{"id":"https://openalex.org/W4288079288","doi":"https://doi.org/10.1145/3379597.3387510","title":"The Software Heritage Graph Dataset","display_name":"The Software Heritage Graph Dataset","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W4288079288","doi":"https://doi.org/10.1145/3379597.3387510"},"language":"en","primary_location":{"id":"doi:10.1145/3379597.3387510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International 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/A5074999005","display_name":"Antoine Pietri","orcid":"https://orcid.org/0000-0003-4052-4469"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Pietri","raw_affiliation_strings":["Inria, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021948425","display_name":"Diomidis Spinellis","orcid":"https://orcid.org/0000-0003-4231-1897"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Diomidis Spinellis","raw_affiliation_strings":["Athens University of Economics and Business, Athens, Greece","AUEB - Athens University of Economics and Business (Patision 76, 10434, Athens - Greece)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business, Athens, Greece","institution_ids":["https://openalex.org/I73142707"]},{"raw_affiliation_string":"AUEB - Athens University of Economics and Business (Patision 76, 10434, Athens - Greece)","institution_ids":["https://openalex.org/I73142707"]}]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefano Zacchiroli","raw_affiliation_strings":["Universit\u00e9 de Paris and Inria, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris and Inria, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0449,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88751808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9987999796867371,"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":0.9923999905586243,"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":0.7943998575210571},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6256570219993591},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6068245768547058},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.5064159631729126},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4661959707736969},{"id":"https://openalex.org/keywords/backporting","display_name":"Backporting","score":0.45720842480659485},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4503244459629059},{"id":"https://openalex.org/keywords/software-evolution","display_name":"Software evolution","score":0.4153730571269989},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3969520032405853},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39211973547935486},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39099323749542236},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.3608589470386505},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3437155485153198},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2520843744277954},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1718977391719818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943998575210571},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6256570219993591},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6068245768547058},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.5064159631729126},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4661959707736969},{"id":"https://openalex.org/C21491501","wikidata":"https://www.wikidata.org/wiki/Q430253","display_name":"Backporting","level":5,"score":0.45720842480659485},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4503244459629059},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.4153730571269989},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3969520032405853},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39211973547935486},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39099323749542236},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.3608589470386505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3437155485153198},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2520843744277954},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1718977391719818},{"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":1,"locations":[{"id":"doi:10.1145/3379597.3387510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1994727615","https://openalex.org/W2039473157","https://openalex.org/W2082773934","https://openalex.org/W2086906616","https://openalex.org/W2491983741","https://openalex.org/W2542459869","https://openalex.org/W2733373979","https://openalex.org/W2748800886","https://openalex.org/W2893990175","https://openalex.org/W2954266827","https://openalex.org/W2964150020","https://openalex.org/W4248468553"],"related_works":["https://openalex.org/W2380017313","https://openalex.org/W2366623749","https://openalex.org/W3130837735","https://openalex.org/W2359702179","https://openalex.org/W3186869374","https://openalex.org/W2144604715","https://openalex.org/W2287452355","https://openalex.org/W2134420764","https://openalex.org/W2387767950","https://openalex.org/W2026093893"],"abstract_inverted_index":{"Software":[0,84],"Heritage":[1,85],"is":[2,91],"the":[3,109],"largest":[4],"existing":[5],"public":[6,113],"archive":[7],"of":[8,75,95,105,112,117],"software":[9,37,40,114],"source":[10,23,67],"code":[11,24,68],"and":[12,26,52,59,72,97,99],"accompanying":[13],"development":[14,47],"history.":[15],"It":[16],"spans":[17],"more":[18,33],"than":[19,34],"five":[20],"billion":[21,28],"unique":[22,29,92],"files":[25],"one":[27],"commits,":[30,71],"coming":[31],"from":[32,44],"80":[35],"million":[36],"projects.":[38],"These":[39],"artifacts":[41],"were":[42],"retrieved":[43],"major":[45],"collaborative":[46],"platforms":[48],"(e.g.,":[49,55],"GitHub,":[50],"GitLab)":[51],"package":[53],"repositories":[54,80,123],"PyPI,":[56],"Debian,":[57],"NPM),":[58],"stored":[60],"in":[61,93],"a":[62,103],"uniform":[63],"representation":[64],"linking":[65],"together":[66],"files,":[69],"directories,":[70],"full":[73],"snapshots":[74],"version":[76],"control":[77],"systems":[78],"(VCS)":[79],"as":[81,124],"observed":[82],"by":[83],"during":[86],"periodic":[87],"crawls.":[88],"This":[89],"dataset":[90],"terms":[94],"accessibility":[96],"scale,":[98],"allows":[100],"to":[101],"explore":[102],"number":[104],"research":[106],"questions":[107],"on":[108,120],"long":[110],"tail":[111],"development,":[115],"instead":[116],"solely":[118],"focusing":[119],"\"most":[121],"starred\"":[122],"it":[125],"often":[126],"happens.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-07-28T00:00:00"}
