{"id":"https://openalex.org/W2073429012","doi":"https://doi.org/10.1145/2597073.2597126","title":"Lean GHTorrent: GitHub data on demand","display_name":"Lean GHTorrent: GitHub data on demand","publication_year":2014,"publication_date":"2014-05-20","ids":{"openalex":"https://openalex.org/W2073429012","doi":"https://doi.org/10.1145/2597073.2597126","mag":"2073429012"},"language":"en","primary_location":{"id":"doi:10.1145/2597073.2597126","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043864604","display_name":"Georgios Gousios","orcid":"https://orcid.org/0000-0002-8495-7939"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Georgios Gousios","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050821883","display_name":"Bogdan Vasilescu","orcid":"https://orcid.org/0000-0003-4418-5783"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bogdan Vasilescu","raw_affiliation_strings":["Eindhoven University of Technology, Netherlands","Eindhoven University of Technology, Netherlands,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Netherlands,","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054753279","display_name":"Alexander Serebrenik","orcid":"https://orcid.org/0000-0002-1418-0095"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexander Serebrenik","raw_affiliation_strings":["Eindhoven University of Technology, Netherlands","Eindhoven University of Technology, Netherlands,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, Netherlands,","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046237164","display_name":"Andy Zaidman","orcid":"https://orcid.org/0000-0003-2413-3935"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Andy Zaidman","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":173,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11675","display_name":"Open Source Software Innovations","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7810569405555725},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6820558905601501},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5647160410881042},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5532205700874329},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5306065678596497},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4830965995788574},{"id":"https://openalex.org/keywords/open-data","display_name":"Open data","score":0.45352065563201904},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.43604904413223267},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.4248805642127991},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.41191112995147705},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.299564003944397},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2604060173034668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810569405555725},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6820558905601501},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5647160410881042},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5532205700874329},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5306065678596497},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4830965995788574},{"id":"https://openalex.org/C2780535194","wikidata":"https://www.wikidata.org/wiki/Q309901","display_name":"Open data","level":2,"score":0.45352065563201904},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.43604904413223267},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.4248805642127991},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.41191112995147705},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.299564003944397},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2604060173034668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1145/2597073.2597126","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/99c19fce-5616-49b0-a66e-8cb908f74148","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/99c19fce-5616-49b0-a66e-8cb908f74148","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Gousios, G, Vasilescu, B N, Serebrenik, A & Zaidman, A 2014, Lean GHTorrent : GitHub data on demand. in 11th Working Conference on Mining Software Repositories (MSR '14, Hyderabad, India, May 31-June 1, 2014). Association for Computing Machinery, Inc., New York NY, pp. 384-387, 11th Working Conference on Mining Software Repositories (MSR 2014), Hyderabad, India, 31/05/14. https://doi.org/10.1145/2597073.2597126","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:772222","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=772222","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.658.1505","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.658.1505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ifipwg213.org/sites/flosshub.org/files/lean-ghtorrent.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.724.6700","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.724.6700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.win.tue.nl/%7Easerebre/msr14georgios.pdf","raw_type":"text"},{"id":"pmh:oai:library.tue.nl:772222","is_oa":false,"landing_page_url":"http://repository.tue.nl/772222","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:tue:oai:pure.tue.nl:publications/99c19fce-5616-49b0-a66e-8cb908f74148","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/99c19fce-5616-49b0-a66e-8cb908f74148","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"11th Working Conference on Mining Software Repositories (MSR '14, Hyderabad, India, May 31-June 1, 2014), 384 - 387","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1554934468","https://openalex.org/W1819759706","https://openalex.org/W1972386298","https://openalex.org/W1974270771","https://openalex.org/W1979848034","https://openalex.org/W1986775229","https://openalex.org/W1989479444","https://openalex.org/W2001150155","https://openalex.org/W2016702417","https://openalex.org/W2018916326","https://openalex.org/W2050136587","https://openalex.org/W2051144853","https://openalex.org/W2055837583","https://openalex.org/W2062208052","https://openalex.org/W2090625011","https://openalex.org/W2110499955","https://openalex.org/W2118174895","https://openalex.org/W2122414758","https://openalex.org/W2124100711","https://openalex.org/W2133032989","https://openalex.org/W2134374547","https://openalex.org/W2139092060","https://openalex.org/W2141077757","https://openalex.org/W2148190602","https://openalex.org/W2187303492","https://openalex.org/W2545778708","https://openalex.org/W6643459645"],"related_works":["https://openalex.org/W2113128227","https://openalex.org/W4386133355","https://openalex.org/W632256878","https://openalex.org/W4211197663","https://openalex.org/W2491403535","https://openalex.org/W3123068371","https://openalex.org/W2479811461","https://openalex.org/W2104915799","https://openalex.org/W2355429491","https://openalex.org/W4251813405"],"abstract_inverted_index":{"In":[0,123],"recent":[1],"years,":[2],"GitHub":[3,39,51,93,120,164,191,207],"has":[4],"become":[5],"the":[6,11,82,115,119,148,180,204,213,217],"largest":[7],"code":[8,47],"host":[9,42],"in":[10,189],"world,":[12],"with":[13],"more":[14],"than":[15],"5M":[16],"developers":[17,71],"collaborating":[18],"across":[19],"10M":[20],"repositories.":[21,165],"Numerous":[22],"popular":[23],"open":[24,65],"source":[25,66],"projects":[26],"(such":[27],"as":[28,40],"Ruby":[29],"on":[30,139,215],"Rails,":[31],"Homebrew,":[32],"Bootstrap,":[33],"Django":[34],"or":[35,78,88],"jQuery)":[36],"have":[37,44,106],"chosen":[38],"their":[41,46,74,198],"and":[43,81],"migrated":[45],"base":[48],"to":[49,72,76,96,134,150,196],"it.":[50],"offers":[52,146],"a":[53,61,68,109,128,153,210],"tremendous":[54],"research":[55],"potential.":[56],"For":[57],"instance,":[58],"it":[59],"is":[60],"flagship":[62],"for":[63,70,160,182,186],"current":[64],"development,":[67],"place":[69],"showcase":[73],"expertise":[75],"peers":[77],"potential":[79],"recruiters,":[80],"platform":[83],"where":[84],"social":[85],"coding":[86],"features":[87],"pull":[89],"requests":[90],"emerged.":[91],"However,":[92],"data":[94,116,137,158,173,192,214],"is,":[95],"date,":[97],"largely":[98],"underexplored.":[99],"To":[100],"facilitate":[101],"studies":[102,208],"of":[103,114,131,163,206,212],"GitHub,":[104],"we":[105,126,175],"created":[107],"GHTorrent,":[108],"scalable,":[110],"queriable,":[111],"offline":[112],"mirror":[113],"offered":[117],"through":[118],"REST":[121],"API.":[122],"this":[124],"paper":[125],"present":[127],"novel":[129],"feature":[130],"GHTorrent":[132,143,157,172],"designed":[133],"offer":[135],"customisable":[136,171],"dumps":[138,159,174],"demand.":[140],"The":[141],"new":[142],"data-on-demand":[144],"service":[145],"users":[147],"possibility":[149],"request":[151],"via":[152],"web":[154],"form":[155],"up-to-date":[156],"any":[161],"collection":[162],"We":[166],"hope":[167],"that":[168],"by":[169],"offering":[170],"will":[176],"not":[177],"only":[178],"lower":[179],"\"barrier":[181],"entry\"":[183],"even":[184],"further":[185],"researchers":[187,195],"interested":[188],"mining":[190,199],"(thus":[193],"encourage":[194],"intensify":[197],"efforts),":[200],"but":[201],"also":[202],"enhance":[203],"replicability":[205],"(since":[209],"snapshot":[211],"which":[216],"results":[218],"were":[219],"obtained":[220],"can":[221],"now":[222],"easily":[223],"accompany":[224],"each":[225],"study).":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":34},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}