{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T06:06:23Z","timestamp":1775369183903,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,22]],"date-time":"2018-07-22T00:00:00Z","timestamp":1532217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Illinois - Indiana Sea Grant","award":["#DW92329201"],"award-info":[{"award-number":["#DW92329201"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#BCS-0941268, #EAR- 331906, #ACI-1261582, #ACI-1443013, #OCI-0940824, #OCI-0525308, #OCI-1053575"],"award-info":[{"award-number":["#BCS-0941268, #EAR- 331906, #ACI-1261582, #ACI-1443013, #OCI-0940824, #OCI-0525308, #OCI-1053575"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000098","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["#1P01AI089556-01A1"],"award-info":[{"award-number":["#1P01AI089556-01A1"]}],"id":[{"id":"10.13039\/100000098","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006133","name":"Advanced Research Projects Agency - Energy","doi-asserted-by":"publisher","award":["#DE-AR0000594"],"award-info":[{"award-number":["#DE-AR0000594"]}],"id":[{"id":"10.13039\/100006133","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Commission","award":["#RI-261600"],"award-info":[{"award-number":["#RI-261600"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,22]]},"DOI":"10.1145\/3219104.3219159","type":"proceedings-article","created":{"date-parts":[[2018,7,12]],"date-time":"2018-07-12T17:46:44Z","timestamp":1531417604000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["Clowder"],"prefix":"10.1145","author":[{"given":"Luigi","family":"Marini","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Indira","family":"Gutierrez-Polo","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Rob","family":"Kooper","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Sandeep Puthanveetil","family":"Satheesan","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Maxwell","family":"Burnette","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Jong","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Todd","family":"Nicholson","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Coordinated Science Laboratory, Urbana, Illinois"}]},{"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]},{"given":"Kenton","family":"McHenry","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications, Urbana, Illinois"}]}],"member":"320","published-online":{"date-parts":[[2018,7,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The BagIt File Packaging Format. (2018). Retrieved","year":"2018","unstructured":"2018. The BagIt File Packaging Format. (2018). Retrieved June 1, 2018 from https:\/\/tools.ietf.org\/html\/draft-kunze-bagit-14 2018. The BagIt File Packaging Format. (2018). Retrieved June 1, 2018 from https:\/\/tools.ietf.org\/html\/draft-kunze-bagit-14"},{"key":"e_1_3_2_1_2_1","volume-title":"IML-CZO Data Management - Critical Zone Observatory Network for Intensively Managed Landscapes. (2018). Retrieved","year":"2018","unstructured":"2018. IML-CZO Data Management - Critical Zone Observatory Network for Intensively Managed Landscapes. (2018). Retrieved June 1, 2018 from http:\/\/imlczo.ncsa.illinois.edu\/ 2018. IML-CZO Data Management - Critical Zone Observatory Network for Intensively Managed Landscapes. (2018). Retrieved June 1, 2018 from http:\/\/imlczo.ncsa.illinois.edu\/"},{"key":"e_1_3_2_1_3_1","volume-title":"JSON-LD - JSON for Linking Data. (2018). Retrieved","year":"2018","unstructured":"2018. JSON-LD - JSON for Linking Data. (2018). Retrieved June 1, 2018 from https:\/\/json-ld.org\/ 2018. JSON-LD - JSON for Linking Data. (2018). Retrieved June 1, 2018 from https:\/\/json-ld.org\/"},{"key":"e_1_3_2_1_4_1","volume-title":"ORE Specifications and User Guides - Table of Contents. (2018). Retrieved","year":"2018","unstructured":"2018. ORE Specifications and User Guides - Table of Contents. (2018). Retrieved June 1, 2018 from http:\/\/www.openarchives.org\/ore\/1.0\/toc 2018. ORE Specifications and User Guides - Table of Contents. (2018). Retrieved June 1, 2018 from http:\/\/www.openarchives.org\/ore\/1.0\/toc"},{"key":"e_1_3_2_1_5_1","volume-title":"PROV Model Primer. (2018). Retrieved","year":"2018","unstructured":"2018. PROV Model Primer. (2018). Retrieved June 1, 2018 from https:\/\/www.w3.org\/TR\/2013\/NOTE-prov-primer-20130430\/#agents-and-responsibility 2018. PROV Model Primer. (2018). Retrieved June 1, 2018 from https:\/\/www.w3.org\/TR\/2013\/NOTE-prov-primer-20130430\/#agents-and-responsibility"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-016-0475-y"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2015.44"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219104.3219152"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11577188_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2949550.2949590"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2017.03.032"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"e_1_3_2_1_13_1","unstructured":"National Science Foundation. 2014. Chapter II - Proposal Preparation Instructions. (Dec 2014). https:\/\/www.nsf.gov\/pubs\/policydocs\/pappguide\/nsf15001\/gpg_2.jsp#IIC2j  National Science Foundation. 2014. Chapter II - Proposal Preparation Instructions. (Dec 2014). https:\/\/www.nsf.gov\/pubs\/policydocs\/pappguide\/nsf15001\/gpg_2.jsp#IIC2j"},{"key":"e_1_3_2_1_14_1","unstructured":"R. B. Girshick P. F. Felzenszwalb and D. McAllester. 2012. Discriminatively Trained Deformable Part Models Release 5. http:\/\/people.cs.uchicago.edu\/rbg\/latent-release5\/. (09 2012).  R. B. Girshick P. F. Felzenszwalb and D. McAllester. 2012. Discriminatively Trained Deformable Part Models Release 5. http:\/\/people.cs.uchicago.edu\/rbg\/latent-release5\/. (09 2012)."},{"key":"e_1_3_2_1_15_1","volume-title":"Monitoring Water Quality in the Great Lakes Leveraging Geo-Temporal Cyberinfrastructure. In 2017 IEEE 13th International Conference on e-Science (e-Science). 364--373","author":"Gutierrez-Polo I.","unstructured":"I. Gutierrez-Polo , Y. Zhao , S. Bradley , E. Roeder , M. Pitcel , K. TePas , P. Collingsworth , and L. Marini . 2017 . Monitoring Water Quality in the Great Lakes Leveraging Geo-Temporal Cyberinfrastructure. In 2017 IEEE 13th International Conference on e-Science (e-Science). 364--373 . I. Gutierrez-Polo, Y. Zhao, S. Bradley, E. Roeder, M. Pitcel, K. TePas, P. Collingsworth, and L. Marini. 2017. Monitoring Water Quality in the Great Lakes Leveraging Geo-Temporal Cyberinfrastructure. In 2017 IEEE 13th International Conference on e-Science (e-Science). 364--373."},{"key":"e_1_3_2_1_16_1","volume-title":"Shedding light on the dark data in the long tail of science","author":"Heidorn P Bryan","year":"2008","unstructured":"P Bryan Heidorn . 2008. Shedding light on the dark data in the long tail of science . Library trends 57, 2 ( 2008 ), 280--299. P Bryan Heidorn. 2008. Shedding light on the dark data in the long tail of science. Library trends 57, 2 (2008), 280--299."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792756"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093338.3093368"},{"key":"e_1_3_2_1_19_1","unstructured":"John A Lewis. 2014. Research data management technical infrastructure: A review of options for development at the University of Sheffield. (2014).  John A Lewis. 2014. Research data management technical infrastructure: A review of options for development at the University of Sheffield. (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2011.08.007"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.103"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2616498.2616540"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2015.56"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.51"},{"key":"e_1_3_2_1_25_1","volume-title":"Retrieved","author":"National Institutes of Health.","year":"2003","unstructured":"National Institutes of Health. 2003 . NIH Data Sharing Policy and Implementation Guidance. (Mar 2003) . Retrieved March 13, 2018 from https:\/\/grants.nih.gov\/grants\/policy\/data_sharing\/data_sharing_guidance.htm National Institutes of Health. 2003. NIH Data Sharing Policy and Implementation Guidance. (Mar 2003). Retrieved March 13, 2018 from https:\/\/grants.nih.gov\/grants\/policy\/data_sharing\/data_sharing_guidance.htm"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2949550.2949647"},{"key":"e_1_3_2_1_27_1","unstructured":"Scott D Peckham. 2014. The CSDMS standard names: Cross-domain naming conventions for describing process models data sets and their associated variables. (2014).  Scott D Peckham. 2014. The CSDMS standard names: Cross-domain naming conventions for describing process models data sets and their associated variables. (2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"Amit Das, Alex Yahja, and Mark Hasegawa-Johnson.","author":"Poole Marshall Scott","year":"2015","unstructured":"Marshall Scott Poole , Natalie Lambert , Sandeep Puthanveetil Satheesan , Amit Das, Alex Yahja, and Mark Hasegawa-Johnson. 2015 . GroupScope : A Framework and Tools for Large Scale Study of Social Processes. (2015). Marshall Scott Poole, Natalie Lambert, Sandeep Puthanveetil Satheesan, Amit Das, Alex Yahja, and Mark Hasegawa-Johnson. 2015. GroupScope: A Framework and Tools for Large Scale Study of Social Processes. (2015)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093338.3093365"},{"key":"e_1_3_2_1_30_1","volume-title":"Brown Dog: Making the Digital World a Better Place, a Few Files at a Time. In PEARC 18: Practice and Experience in Advanced Research Computing. ACM","author":"Satheesan Sandeep Puthanveetil","year":"2018","unstructured":"Sandeep Puthanveetil Satheesan , Jay Alameda , Shannon Bradley , Michael Dietze , Benjamin Galewsky , Gregory Jansen , Rob Kooper , Praveen Kumar , Jong Lee , Richard Marciano , Luigi Marini , Christopher M. Navarro Barbara S. Minsker , Arthur Schmidt , Marcus Slavenas , William C. Sullivan , Bing Zhang , Yan Zhao , Inna Zharnitsky , and Kenton McHenry . 2018 . Brown Dog: Making the Digital World a Better Place, a Few Files at a Time. In PEARC 18: Practice and Experience in Advanced Research Computing. ACM , New York, NY, USA . To appear. Sandeep Puthanveetil Satheesan, Jay Alameda, Shannon Bradley, Michael Dietze, Benjamin Galewsky, Gregory Jansen, Rob Kooper, Praveen Kumar, Jong Lee, Richard Marciano, Luigi Marini, Christopher M. Navarro Barbara S. Minsker, Arthur Schmidt, Marcus Slavenas, William C. Sullivan, Bing Zhang, Yan Zhao, Inna Zharnitsky, and Kenton McHenry. 2018. Brown Dog: Making the Digital World a Better Place, a Few Files at a Time. In PEARC 18: Practice and Experience in Advanced Research Computing. ACM, New York, NY, USA. To appear."},{"key":"e_1_3_2_1_31_1","volume-title":"Medici 2: A scalable content management system for cultural heritage datasets. Code4Lib Jounral","author":"Sophocleous Constantinos","year":"2017","unstructured":"Constantinos Sophocleous , Luigi Marini , Ropertos Georgiou , Mohammed El-farargy, and Kenton McHenry . 2017. Medici 2: A scalable content management system for cultural heritage datasets. Code4Lib Jounral ( 2017 ). Constantinos Sophocleous, Luigi Marini, Ropertos Georgiou, Mohammed El-farargy, and Kenton McHenry. 2017. Medici 2: A scalable content management system for cultural heritage datasets. Code4Lib Jounral (2017)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/bult.70"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2008.470"},{"key":"e_1_3_2_1_34_1","unstructured":"Joss Winn et al. 2013. Open data and the academy: an evaluation of CKAN for research data management. (2013).  Joss Winn et al. 2013. Open data and the academy: an evaluation of CKAN for research data management. (2013)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"B. Zhang L. C. Pouchard P. M. Smith A. Gasc and B. C. Pijanowski. 2016. Data storage and sharing for the long tail of science. In 2016 New York Scientific Data Summit (NYSDS). 1--9.  B. Zhang L. C. Pouchard P. M. Smith A. Gasc and B. C. Pijanowski. 2016. Data storage and sharing for the long tail of science. In 2016 New York Scientific Data Summit (NYSDS). 1--9.","DOI":"10.1109\/NYSDS.2016.7747811"},{"key":"e_1_3_2_1_36_1","volume-title":"2016 IEEE 12th International Conference on e-Science (e-Science). 165--174","author":"Zhao Y.","unstructured":"Y. Zhao , E. F. Black , L. Marini , K. McHenry , N. Kenyon , R. Patil , A. Balla , and A. Bartholomew . 2016. Automatic glomerulus extraction in whole slide images towards computer aided diagnosis . In 2016 IEEE 12th International Conference on e-Science (e-Science). 165--174 . Y. Zhao, E. F. Black, L. Marini, K. McHenry, N. Kenyon, R. Patil, A. Balla, and A. Bartholomew. 2016. Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. In 2016 IEEE 12th International Conference on e-Science (e-Science). 165--174."}],"event":{"name":"PEARC '18: Practice and Experience in Advanced Research Computing","location":"Pittsburgh PA USA","acronym":"PEARC '18"},"container-title":["Proceedings of the Practice and Experience on Advanced Research Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219104.3219159","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219104.3219159","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219104.3219159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:07:12Z","timestamp":1750212432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219104.3219159"}},"subtitle":["Open Source Data Management for Long Tail Data"],"short-title":[],"issued":{"date-parts":[[2018,7,22]]},"references-count":36,"alternative-id":["10.1145\/3219104.3219159","10.1145\/3219104"],"URL":"https:\/\/doi.org\/10.1145\/3219104.3219159","relation":{},"subject":[],"published":{"date-parts":[[2018,7,22]]},"assertion":[{"value":"2018-07-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}