{"id":"https://openalex.org/W3005685668","doi":"https://doi.org/10.1145/3379597.3387455","title":"A Study of Potential Code Borrowing and License Violations in Java Projects on GitHub","display_name":"A Study of Potential Code Borrowing and License Violations in Java Projects on GitHub","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3005685668","doi":"https://doi.org/10.1145/3379597.3387455","mag":"3005685668"},"language":"en","primary_location":{"id":"doi:10.1145/3379597.3387455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387455","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.05237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013316832","display_name":"Yaroslav Golubev","orcid":"https://orcid.org/0000-0001-7009-635X"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yaroslav Golubev","raw_affiliation_strings":["JetBrains Research, ITMO University","JetBrains Research ITMO University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains Research, ITMO University","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"JetBrains Research ITMO University","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003885993","display_name":"Maria Eliseeva","orcid":null},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Maria Eliseeva","raw_affiliation_strings":["Higher School of Economics","[Higher School of Economics]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Higher School of Economics","institution_ids":["https://openalex.org/I118501908"]},{"raw_affiliation_string":"[Higher School of Economics]","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081382143","display_name":"Nikita Povarov","orcid":"https://orcid.org/0000-0003-4894-0598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Povarov","raw_affiliation_strings":["JetBrains"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065316896","display_name":"Timofey Bryksin","orcid":"https://orcid.org/0000-0001-9022-3563"},"institutions":[{"id":"https://openalex.org/I172901346","display_name":"St Petersburg University","ror":"https://ror.org/023znxa73","country_code":"RU","type":"education","lineage":["https://openalex.org/I172901346"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Timofey Bryksin","raw_affiliation_strings":["JetBrains Research, Saint Petersburg State University","JetBrains Research, Saint-Petersburg State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains Research, Saint Petersburg State University","institution_ids":["https://openalex.org/I172901346"]},{"raw_affiliation_string":"JetBrains Research, Saint-Petersburg State University","institution_ids":["https://openalex.org/I172901346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2785,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62309855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/license","display_name":"License","score":0.8576170206069946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7919126749038696},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.73953777551651},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.7004823684692383},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6812468767166138},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6392512321472168},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6015967726707458},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.5954943895339966},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4742005467414856},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4698447585105896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4348142147064209},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.410483717918396},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38006460666656494},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36610472202301025},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20820140838623047},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.20159912109375},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.0713283121585846}],"concepts":[{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.8576170206069946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919126749038696},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.73953777551651},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.7004823684692383},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6812468767166138},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6392512321472168},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6015967726707458},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.5954943895339966},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4742005467414856},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4698447585105896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4348142147064209},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.410483717918396},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38006460666656494},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36610472202301025},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20820140838623047},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.20159912109375},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0713283121585846},{"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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3379597.3387455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387455","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"},{"id":"pmh:oai:arXiv.org:2002.05237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05237","pdf_url":"https://arxiv.org/pdf/2002.05237","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"mag:3005685668","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2002.05237","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.05237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.05237","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.05237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05237","pdf_url":"https://arxiv.org/pdf/2002.05237","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3005685668.pdf","grobid_xml":"https://content.openalex.org/works/W3005685668.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1975770691","https://openalex.org/W1992218759","https://openalex.org/W2002841430","https://openalex.org/W2024900230","https://openalex.org/W2027370816","https://openalex.org/W2029181676","https://openalex.org/W2041190309","https://openalex.org/W2055774542","https://openalex.org/W2056830820","https://openalex.org/W2063696749","https://openalex.org/W2069859158","https://openalex.org/W2098230348","https://openalex.org/W2098347799","https://openalex.org/W2099154878","https://openalex.org/W2099677903","https://openalex.org/W2106950567","https://openalex.org/W2109943392","https://openalex.org/W2132944054","https://openalex.org/W2134329651","https://openalex.org/W2136128399","https://openalex.org/W2154197043","https://openalex.org/W2165739648","https://openalex.org/W2559532455","https://openalex.org/W2610548325","https://openalex.org/W2730498790","https://openalex.org/W2762844179","https://openalex.org/W2775209903","https://openalex.org/W2887906052","https://openalex.org/W2993280551","https://openalex.org/W3105685701","https://openalex.org/W3106502818","https://openalex.org/W4247858078","https://openalex.org/W4300007223"],"related_works":["https://openalex.org/W3089853590","https://openalex.org/W2029181676","https://openalex.org/W2559532455","https://openalex.org/W2402241391","https://openalex.org/W2063696749","https://openalex.org/W2209934102","https://openalex.org/W2548636867","https://openalex.org/W2046541848","https://openalex.org/W1525478949","https://openalex.org/W2791776396","https://openalex.org/W2795251638","https://openalex.org/W2469415976","https://openalex.org/W2099154878","https://openalex.org/W3202705250","https://openalex.org/W2801496046","https://openalex.org/W3181400453","https://openalex.org/W3091454237","https://openalex.org/W2928487989","https://openalex.org/W3123068371","https://openalex.org/W2730498790"],"abstract_inverted_index":{"With":[0],"an":[1,45,61],"ever-increasing":[2],"amount":[3],"of":[4,9,23,28,48,64,74,84,97,106,122,125,133,148,155,166],"open-source":[5,24],"software,":[6,25],"the":[7,21,26,32,72,90,120],"popularity":[8,86],"services":[10],"like":[11],"GitHub":[12],"that":[13,153],"facilitate":[14],"code":[15,33,57,66,75,127,162],"reuse,":[16],"and":[17,37,59,68,103,110,116,164],"common":[18],"misconceptions":[19],"about":[20],"licensing":[22,121],"problem":[27,92],"license":[29,69,135,143],"violations":[30,70,144],"in":[31,87,114,119,145,160],"is":[34,93],"getting":[35],"more":[36,38],"prominent.":[39],"In":[40],"this":[41],"study,":[42],"we":[43,150],"compile":[44],"extensive":[46],"corpus":[47],"popular":[49],"Java":[50,79],"projects":[51],"from":[52],"GitHub,":[53],"search":[54],"it":[55],"for":[56],"clones,":[58],"perform":[60],"original":[62,171],"analysis":[63],"possible":[65,98,134,142],"borrowing":[67,128,163],"on":[71],"level":[73],"fragments.":[76],"We":[77,101],"chose":[78],"as":[80],"a":[81],"language":[82],"because":[83,96],"its":[85],"industry,":[88],"where":[89],"plagiarism":[91],"especially":[94],"relevant":[95],"legal":[99],"action.":[100],"analyze":[102],"discuss":[104],"distribution":[105,124],"94":[107],"different":[108],"discovered":[109,152],"manually":[111],"evaluated":[112],"licenses":[113],"files":[115],"projects,":[117],"differences":[118],"files,":[123],"potential":[126,161],"between":[129],"licenses,":[130,139],"various":[131],"types":[132],"violations,":[136],"most":[137],"violated":[138],"etc.":[140],"Studying":[141],"specific":[146],"blocks":[147],"code,":[149],"have":[151],"29.6%":[154],"them":[156,167],"might":[157],"be":[158],"involved":[159],"9.4%":[165],"could":[168],"potentially":[169],"violate":[170],"licenses.":[172]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
