{"id":"https://openalex.org/W3209931987","doi":"https://doi.org/10.5281/zenodo.2583978","title":"The Software Heritage Graph Dataset","display_name":"The Software Heritage Graph Dataset","publication_year":2019,"publication_date":"2019-03-05","ids":{"openalex":"https://openalex.org/W3209931987","doi":"https://doi.org/10.5281/zenodo.2583978","mag":"3209931987"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:2583978","is_oa":true,"landing_page_url":"https://zenodo.org/record/2583978","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/2583978","any_repository_has_fulltext":true},"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":"Pietri, Antoine","raw_affiliation_strings":["Inria, France"],"raw_orcid":"https://orcid.org/0000-0003-4052-4469","affiliations":[{"raw_affiliation_string":"Inria, 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":"Spinellis, Diomidis","raw_affiliation_strings":["Athens University of Economics and Business, Greece"],"raw_orcid":"https://orcid.org/0000-0003-4231-1897","affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business, 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/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/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":"Zacchiroli, Stefano","raw_affiliation_strings":["University Paris Diderot and Inria, France"],"raw_orcid":"https://orcid.org/0000-0002-4576-136X","affiliations":[{"raw_affiliation_string":"University Paris Diderot and Inria, France","institution_ids":["https://openalex.org/I169173203","https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9962000250816345,"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/T10260","display_name":"Software Engineering Research","score":0.9635000228881836,"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":0.9598000049591064,"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":0.5647802948951721},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5300953984260559},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48731669783592224},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17706423997879028},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15280300378799438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5647802948951721},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5300953984260559},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48731669783592224},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17706423997879028},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15280300378799438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:2583978","is_oa":true,"landing_page_url":"https://zenodo.org/record/2583978","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.2583978","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2583978","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:2583978","is_oa":true,"landing_page_url":"https://zenodo.org/record/2583978","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Software":[0,43,54,87,137,182,220,242],"Heritage":[1,44,55,88,138,183,221],"is":[2,41,116,141],"the":[3,42,53,78,134,176,181,188,192,209,260,266],"largest":[4],"existing":[5],"public":[6,161],"archive":[7,189],"of":[8,52,81,194,233],"software":[9,38,225],"source<br>":[10],"code":[11,25,65,128],"and":[12,27,108,123,150,191,268],"accompanying":[13],"development":[14,98,226],"history:":[15],"it":[16],"currently":[17],"spans":[18],"more":[19,34,264],"than":[20,35],"five<br>":[21],"billion":[22,29],"unique":[23,30],"source":[24,64,127],"files":[26,153],"one":[28,228],"commits,":[31],"coming":[32],"from<br>":[33],"80":[36],"million":[37],"projects.":[39],"This":[40],"graph":[45,139],"dataset:":[46],"a":[47],"fully-deduplicated<br>":[48],"Merkle":[49],"DAG":[50],"representation":[51],"archive.":[56],"The":[57,136,236],"dataset":[58,140,203,267],"links<br>":[59],"together":[60],"file":[61],"content":[62],"identifiers,":[63],"directories,":[66],"Version":[67],"Control<br>":[68],"System":[69],"(VCS)":[70],"commits":[71],"tracking":[72],"evolution":[73],"over":[74],"time,":[75],"up":[76],"to":[77,259],"full":[79],"states":[80],"VCS<br>":[82],"repositories":[83],"as":[84,157,159],"observed":[85,132],"by":[86],"during":[89],"periodic":[90],"crawls.":[91],"The<br>":[92],"dataset\u2019s":[93],"contents":[94],"come":[95],"from":[96],"major":[97],"forges":[99],"(including":[100],"GitHub":[101],"and<br>":[102],"GitLab),":[103],"FOSS":[104],"distributions":[105],"(e.g.,":[106,112],"Debian),":[107],"language-specific":[109],"package<br>":[110],"managers":[111],"PyPI).":[113],"Crawling":[114],"information":[115,265],"also":[117,257],"included,":[118],"providing<br>":[119],"timestamps":[120],"about":[121],"when":[122],"where":[124],"all":[125],"archived":[126],"artifacts":[129],"have":[130],"been<br>":[131],"in":[133,143],"wild.":[135],"available":[142],"multiple":[144],"formats,":[145],"including<br>":[146],"downloadable":[147],"CSV":[148],"dumps":[149],"Apache":[151],"Parquet":[152],"for":[154,169,186,196,204,263],"local":[155],"use,":[156],"well":[158],"a<br>":[160],"instance":[162],"on":[163,240],"Amazon":[164],"Athena":[165],"interactive":[166],"query":[167],"service":[168],"ready-to-use<br>":[170],"powerful":[171],"analytical":[172],"processing.":[173],"By":[174],"accessing":[175],"dataset,":[177],"you":[178,200],"agree":[179],"with":[180,249],"Ethical":[184],"Charter<br>":[185],"using":[187],"data,":[190],"terms":[193],"use":[195,201],"bulk":[197],"access.":[198],"If":[199],"this":[202],"research":[205],"purposes,":[206],"please":[207],"cite":[208],"following":[210],"paper:":[211],"Antoine":[212],"Pietri,":[213],"Diomidis":[214],"Spinellis,":[215],"Stefano":[216],"Zacchiroli.":[217],"<br>":[218,230,252],"<em>The":[219],"Graph":[222],"Dataset:":[223],"Public":[224],"under":[227],"roof</em>.":[229],"In":[231],"proceedings":[232],"MSR":[234],"2019:":[235],"16th":[237],"International":[238],"Conference":[239],"Mining":[241],"Repositories,":[243],"May":[244],"2019,":[245],"Montreal,":[246],"Canada.":[247],"Co-located":[248],"ICSE":[250],"2019.":[251],"preprint,":[253],"bibtex":[254],"You":[255],"can":[256],"refer":[258],"above":[261],"paper":[262],"sample":[269],"queries.":[270]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
