{"id":"https://openalex.org/W2115052242","doi":"https://doi.org/10.1109/msr.2009.5069501","title":"SourcererDB: An aggregated repository of statically analyzed and cross-linked open source Java projects","display_name":"SourcererDB: An aggregated repository of statically analyzed and cross-linked open source Java projects","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2115052242","doi":"https://doi.org/10.1109/msr.2009.5069501","mag":"2115052242"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2009.5069501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069501","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/A5072825080","display_name":"Joel Ossher","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joel Ossher","raw_affiliation_strings":["Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","Bren School of Information and Computer Sciences, University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010166020","display_name":"Sushil Bajracharya","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sushil Bajracharya","raw_affiliation_strings":["Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","Bren School of Information and Computer Sciences, University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059418584","display_name":"Erik Linstead","orcid":"https://orcid.org/0000-0003-0174-7002"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Linstead","raw_affiliation_strings":["Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","Bren School of Information and Computer Sciences, University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088813478","display_name":"Pierre Baldi","orcid":"https://orcid.org/0000-0001-8752-4664"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierre Baldi","raw_affiliation_strings":["Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","Bren School of Information and Computer Sciences, University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103284742","display_name":"Cristina Videira Lopes","orcid":"https://orcid.org/0000-0003-0551-3908"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristina Lopes","raw_affiliation_strings":["Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","Bren School of Information and Computer Sciences, University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Bren School of Information and Computer Sciences, University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072825080"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":16.3023,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.98854957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9728000164031982,"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/computer-science","display_name":"Computer science","score":0.8346002101898193},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.8275550603866577},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6710526347160339},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5444151759147644},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.505828857421875},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.48478978872299194},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.46784576773643494},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.45367878675460815},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.4523053467273712},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4354836940765381},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.415094256401062},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3842526078224182},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.36202794313430786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346002101898193},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.8275550603866577},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6710526347160339},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5444151759147644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.505828857421875},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.48478978872299194},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.46784576773643494},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.45367878675460815},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.4523053467273712},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4354836940765381},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.415094256401062},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3842526078224182},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36202794313430786},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msr.2009.5069501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2009.5069501","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:10.1.1.395.7512","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.7512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~lopes/documents/msr 09 sourcerer/IEEEXplore-13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1991945471","https://openalex.org/W2029722359","https://openalex.org/W2091543920","https://openalex.org/W2108505327","https://openalex.org/W2119301379","https://openalex.org/W2130267307","https://openalex.org/W2166019458","https://openalex.org/W2169952536","https://openalex.org/W3152035904","https://openalex.org/W4247560582","https://openalex.org/W4285719527","https://openalex.org/W6684061036"],"related_works":["https://openalex.org/W4312691020","https://openalex.org/W2597601979","https://openalex.org/W4376877853","https://openalex.org/W194942058","https://openalex.org/W2991900792","https://openalex.org/W2113128227","https://openalex.org/W2491403535","https://openalex.org/W632256878","https://openalex.org/W2104915799","https://openalex.org/W4311938462"],"abstract_inverted_index":{"The":[0],"open":[1,93],"source":[2,9,43,94,192],"movement":[3],"has":[4],"made":[5],"vast":[6],"quantities":[7],"of":[8,47,88,101,166,191,198,207],"code":[10,44,193],"available":[11],"online":[12],"for":[13,20,51,142,156,170],"free,":[14],"providing":[15],"an":[16,85],"extremely":[17],"large":[18],"dataset":[19,177,190],"empirical":[21,52],"study":[22],"and":[23,54,62,75,91,109,139,158,167,174,201,205],"potential":[24,32],"resuse.":[25],"A":[26],"major":[27],"difficulty":[28],"in":[29,72,125,132,182],"exploiting":[30],"this":[31,80],"fully":[33],"is":[34,122,185],"that":[35],"the":[36,133,154,164,168,171,196],"data":[37,200],"are":[38,49,64,113,137],"currently":[39],"scattered":[40],"between":[41],"competing":[42],"repositories,":[45],"none":[46],"which":[48,121],"structured":[50],"analysis":[53],"cross-project":[55,143,161],"comparison.":[56],"As":[57],"a":[58,126,188],"result,":[59],"software":[60],"researchers":[61],"developers":[63],"left":[65],"to":[66,116,130,146,186,194,202],"compile":[67],"their":[68],"own":[69],"datasets,":[70],"resulting":[71],"duplicated":[73],"effort":[74],"limited":[76],"results.":[77],"To":[78],"address":[79],"challenge,":[81],"we":[82],"built":[83],"SourcererDB,":[84],"aggregated":[86],"repository":[87],"statically":[89,114],"analyzed":[90,115],"cross-linked":[92],"Java":[95,103],"projects.":[96],"SourcererDB":[97,172,184],"contains":[98],"local":[99],"snapshots":[100],"2,852":[102],"projects":[104,112],"taken":[105],"from":[106],"Sourceforge,":[107],"Apache":[108],"Java.net.":[110],"These":[111],"extract":[117],"rich":[118,189],"structural":[119],"information,":[120],"then":[123],"stored":[124],"relational":[127],"database.":[128],"References":[129],"entities":[131],"16,058":[134],"external":[135],"jars":[136],"resolved":[138],"grouped,":[140],"allowing":[141],"usage":[144],"information":[145],"be":[147],"accessed":[148],"easily.":[149],"This":[150],"paper":[151],"describes:":[152],"(a)":[153],"mechanism":[155],"resolving":[157],"grouping":[159],"these":[160],"references,":[162],"(b)":[163],"structure":[165],"metamodel":[169],"repository,":[173],"(d)":[175],"end-user":[176],"access":[178],"mechanisms.":[179],"Our":[180],"goal":[181],"building":[183],"provide":[187],"facilitate":[195],"sharing":[197],"extracted":[199],"encourage":[203],"reuse":[204],"repeatability":[206],"experiments.":[208]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
