{"id":"https://openalex.org/W2099677903","doi":"https://doi.org/10.1109/msr.2009.5069476","title":"Amassing and indexing a large sample of version control systems: Towards the census of public source code history","display_name":"Amassing and indexing a large sample of version control systems: Towards the census of public source code history","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2099677903","doi":"https://doi.org/10.1109/msr.2009.5069476","mag":"2099677903"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"article","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/A5067199285","display_name":"Audris Mockus","orcid":"https://orcid.org/0000-0002-7987-7598"},"institutions":[{"id":"https://openalex.org/I60921084","display_name":"Avaya (Bermuda)","ror":"https://ror.org/01ye7b264","country_code":"BM","type":"company","lineage":["https://openalex.org/I4210137298","https://openalex.org/I60921084"]},{"id":"https://openalex.org/I4210137298","display_name":"Avaya (United States)","ror":"https://ror.org/041vyyf82","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137298"]}],"countries":["BM","US"],"is_corresponding":true,"raw_author_name":"Audris Mockus","raw_affiliation_strings":["Avaya Laboratories Research, Basking Ridge, NJ, USA","Avaya Labs Research, 233 Mt Airy Rd, Basking Ridge, NJ 07901, USA"],"affiliations":[{"raw_affiliation_string":"Avaya Laboratories Research, Basking Ridge, NJ, USA","institution_ids":["https://openalex.org/I4210137298"]},{"raw_affiliation_string":"Avaya Labs Research, 233 Mt Airy Rd, Basking Ridge, NJ 07901, USA","institution_ids":["https://openalex.org/I60921084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067199285"],"corresponding_institution_ids":["https://openalex.org/I4210137298","https://openalex.org/I60921084"],"apc_list":null,"apc_paid":null,"fwci":21.6927,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.9922468,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.995199978351593,"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":0.7748708724975586},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.684838593006134},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48538029193878174},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47687608003616333},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.47135061025619507},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47063514590263367},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3475250005722046},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2851998805999756},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20618915557861328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748708724975586},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.684838593006134},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48538029193878174},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47687608003616333},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.47135061025619507},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47063514590263367},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3475250005722046},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2851998805999756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20618915557861328},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msr.2009.5069476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 6th IEEE International Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.9341","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.9341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mockus.us/papers/amassing.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W188174107","https://openalex.org/W1583467731","https://openalex.org/W2038276547","https://openalex.org/W2042117400","https://openalex.org/W2050136587","https://openalex.org/W2066521842","https://openalex.org/W2096624252","https://openalex.org/W2101149922","https://openalex.org/W2116484544","https://openalex.org/W2121528215","https://openalex.org/W2125951552","https://openalex.org/W2127768196","https://openalex.org/W2128737833","https://openalex.org/W2132944054","https://openalex.org/W2141482658","https://openalex.org/W2154962571","https://openalex.org/W4233773669","https://openalex.org/W4240398231","https://openalex.org/W4244325127","https://openalex.org/W4247088722"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2000569830","https://openalex.org/W3081644756"],"abstract_inverted_index":{"The":[0,117],"source":[1,52,66,102,177],"code":[2,67,103,178],"and":[3,9,15,22,31,68,84,99,123,136,144,173],"its":[4,69],"history":[5],"represent":[6],"the":[7,44,51,60,77,101,110,134,140,161,176],"output":[8],"process":[10],"of":[11,24,33,46,50,63,88,133,142,151,160,170,175],"software":[12,25],"development":[13,26],"activities":[14],"are":[16,180],"an":[17,86],"invaluable":[18],"resource":[19],"for":[20,93,100],"study":[21],"improvement":[23],"practice.":[27],"While":[28,108],"individual":[29],"projects":[30,34],"groups":[32],"have":[35],"been":[36],"extensively":[37],"analyzed,":[38],"some":[39],"fundamental":[40],"questions,":[41],"such":[42,89],"as":[43],"spread":[45],"innovation":[47],"or":[48],"genealogy":[49],"code,":[53],"can":[54,126],"be":[55,127],"answered":[56],"only":[57],"by":[58],"considering":[59],"entire":[61],"universe":[62],"publicly":[64,94],"available":[65],"history.":[70],"We":[71],"describe":[72],"methods":[73],"we":[74],"developed":[75],"over":[76],"last":[78],"six":[79],"years":[80],"to":[81],"gather,":[82],"index,":[83],"update":[85],"approximation":[87],"a":[90,105,147],"universal":[91,165],"repository":[92,166],"accessible":[95],"version":[96,153],"control":[97,154],"systems":[98,155],"inside":[104],"large":[106],"corporation.":[107],"challenging,":[109],"task":[111],"is":[112],"achievable":[113],"with":[114,129],"limited":[115],"resources.":[116],"bottlenecks":[118],"in":[119],"network":[120],"bandwidth,":[121],"processing,":[122],"disk":[124],"access":[125],"dealt":[128],"using":[130],"inherent":[131],"parallelism":[132],"tasks":[135],"suitable":[137],"tradeoffs":[138],"between":[139],"amount":[141],"storage":[143],"computations,":[145],"but":[146],"completely":[148],"automated":[149],"discovery":[150],"public":[152],"may":[156],"require":[157],"enticing":[158],"participation":[159],"sampled":[162],"projects.":[163],"Such":[164],"would":[167],"allow":[168],"studies":[169],"global":[171],"properties":[172],"origins":[174],"that":[179],"not":[181],"possible":[182],"through":[183],"other":[184],"means.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}