{"id":"https://openalex.org/W3144106047","doi":"https://doi.org/10.1109/msr.2009.5069475","title":"The promises and perils of mining git","display_name":"The promises and perils of mining git","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W3144106047","doi":"https://doi.org/10.1109/msr.2009.5069475","mag":"3144106047"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069475","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":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1276077","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036278905","display_name":"Christian Bird","orcid":"https://orcid.org/0000-0002-7774-0387"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christian Bird","raw_affiliation_strings":["University of California, San Diego, Davis, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, Davis, USA","institution_ids":["https://openalex.org/I84218800","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020289098","display_name":"Peter C. Rigby","orcid":"https://orcid.org/0000-0003-1137-4297"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Peter C. Rigby","raw_affiliation_strings":["University of Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076587279","display_name":"Earl T. Barr","orcid":"https://orcid.org/0000-0003-0771-7891"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Earl T. Barr","raw_affiliation_strings":["University of California, San Diego, Davis, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, Davis, USA","institution_ids":["https://openalex.org/I84218800","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079682371","display_name":"David J. Hamilton","orcid":"https://orcid.org/0000-0002-3030-9485"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David J. Hamilton","raw_affiliation_strings":["University of California, San Diego, Davis, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, Davis, USA","institution_ids":["https://openalex.org/I84218800","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027592388","display_name":"Daniel M. Germ\u00e1n","orcid":"https://orcid.org/0000-0001-5661-4392"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel M. German","raw_affiliation_strings":["University of Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036744986","display_name":"Pr\u00e9mkumar D\u00e9vanbu","orcid":"https://orcid.org/0000-0002-4346-5276"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Devanbu","raw_affiliation_strings":["University of California, San Diego, Davis, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, Davis, USA","institution_ids":["https://openalex.org/I84218800","https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036278905"],"corresponding_institution_ids":["https://openalex.org/I36258959","https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":24.8422,"has_fulltext":false,"cited_by_count":308,"citation_normalized_percentile":{"value":0.99383177,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.7963411808013916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6957887411117554},{"id":"https://openalex.org/keywords/decentralization","display_name":"Decentralization","score":0.6393519639968872},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5192944407463074},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.505652666091919},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4960547387599945},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47939252853393555},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4597696363925934},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4371407926082611},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41167157888412476},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3269873261451721},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25873732566833496},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1394154131412506},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11755481362342834},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10309061408042908}],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.7963411808013916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957887411117554},{"id":"https://openalex.org/C136810230","wikidata":"https://www.wikidata.org/wiki/Q188961","display_name":"Decentralization","level":2,"score":0.6393519639968872},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5192944407463074},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.505652666091919},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4960547387599945},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47939252853393555},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4597696363925934},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4371407926082611},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41167157888412476},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3269873261451721},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25873732566833496},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1394154131412506},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11755481362342834},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10309061408042908},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/msr.2009.5069475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069475","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:10.1.1.158.6735","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.6735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://macbeth.cs.ucdavis.edu/gitminingpaper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.6011","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.6011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wwwcsif.cs.ucdavis.edu/~bird/papers/bird2009ppm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.408.6999","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.408.6999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://earlbarr.com/publications/promisePeril.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.495.8595","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.495.8595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://turingmachine.org/~dmg/papers/dmg2009_msr_git.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1377859","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1377859/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:   (Proceedings) 6th IEEE International Working Conference on Mining Software Repositories. (pp. 1-+).  IEEE (2009)     ","raw_type":"Proceedings paper"},{"id":"pmh:oai:zenodo.org:1276077","is_oa":true,"landing_page_url":"https://zenodo.org/record/1276077","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1276077","is_oa":true,"landing_page_url":"https://zenodo.org/record/1276077","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1576624296","https://openalex.org/W1994360381","https://openalex.org/W2032342931","https://openalex.org/W2103188316","https://openalex.org/W2107294940","https://openalex.org/W2110385988","https://openalex.org/W2110498832","https://openalex.org/W2112357885","https://openalex.org/W2125889680","https://openalex.org/W2133561941","https://openalex.org/W2141558501","https://openalex.org/W2147122181","https://openalex.org/W2149231960","https://openalex.org/W2152094063","https://openalex.org/W2162520939","https://openalex.org/W2175631294","https://openalex.org/W6676396137"],"related_works":["https://openalex.org/W4367365664","https://openalex.org/W4293227618","https://openalex.org/W2136634148","https://openalex.org/W3122851392","https://openalex.org/W3122800671","https://openalex.org/W4250708772","https://openalex.org/W4288862737","https://openalex.org/W2186336397","https://openalex.org/W1984769753","https://openalex.org/W2052474771"],"abstract_inverted_index":{"We":[0,66],"are":[1,115],"now":[2],"witnessing":[3],"the":[4,55,61,109],"rapid":[5],"growth":[6],"of":[7,26,57,63,82,131],"decentralized":[8],"source":[9],"code":[10],"management":[11],"(DSCM)":[12],"systems,":[13],"in":[14,28,75,154,159,168],"which":[15,29],"every":[16],"developer":[17],"has":[18],"her":[19],"own":[20],"repository.":[21,50],"DSCMs":[22,137,169],"facilitate":[23],"a":[24,48,70,146],"style":[25],"collaboration":[27],"work":[30],"output":[31],"can":[32],"flow":[33,105],"sideways":[34],"(and":[35,45],"privately)":[36],"between":[37,106,127],"collaborators,":[38],"rather":[39],"than":[40],"always":[41],"up":[42],"and":[43,60,79,136,172,177],"down":[44],"publicly)":[46],"via":[47],"central":[49],"Decentralization":[51],"comes":[52],"with":[53],"both":[54],"promise":[56],"new":[58,98],"data":[59],"peril":[62],"its":[64],"misinterpretation.":[65],"focus":[67],"on":[68],"git,":[69,83],"very":[71],"popular":[72],"DSCM":[73],"used":[74],"high-profile":[76],"projects.":[77],"Decentralization,":[78],"other":[80,173],"features":[81],"such":[84,100],"as":[85,101,124],"automatically":[86],"recorded":[87],"contributor":[88],"attribution,":[89],"lead":[90],"to":[91,97,108,134,151,164],"richer":[92],"content":[93],"histories,":[94],"giving":[95],"rise":[96],"questions":[99],"ldquoHow":[102],"do":[103],"contributions":[104],"developers":[107,153],"official":[110],"project":[111],"repository?rdquo":[112],"However,":[113],"there":[114],"pitfalls.":[116],"Commits":[117],"may":[118],"be":[119],"reordered,":[120],"deleted,":[121],"or":[122],"edited":[123],"they":[125],"move":[126],"repositories.":[128],"The":[129],"semantics":[130],"terms":[132],"common":[133],"SCMs":[135],"sometimes":[138],"differ":[139],"markedly,":[140],"potentially":[141],"creating":[142],"confusion.":[143],"For":[144],"example,":[145],"commit":[147],"is":[148,163],"immediately":[149],"visible":[150],"all":[152],"centralized":[155],"SCMs,":[156],"but":[157],"not":[158],"DSCMs.":[160],"Our":[161],"goal":[162],"help":[165],"researchers":[166],"interested":[167],"avoid":[170],"these":[171],"perils":[174],"when":[175],"mining":[176],"analyzing":[178],"git":[179],"data.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":34},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
