{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T18:10:03Z","timestamp":1748715003208,"version":"3.41.0"},"reference-count":60,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,10]]},"DOI":"10.1109\/dsaa.2015.7344805","type":"proceedings-article","created":{"date-parts":[[2015,12,8]],"date-time":"2015-12-08T22:18:36Z","timestamp":1449613116000},"page":"1-10","source":"Crossref","is-referenced-by-count":8,"title":["The NIST data science initiative"],"prefix":"10.1109","author":[{"given":"Bonnie J.","family":"Dorr","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Craig S.","family":"Greenberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Fontana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Przybocki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marion","family":"Le Bras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cathryn","family":"Ploehn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oleg","family":"Aulov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martial","family":"Michel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E. Jim","family":"Golden","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wo","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Fundamental methods of data science: Classification, regression and similarity matching","year":"2015","author":"jeevan","key":"ref39"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-31164-2","author":"christen","year":"2012","journal-title":"Data Matching Concepts and Techniques for Record Linkage Entity Resolution and Duplicate Detection"},{"journal-title":"Information Visualization in Data Mining and Knowledge Discovery","year":"2002","author":"fayyad","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/2945.981847"},{"journal-title":"Design for Information An Introduction to the Histories Theories and Best Practices behind Effective Information Visualizations","year":"2013","author":"meirelles","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.4018\/ijagr.2015040105"},{"journal-title":"Conceptual Modeling Foundations and Applications","year":"2009","author":"fagin","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2305334"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972818.4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972818.61"},{"key":"ref60","first-page":"178","article-title":"Advanced digital image preservation data management architecture","volume":"2009","year":"2009","journal-title":"Archiving Conference"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1057\/9781137379283","author":"finlay","year":"2014","journal-title":"Predictive Analytics Data Mining and Big Data Myths Misconceptions and Methods"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1084805.1084812"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref2","article-title":"DSAA trends and controversies","author":"cao","year":"2014","journal-title":"International Conference on Data Science and Advanced Analytics (DSAA)"},{"article-title":"The White House names Dr. D.J. Patil as the first U.S. chief data scientist","year":"2015","author":"smith","key":"ref1"},{"journal-title":"Information Dashboard Design Displaying Data for At-a- Glance Monitoring","year":"2013","author":"few","key":"ref20"},{"article-title":"The Geographer's craft project","year":"2015","author":"foote","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2200\/S00362ED1V01Y201105DTM016"},{"key":"ref24","article-title":"Bringing provenance to its full potential using causal reasoning","author":"meliou","year":"2011","journal-title":"Theory and Practice of Provenance"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04483-5_5"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1561\/1900000006","article-title":"Provenance in databases: Why, how, and where","volume":"1","author":"james","year":"2007","journal-title":"Foundations and Trends in Databases"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/3-540-44450-5_6","article-title":"Data provenance: Some basic issues","volume":"1974","author":"buneman","year":"2000","journal-title":"FST TCS 2000 Foundations of Software Technology and Theoretical Computer Science ser Lecture Notes in Computer Science"},{"journal-title":"Information Visualization Third Edition Perception for Design","year":"2012","author":"ware","key":"ref50"},{"journal-title":"The Craft of Information Visualization Readings and Reflections","year":"2003","author":"bederson","key":"ref51"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"202","DOI":"10.2352\/issn.2168-3204.2010.7.1.art00038","article-title":"Preliminary digital preservation interoperability framework (dpif) results","volume":"2010","author":"chang","year":"2010","journal-title":"Archiving Conference"},{"key":"ref58","article-title":"A novel metadata standard for multimedia preservation","author":"allasia","year":"2014","journal-title":"Proceedings of iPres"},{"year":"2014","key":"ref57","article-title":"Big data privacy workshop: Advancing the state of the art in technology and practice"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440"},{"key":"ref55","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"guyon","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref54","article-title":"Monitoring parallel programs for performance tuning in cluster environments","author":"de","year":"2001","journal-title":"Parallel Program Development for Cluster Computing Methodology Tools and Integrated Environments"},{"journal-title":"The Art of Computer Systems Performance Analysis Techniques for Experimental Design Measurement","year":"1991","author":"jain","key":"ref53"},{"journal-title":"Applied Security Visualization","year":"2009","author":"marty","key":"ref52"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1609\/aimag.v36i1.2565","article-title":"Exploiting semantics for big data integration","volume":"36","author":"knoblock","year":"2015","journal-title":"AI Magazine"},{"key":"ref11","article-title":"Entity type recognition for heterogeneous semantic graphs","author":"sleeman","year":"2013","journal-title":"2013 AAAI Fall Symposium Series"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7443.001.0001","author":"bakir","year":"2007","journal-title":"Predicting Structured Data (Neural Information Processing)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367564"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1609\/aimag.v36i1.2568","article-title":"Using semantics & statistics to turn data into knowledge","volume":"36","author":"pujara","year":"2015","journal-title":"Al Magazine"},{"article-title":"Big data and data science: Some hype but real opportunities","year":"2015","author":"franklin","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2164-15-S8-S1"},{"key":"ref16","article-title":"Understanding structural and semantic heterogeneity in the context of database schema integration","author":"george","year":"2005","journal-title":"Department of Computing"},{"article-title":"Stock prediction using twitter sentiment analysis","year":"2011","author":"mittal","key":"ref17"},{"article-title":"Visual media forensics: Knowing when seeing is believing","year":"2015","author":"doermann","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/scin.2015.187003022"},{"volume":"6","article-title":"NIST special publication 1500–6 information technology laboratory: DRAFT NIST big data interoperability framework","year":"0","key":"ref4"},{"article-title":"1st ISO\/IEC JTC 1 study group on big data meeting","year":"0","author":"chang","key":"ref3"},{"article-title":"Why only one of the 5 Vs of big data really matters","year":"2015","author":"marr","key":"ref6"},{"year":"2015","key":"ref5","article-title":"NIST big data public working group (NBD-PWG) request for public comment"},{"article-title":"3D data management: Controlling data volume, velocity, variety","year":"2001","author":"laney","key":"ref8"},{"key":"ref7","article-title":"Understanding big data","author":"mcnulty","year":"2014","journal-title":"Dataconomy"},{"key":"ref49","first-page":"81","article-title":"Assimilation of observations: An introduction","volume":"75","author":"talagrand","year":"1997","journal-title":"Journal-Meteorological Society of Japan Series"},{"journal-title":"IBM","article-title":"The four V's of big data","year":"2013","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.161"},{"article-title":"Deep learning","year":"2015","author":"bengio","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511802270"},{"year":"2014","key":"ref47","article-title":"Text retrieval conference"},{"key":"ref42","first-page":"238","article-title":"Discriminatory analysis. nonparametric discrimination: Consistency properties","author":"fix","year":"1957","journal-title":"International Statistical Review \/ Revue Internationale de Statistique"},{"key":"ref41","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning Ser ICML '01"},{"key":"ref44","first-page":"9","article-title":"A statistical method for integrated data cleaning and imputation","author":"mayfield","year":"2009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/1403796"}],"event":{"name":"2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)","start":{"date-parts":[[2015,10,19]]},"location":"Campus des Cordeliers, Paris, France","end":{"date-parts":[[2015,10,21]]}},"container-title":["2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7344768\/7344769\/07344805.pdf?arnumber=7344805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T17:57:14Z","timestamp":1748714234000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7344805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/dsaa.2015.7344805","relation":{},"subject":[],"published":{"date-parts":[[2015,10]]}}}