{"id":"https://openalex.org/W2529650839","doi":"https://doi.org/10.1007/s10664-016-9461-5","title":"The Debsources Dataset: two decades of free and open source software","display_name":"The Debsources Dataset: two decades of free and open source software","publication_year":2016,"publication_date":"2016-10-07","ids":{"openalex":"https://openalex.org/W2529650839","doi":"https://doi.org/10.1007/s10664-016-9461-5","mag":"2529650839"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-016-9461-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-016-9461-5","pdf_url":null,"source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10664-016-9461-5","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082059069","display_name":"Matthieu Caneill","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Caneill","raw_affiliation_strings":["Universit\u00e9 Grenoble Alpes, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]},{"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. Germ\u00e1n","raw_affiliation_strings":["University of Victoria, Victoria, Canada"],"affiliations":[{"raw_affiliation_string":"University of Victoria, Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006129685","display_name":"Stefano Zacchiroli","orcid":"https://orcid.org/0000-0002-4576-136X"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I169173203","display_name":"D\u00e9l\u00e9gation Paris 7","ror":"https://ror.org/00bw5n526","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488","https://openalex.org/I169173203"]},{"id":"https://openalex.org/I4210091437","display_name":"Sorbonne Paris Cit\u00e9","ror":"https://ror.org/001z21q04","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210091437"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Stefano Zacchiroli","raw_affiliation_strings":["Inria, Paris, France","Sorbonne Paris Cit\u00e9, IRIF, UMR 8243, CNRS, Universit\u00e9 Paris Diderot, 75205, Paris, France","Sorbonne Paris Cit\u00e9, IRIF, UMR 8243, CNRS, Universit\u00e9 Paris Diderot, Paris, France"],"affiliations":[{"raw_affiliation_string":"Inria, Paris, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Sorbonne Paris Cit\u00e9, IRIF, UMR 8243, CNRS, Universit\u00e9 Paris Diderot, 75205, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I169173203","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Sorbonne Paris Cit\u00e9, IRIF, UMR 8243, CNRS, Universit\u00e9 Paris Diderot, Paris, France","institution_ids":["https://openalex.org/I169173203","https://openalex.org/I4210091437","https://openalex.org/I204730241","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006129685"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I169173203","https://openalex.org/I204730241","https://openalex.org/I4210091437"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":5.3078,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95787241,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"3","first_page":"1405","last_page":"1437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9986000061035156,"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":0.9986000061035156,"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":0.998199999332428,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7992731928825378},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7558399438858032},{"id":"https://openalex.org/keywords/checksum","display_name":"Checksum","score":0.7338240146636963},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6999953389167786},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.6886984705924988},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5378344058990479},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5164694786071777},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.5041381120681763},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4869750440120697},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.4750773310661316},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4704248905181885},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.44053882360458374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.439716100692749},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3812897503376007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33004066348075867},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.279118150472641},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22506296634674072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992731928825378},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7558399438858032},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.7338240146636963},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6999953389167786},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.6886984705924988},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5378344058990479},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5164694786071777},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.5041381120681763},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4869750440120697},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.4750773310661316},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4704248905181885},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.44053882360458374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.439716100692749},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3812897503376007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33004066348075867},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.279118150472641},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22506296634674072}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10664-016-9461-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-016-9461-5","pdf_url":null,"source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10664-016-9461-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-016-9461-5","pdf_url":null,"source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W122154057","https://openalex.org/W296482857","https://openalex.org/W1739451848","https://openalex.org/W1983565008","https://openalex.org/W1989479444","https://openalex.org/W1992218759","https://openalex.org/W1995709637","https://openalex.org/W2016522855","https://openalex.org/W2021963610","https://openalex.org/W2027370816","https://openalex.org/W2037786492","https://openalex.org/W2042019816","https://openalex.org/W2045749853","https://openalex.org/W2049158239","https://openalex.org/W2050136587","https://openalex.org/W2052823280","https://openalex.org/W2063696749","https://openalex.org/W2112606801","https://openalex.org/W2152759400","https://openalex.org/W2164215197","https://openalex.org/W4232126833","https://openalex.org/W4232691406","https://openalex.org/W4234659140","https://openalex.org/W4236003219","https://openalex.org/W4247858078"],"related_works":["https://openalex.org/W2986478207","https://openalex.org/W4312706861","https://openalex.org/W2113128227","https://openalex.org/W2061990085","https://openalex.org/W2169022535","https://openalex.org/W4225687299","https://openalex.org/W2992772838","https://openalex.org/W4311938462","https://openalex.org/W4390042077","https://openalex.org/W2529650839"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,23,26,128,143,162,174,177],"Debsources":[3,90,129,167],"Dataset:":[4],"source":[5,38,76,101,110],"code":[6,39,77,102],"and":[7,15,83,136,182],"related":[8],"metadata":[9,43],"spanning":[10],"two":[11,164],"decades":[12],"of":[13,25,37,51,71,96,142,145,157,161,176],"Free":[14],"Open":[16,170],"Source":[17],"Software":[18],"(FOSS)":[19],"history,":[20],"seen":[21],"through":[22],"lens":[24],"Debian":[27,146],"distribution.":[28],"The":[29,89,166],"dataset":[30],"spans":[31],"more":[32],"than":[33],"3":[34],"billion":[35],"lines":[36],"as":[40,42,93],"well":[41],"about":[44],"them":[45],"such":[46],"as:":[47],"size":[48],"metrics":[49],"(lines":[50],"code,":[52],"disk":[53],"usage),":[54],"developer-defined":[55],"symbols":[56],"(ctags),":[57],"file-level":[58],"checksums":[59,108],"(SHA1,":[60],"SHA256,":[61],"TLSH),":[62],"file":[63],"media":[64],"types":[65],"(MIME),":[66],"release":[67],"information":[68,85],"(which":[69],"version":[70],"which":[72,75],"package":[73],"containing":[74,98],"files":[78,103],"has":[79],"been":[80],"released":[81,172],"when),":[82],"license":[84],"(GPL,":[86],"BSD,":[87],"etc).":[88],"Dataset":[91,130,168],"comes":[92],"a":[94,113,155],"set":[95],"tarballs":[97],"deduplicated":[99],"unique":[100],"organized":[104],"by":[105],"their":[106],"SHA1":[107],"(the":[109,118],"code),":[111],"plus":[112],"portable":[114],"PostgreSQL":[115],"database":[116],"dump":[117],"metadata).":[119],"A":[120],"case":[121],"study":[122],"is":[123,169],"run":[124],"to":[125,134],"show":[126],"how":[127],"can":[131],"be":[132],"used":[133],"easily":[135],"efficiently":[137],"instrument":[138],"very":[139],"long-term":[140],"analyses":[141],"evolution":[144],"from":[147,186],"various":[148],"angles":[149],"(size,":[150],"granularity,":[151],"licensing,":[152],"etc.),":[153],"getting":[154],"grasp":[156],"major":[158],"FOSS":[159],"trends":[160],"past":[163],"decades.":[165],"Data,":[171],"under":[173],"terms":[175],"CC":[178],"BY-SA":[179],"4.0":[180],"license,":[181],"available":[183],"for":[184],"download":[185],"Zenodo":[187],"with":[188],"DOI":[189],"reference":[190],"10.5281/zenodo.61089.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
