{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T20:36:52Z","timestamp":1790800612708,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100007601","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["825328"],"award-info":[{"award-number":["825328"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,29]]},"DOI":"10.1145\/3379597.3387496","type":"proceedings-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T22:12:49Z","timestamp":1600467169000},"page":"523-527","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["A Dataset for GitHub Repository Deduplication"],"prefix":"10.1145","author":[{"given":"Diomidis","family":"Spinellis","sequence":"first","affiliation":[{"name":"Athens University of Economics and Business"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zoe","family":"Kotti","sequence":"additional","affiliation":[{"name":"Athens University of Economics and Business"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Audris","family":"Mockus","sequence":"additional","affiliation":[{"name":"University of Tennessee"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183519.3183549"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359591.3359735"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning (ICML '16)","author":"Allamanis Miltiadis","year":"2016","unstructured":"Miltiadis Allamanis , Hao Peng , and Charles Sutton . 2016 . A Convolutional Attention Network for Extreme Summarization of Source Code . In International Conference on Machine Learning (ICML '16) . 2091--2100. https:\/\/arxiv.org\/pdf\/1602.03001.pdf Miltiadis Allamanis, Hao Peng, and Charles Sutton. 2016. A Convolutional Attention Network for Extreme Summarization of Source Code. In International Conference on Machine Learning (ICML '16). 2091--2100. https:\/\/arxiv.org\/pdf\/1602.03001.pdf"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1136\/jme.2003.004374"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2014.23247"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-018-9650-5"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/32.799939"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00072"},{"key":"e_1_3_2_1_9_1","unstructured":"Roberto de la Cruz and Jan-Ulrich Kreft. 2018. Geometric mean extension for data sets with zeros. Available online https:\/\/arxiv.org\/abs\/1806.06403.arXiv:stat.AP\/1806.06403  Roberto de la Cruz and Jan-Ulrich Kreft. 2018. Geometric mean extension for data sets with zeros. Available online https:\/\/arxiv.org\/abs\/1806.06403.arXiv:stat.AP\/1806.06403"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/1097-024X(200009)30:11<1203::AID-SPE338>3.0.CO;2-N"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2487085.2487132"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2568225.2568260"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2664446.2664449"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-C.2017.164"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884826"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597073.2597122"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2818754.2818800"},{"key":"e_1_3_2_1_18_1","volume-title":"McDaniel","author":"Grosse Kathrin","year":"2017","unstructured":"Kathrin Grosse , Praveen Manoharan , Nicolas Papernot , Michael Backes , and Patrick D . McDaniel . 2017 . On the (Statistical) Detection of Adversarial Examples. ArXiv abs\/1702.06280 (2017). Kathrin Grosse, Praveen Manoharan, Nicolas Papernot, Michael Backes, and Patrick D. McDaniel. 2017. On the (Statistical) Detection of Adversarial Examples. ArXiv abs\/1702.06280 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"McDaniel","author":"Grosse Kathrin","year":"2016","unstructured":"Kathrin Grosse , Nicolas Papernot , Praveen Manoharan , Michael Backes , and Patrick D . McDaniel . 2016 . Adversarial Perturbations Against Deep Neural Networks for Malware Classification. CoRR abs\/1606.04435 (2016). http:\/\/arxiv.org\/abs\/1606.04435 Kathrin Grosse, Nicolas Papernot, Praveen Manoharan, Michael Backes, and Patrick D. McDaniel. 2016. Adversarial Perturbations Against Deep Neural Networks for Malware Classification. CoRR abs\/1606.04435 (2016). http:\/\/arxiv.org\/abs\/1606.04435"},{"key":"e_1_3_2_1_20_1","first-page":"419","article-title":"Geometric Mean for Negative and Zero Values","volume":"11","author":"Habib Elsayed AE","year":"2012","unstructured":"Elsayed AE Habib . 2012 . Geometric Mean for Negative and Zero Values . International Journal of Research and Reviews in Applied Sciences 11 , 3 (2012), 419 -- 432 . Elsayed AE Habib. 2012. Geometric Mean for Negative and Zero Values. International Journal of Research and Reviews in Applied Sciences 11, 3 (2012), 419--32.","journal-title":"International Journal of Research and Reviews in Applied Sciences"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236051"},{"key":"e_1_3_2_1_22_1","volume-title":"The Case for Open Computer Programs. Nature 482, 7386","author":"Ince Darrel C","year":"2012","unstructured":"Darrel C Ince , Leslie Hatton , and John Graham-Cumming . 2012. The Case for Open Computer Programs. Nature 482, 7386 ( 2012 ), 485--488. Darrel C Ince, Leslie Hatton, and John Graham-Cumming. 2012. The Case for Open Computer Programs. Nature 482, 7386 (2012), 485--488."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11416-018-0316-z"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1195"},{"key":"e_1_3_2_1_25_1","volume-title":"An In-Depth Study of the Promises and Perils of mining GitHub. Empirical Software Engineering 21, 5 (01","author":"Kalliamvakou Eirini","year":"2016","unstructured":"Eirini Kalliamvakou , Georgios Gousios , Kelly Blincoe , Leif Singer , Daniel M. German , and Daniela Damian . 2016. An In-Depth Study of the Promises and Perils of mining GitHub. Empirical Software Engineering 21, 5 (01 Oct. 2016 ), 2035--2071. https:\/\/doi.org\/10.1007\/s10664-015-9393-5 10.1007\/s10664-015-9393-5 Eirini Kalliamvakou, Georgios Gousios, Kelly Blincoe, Leif Singer, Daniel M. German, and Daniela Damian. 2016. An In-Depth Study of the Promises and Perils of mining GitHub. Empirical Software Engineering 21, 5 (01 Oct. 2016), 2035--2071. https:\/\/doi.org\/10.1007\/s10664-015-9393-5"},{"key":"e_1_3_2_1_26_1","volume-title":"Finding Similar Items","author":"Leskovec Jure","unstructured":"Jure Leskovec , Anand Rajaraman , and Jeff Ullman . 2020. Chapter 3. Finding Similar Items . Cambridge University Press , New York, NY, USA . http:\/\/infolab.stanford.edu\/~ullman\/mmds\/book0n.pdf Jure Leskovec, Anand Rajaraman, and Jeff Ullman. 2020. Chapter 3. Finding Similar Items. Cambridge University Press, New York, NY, USA. http:\/\/infolab.stanford.edu\/~ullman\/mmds\/book0n.pdf"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133908"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning -","volume":"32","author":"Chris","unstructured":"Chris J. Maddison and Daniel Tarlow. 2014. Structured Generative Models of Natural Source Code . In Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 (ICML '14). JMLR.org, 649--657. Chris J. Maddison and Daniel Tarlow. 2014. Structured Generative Models of Natural Source Code. In Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 (ICML '14). JMLR.org, 649--657."},{"key":"e_1_3_2_1_29_1","volume-title":"Topic Modeling of Public Repositories at Scale using Names in Source Code. CoRR abs\/1704.00135","author":"Markovtsev Vadim","year":"2017","unstructured":"Vadim Markovtsev and Eiso Kant . 2017. Topic Modeling of Public Repositories at Scale using Names in Source Code. CoRR abs\/1704.00135 ( 2017 ). arXiv:1704.00135 http:\/\/arxiv.org\/abs\/1704.00135 Vadim Markovtsev and Eiso Kant. 2017. Topic Modeling of Public Repositories at Scale using Names in Source Code. CoRR abs\/1704.00135 (2017). arXiv:1704.00135 http:\/\/arxiv.org\/abs\/1704.00135"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387499"},{"key":"e_1_3_2_1_31_1","volume-title":"Curating GitHub for Engineered Software Projects. Empirical Software Engineering 22, 6 (01","author":"Munaiah Nuthan","year":"2017","unstructured":"Nuthan Munaiah , Steven Kroh , Craig Cabrey , and Meiyappan Nagappan . 2017. Curating GitHub for Engineered Software Projects. Empirical Software Engineering 22, 6 (01 Dec 2017 ), 3219--3253. https:\/\/doi.org\/10.1007\/s10664-017-9512-6 10.1007\/s10664-017-9512-6 Nuthan Munaiah, Steven Kroh, Craig Cabrey, and Meiyappan Nagappan. 2017. Curating GitHub for Engineered Software Projects. Empirical Software Engineering 22, 6 (01 Dec 2017), 3219--3253. https:\/\/doi.org\/10.1007\/s10664-017-9512-6"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491411.2491415"},{"key":"e_1_3_2_1_33_1","volume-title":"Riccardo Rubei, and Davide Di Ruscio.","author":"Nguyen Phuong T.","year":"2020","unstructured":"Phuong T. Nguyen , Juri Di Rocco , Riccardo Rubei, and Davide Di Ruscio. 2020 . An automated approach to assess the similarity of GitHub repositories. Software Quality Journal (Feb . 2020). https:\/\/doi.org\/10.1007\/s11219-019-09483-0 10.1007\/s11219-019-09483-0 Phuong T. Nguyen, Juri Di Rocco, Riccardo Rubei, and Davide Di Ruscio. 2020. An automated approach to assess the similarity of GitHub repositories. Software Quality Journal (Feb. 2020). https:\/\/doi.org\/10.1007\/s11219-019-09483-0"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132785"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00033"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2676726.2677009"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594321"},{"key":"e_1_3_2_1_38_1","volume-title":"Research in Attacks, Intrusions, and Defenses, Fabian Monrose, Marc Dacier, Gregory Blanc, and Joaquin Garcia-Alfaro (Eds.)","author":"Sebasti\u00e1n Marcos","unstructured":"Marcos Sebasti\u00e1n , Richard Rivera , Platon Kotzias , and Juan Caballero . 2016. AV-class: A Tool for Massive Malware Labeling . In Research in Attacks, Intrusions, and Defenses, Fabian Monrose, Marc Dacier, Gregory Blanc, and Joaquin Garcia-Alfaro (Eds.) . Springer International Publishing , Cham , 230--253. Marcos Sebasti\u00e1n, Richard Rivera, Platon Kotzias, and Juan Caballero. 2016. AV-class: A Tool for Massive Malware Labeling. In Research in Attacks, Intrusions, and Defenses, Fabian Monrose, Marc Dacier, Gregory Blanc, and Joaquin Garcia-Alfaro (Eds.). Springer International Publishing, Cham, 230--253."},{"key":"#cr-split#-e_1_3_2_1_39_1.1","doi-asserted-by":"crossref","unstructured":"Diomidis Spinellis Zoe Kotti and Audris Mockus. 2020. A Dataset for GitHub Repository Deduplication: Extended Description. https:\/\/doi.org\/10.5281\/zenodo.3740595 10.5281\/zenodo.3740595","DOI":"10.1145\/3379597.3387496"},{"key":"#cr-split#-e_1_3_2_1_39_1.2","doi-asserted-by":"crossref","unstructured":"Diomidis Spinellis Zoe Kotti and Audris Mockus. 2020. A Dataset for GitHub Repository Deduplication: Extended Description. https:\/\/doi.org\/10.5281\/zenodo.3740595","DOI":"10.1145\/3379597.3387496"}],"event":{"name":"MSR '20: 17th International Conference on Mining Software Repositories","location":"Seoul Republic of Korea","acronym":"MSR '20","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 17th International Conference on Mining Software Repositories"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3379597.3387496","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3379597.3387496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:41:20Z","timestamp":1750185680000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3379597.3387496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":40,"alternative-id":["10.1145\/3379597.3387496","10.1145\/3379597"],"URL":"https:\/\/doi.org\/10.1145\/3379597.3387496","relation":{},"subject":[],"published":{"date-parts":[[2020,6,29]]},"assertion":[{"value":"2020-09-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}