{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:08:23Z","timestamp":1775815703239,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,5,31]],"date-time":"2014-05-31T00:00:00Z","timestamp":1401494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,5,31]]},"DOI":"10.1145\/2597073.2597126","type":"proceedings-article","created":{"date-parts":[[2014,5,20]],"date-time":"2014-05-20T13:48:00Z","timestamp":1400593680000},"page":"384-387","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":97,"title":["Lean GHTorrent: GitHub data on demand"],"prefix":"10.1145","author":[{"given":"Georgios","family":"Gousios","sequence":"first","affiliation":[{"name":"Delft University of Technology, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Vasilescu","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Serebrenik","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy","family":"Zaidman","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2014,5,31]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"216","volume-title":"MSR","author":"Allamanis M.","unstructured":"M. Allamanis and C. Sutton . Mining source code repositories at massive scale using language modeling . In MSR , pages 207\u2013 216 . IEEE, 2013. M. Allamanis and C. Sutton. Mining source code repositories at massive scale using language modeling. In MSR, pages 207\u2013216. IEEE, 2013."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28872-2_22"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806799.1806821"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145204.2145396"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SDSOA.2007.5"},{"key":"e_1_3_2_1_6_1","first-page":"431","volume-title":"ICSE","author":"Dyer R.","unstructured":"R. Dyer , H. A. Nguyen , H. Rajan , and T. N. Nguyen . Boa: A language and infrastructure for analyzing ultra-large-scale software repositories . In ICSE , pages 422\u2013 431 . IEEE, 2013. R. Dyer, H. A. Nguyen, H. Rajan, and T. N. Nguyen. Boa: A language and infrastructure for analyzing ultra-large-scale software repositories. In ICSE, pages 422\u2013431. IEEE, 2013."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-011-9181-9"},{"key":"e_1_3_2_1_8_1","first-page":"236","volume-title":"MSR","author":"Gousios G.","unstructured":"G. Gousios . The GHTorent dataset and tool suite . In MSR , pages 233\u2013 236 . IEEE, 2013. G. Gousios. The GHTorent dataset and tool suite. In MSR, pages 233\u2013236. IEEE, 2013."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2568225.2568260"},{"key":"e_1_3_2_1_10_1","first-page":"21","volume-title":"MSR","author":"Gousios G.","unstructured":"G. Gousios and D. Spinellis . GHTorrent: Github\u2019s data from a firehose . In MSR , pages 12\u2013 21 . IEEE, 2012. G. Gousios and D. Spinellis. GHTorrent: Github\u2019s data from a firehose. In MSR, pages 12\u201321. IEEE, 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491055.2491070"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985441.1985476"},{"issue":"3","key":"e_1_3_2_1_13_1","first-page":"17","article-title":"FLOSSmole: A collaborative repository for FLOSS research data and analyses","volume":"1","author":"Howison J.","year":"2006","unstructured":"J. Howison , M. Conklin , and K. Crowston . FLOSSmole: A collaborative repository for FLOSS research data and analyses . IJIT , 1 ( 3 ): 17 \u2013 26 , 2006 . J. Howison, M. Conklin, and K. Crowston. FLOSSmole: A collaborative repository for FLOSS research data and analyses. IJIT, 1(3):17\u201326, 2006.","journal-title":"IJIT"},{"key":"e_1_3_2_1_14_1","first-page":"141","volume-title":"WCRE","author":"Jiang J.","unstructured":"J. Jiang , L. Zhang , and L. Li . Understanding project dissemination on a social coding site . In WCRE , pages 132\u2013 141 . IEEE, 2013. J. Jiang, L. Zhang, and L. Li. Understanding project dissemination on a social coding site. In WCRE, pages 132\u2013141. IEEE, 2013."},{"key":"e_1_3_2_1_15_1","first-page":"4","volume-title":"ICISA","author":"Lee H.","unstructured":"H. Lee , B.-K. Seo , and E. Seo . A git source repository analysis tool based on a novel branch-oriented approach . In ICISA , pages 1\u2013 4 . IEEE, 2013. H. Lee, B.-K. Seo, and E. Seo. A git source repository analysis tool based on a novel branch-oriented approach. In ICISA, pages 1\u20134. IEEE, 2013."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2441776.2441792"},{"key":"e_1_3_2_1_17_1","first-page":"121","volume-title":"ICSE","author":"Pham R.","unstructured":"R. Pham , L. Singer , O. Liskin , F. Figueira Filho , and K. Schneider . Creating a shared understanding of testing culture on a social coding site . In ICSE , pages 112\u2013 121 . IEEE, 2013. R. Pham, L. Singer, O. Liskin, F. Figueira Filho, and K. Schneider. Creating a shared understanding of testing culture on a social coding site. In ICSE, pages 112\u2013121. IEEE, 2013."},{"key":"e_1_3_2_1_18_1","first-page":"1212","volume-title":"ICSE","author":"Pham R.","unstructured":"R. Pham , L. Singer , and K. Schneider . Building test suites in social coding sites by leveraging drive-by commits . In ICSE , pages 1209\u2013 1212 . IEEE, 2013. R. Pham, L. Singer, and K. Schneider. Building test suites in social coding sites by leveraging drive-by commits. In ICSE, pages 1209\u20131212. IEEE, 2013."},{"key":"e_1_3_2_1_19_1","volume-title":"Information and Software Technology","author":"Schall D.","year":"2013","unstructured":"D. Schall . Who to follow recommendation in large-scale online development communities . Information and Software Technology , 2013 . D. Schall. Who to follow recommendation in large-scale online development communities. Information and Software Technology, 2013."},{"key":"e_1_3_2_1_20_1","series-title":"IFIP","first-page":"160","volume-title":"Open Source Development, Adoption and Innovation","author":"Sowe S. K.","unstructured":"S. K. Sowe , L. Angelis , I. Stamelos , and Y. Manolopoulos . Using repository of repositories (RoRs) to study the growth of F\/OSS projects: A meta-analysis research approach . In Open Source Development, Adoption and Innovation , volume 234 of IFIP , pages 147\u2013 160 . Springer, 2007. S. K. Sowe, L. Angelis, I. Stamelos, and Y. Manolopoulos. Using repository of repositories (RoRs) to study the growth of F\/OSS projects: A meta-analysis research approach. In Open Source Development, Adoption and Innovation, volume 234 of IFIP, pages 147\u2013160. Springer, 2007."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2014.405"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSMR.2013.41"},{"key":"e_1_3_2_1_23_1","unstructured":"B. Vasilescu. Academic papers using Stack Overflow data. http:\/\/meta.stackoverflow.com\/q\/134495 2012.  B. Vasilescu. Academic papers using Stack Overflow data. http:\/\/meta.stackoverflow.com\/q\/134495 2012."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SocialCom.2013.35"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1137983.1138024"},{"key":"e_1_3_2_1_26_1","first-page":"232","volume-title":"MSR","author":"Wagstrom P.","unstructured":"P. Wagstrom , C. Jergensen , and A. Sarma . A network of rails: a graph dataset of ruby on rails and associated projects . In MSR , pages 229\u2013 232 . IEEE, 2013. P. Wagstrom, C. Jergensen, and A. Sarma. A network of rails: a graph dataset of ruby on rails and associated projects. In MSR, pages 229\u2013232. IEEE, 2013."}],"event":{"name":"ICSE '14: 36th International Conference on Software Engineering","location":"Hyderabad India","acronym":"ICSE '14","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","TCSE IEEE Computer Society's Tech. Council on Software Engin."]},"container-title":["Proceedings of the 11th Working Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2597073.2597126","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2597073.2597126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:09:57Z","timestamp":1750234197000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2597073.2597126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,31]]},"references-count":26,"alternative-id":["10.1145\/2597073.2597126","10.1145\/2597073"],"URL":"https:\/\/doi.org\/10.1145\/2597073.2597126","relation":{},"subject":[],"published":{"date-parts":[[2014,5,31]]},"assertion":[{"value":"2014-05-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}