak, M., et al.: ModelDB: a system for machine learning model management. In: Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2016. Association for Computing Machinery, New York (2016). https:\/\/doi.org\/10.1145\/2939502.2939516","key":"14_CR24","DOI":"10.1145\/2939502.2939516"},{"doi-asserted-by":"publisher","unstructured":"Wilamowski, M., et al.: 2\u2019-O methylation of RNA cap in SARS-CoV-2 captured by serial crystallography. Proc. Natl. Acad. Sci. 118(21) (2021). https:\/\/doi.org\/10.1073\/pnas.2100170118. https:\/\/www.pnas.org\/content\/118\/21\/e2100170118","key":"14_CR25","DOI":"10.1073\/pnas.2100170118"},{"issue":"1","key":"14_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"MD Wilkinson","year":"2016","unstructured":"Wilkinson, M.D., et al.: The FAIR guiding principles for scientific data management and stewardship. Sci. Data 3(1), 1\u20139 (2016)","journal-title":"Sci. Data"},{"doi-asserted-by":"crossref","unstructured":"Wozniak, J.M., Armstrong, T.G., Wilde, M., Katz, D.S., Lusk, E., Foster, I.T.: Swift\/T: scalable data flow programming for distributed-memory task-parallel applications. In: Proceedings of the CCGrid (2013)","key":"14_CR27","DOI":"10.1145\/2442516.2442559"},{"doi-asserted-by":"publisher","unstructured":"Wozniak, J.M., et al.: CANDLE\/Supervisor: a workflow framework for machine learning applied to cancer research. BMC Bioinform. 19(18), 491 (2018). https:\/\/doi.org\/10.1186\/s12859-018-2508-4","key":"14_CR28","DOI":"10.1186\/s12859-018-2508-4"},{"unstructured":"Wozniak, J.M., et al.: Braid-DB GitHub repository. https:\/\/github.com\/ANL-Braid\/DB","key":"14_CR29"}],"container-title":["Communications in Computer and Information Science","Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-96498-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T09:06:43Z","timestamp":1657012003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-96498-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030964979","9783030964986"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-96498-6_14","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SMC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Smoky Mountains Computational Sciences and Engineering Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"smc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/smc2021.ornl.gov","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"88","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}