{"id":"https://openalex.org/W4288080275","doi":"https://doi.org/10.1145/3379597.3387445","title":"Embedding Java Classes with code2vec","display_name":"Embedding Java Classes with code2vec","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W4288080275","doi":"https://doi.org/10.1145/3379597.3387445"},"language":"en","primary_location":{"id":"doi:10.1145/3379597.3387445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387445","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.02942","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078204860","display_name":"Rhys Compton","orcid":null},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Rhys Compton","raw_affiliation_strings":["University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059992863","display_name":"Eibe Frank","orcid":"https://orcid.org/0000-0001-6152-7111"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Eibe Frank","raw_affiliation_strings":["University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056585882","display_name":"Panos Patros","orcid":null},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Panos Patros","raw_affiliation_strings":["University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054372628","display_name":"Abigail Koay","orcid":"https://orcid.org/0000-0002-4130-9931"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Abigail Koay","raw_affiliation_strings":["University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078204860"],"corresponding_institution_ids":["https://openalex.org/I52179390"],"apc_list":null,"apc_paid":null,"fwci":10.2911,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.9823284,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"253"},"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":0.9990000128746033,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9796000123023987,"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/computer-science","display_name":"Computer science","score":0.8505901098251343},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.7274765968322754},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6683921813964844},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6111204624176025},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5527872443199158},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.522876501083374},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5021045207977295},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4951108992099762},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45455941557884216},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4317489266395569},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42213818430900574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3777538239955902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8505901098251343},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.7274765968322754},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6683921813964844},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6111204624176025},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5527872443199158},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.522876501083374},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5021045207977295},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4951108992099762},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45455941557884216},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4317489266395569},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42213818430900574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3777538239955902},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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":2,"locations":[{"id":"doi:10.1145/3379597.3387445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387445","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:2004.02942","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.02942","pdf_url":"https://arxiv.org/pdf/2004.02942","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.02942","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.02942","pdf_url":"https://arxiv.org/pdf/2004.02942","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1529790664","https://openalex.org/W2010065958","https://openalex.org/W2064236088","https://openalex.org/W2157532207","https://openalex.org/W2897961188","https://openalex.org/W2916020270","https://openalex.org/W2951005127","https://openalex.org/W2964150020","https://openalex.org/W2994865335","https://openalex.org/W2995923588"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2749690376","https://openalex.org/W2786317006","https://openalex.org/W4367724653","https://openalex.org/W2345479200","https://openalex.org/W2788563018","https://openalex.org/W2183306018","https://openalex.org/W2997587123","https://openalex.org/W2849310602","https://openalex.org/W4281673905"],"abstract_inverted_index":{"Automatic":[0],"source":[1,37,47,259],"code":[2,12,48,59,193,245,251],"analysis":[3],"in":[4,135,162,166],"key":[5],"areas":[6],"of":[7,29,57,76,129,154,173,179,191,210,221],"software":[8],"engineering,":[9],"such":[10,131],"as":[11,60,62,132],"security,":[13],"can":[14],"benefit":[15],"from":[16],"Machine":[17],"Learning":[18],"(ML).":[19],"However,":[20,87],"many":[21],"standard":[22],"ML":[23,256],"approaches":[24],"require":[25],"a":[26,66,136,180,200,217],"numeric":[27,50],"representation":[28],"data":[30],"and":[31,123,198,241,250],"cannot":[32,124],"be":[33,105],"applied":[34],"directly":[35],"to":[36,40,45,80,84,95,104,118,143,183,186,203,238],"code.":[38,260],"Thus,":[39],"enable":[41],"ML,":[42],"we":[43],"need":[44],"embed":[46,119,125],"into":[49],"feature":[51,85],"vectors":[52],"while":[53],"maintaining":[54],"the":[55,58,73,147,152,163,171,189,192],"semantics":[56],"much":[61],"possible.":[63],"code2vec":[64,90,181],"is":[65,115,235],"recently":[67],"released":[68],"embedding":[69,232],"approach":[70,202],"that":[71,92,226,234],"uses":[72],"proxy":[74],"task":[75],"method":[77,211],"name":[78],"prediction":[79],"map":[81],"Java":[82,121,138,156],"methods":[83,122,130],"vectors.":[86],"experimentation":[88],"with":[89],"shows":[91],"it":[93,103,114,141,185],"learns":[94],"rely":[96,187],"on":[97,188,216,258],"variable":[98,175,228,239],"names":[99,176,197,229],"for":[100,151,254],"prediction,":[101],"causing":[102],"easily":[106],"fooled":[107],"by":[108,207],"typos":[109],"or":[110],"adversarial":[111],"attacks.":[112],"Moreover,":[113],"only":[116],"able":[117],"individual":[120],"an":[126,231],"entire":[127],"collection":[128,220],"those":[133],"present":[134],"typical":[137],"class,":[139],"making":[140],"difficult":[142],"perform":[144],"predictions":[145],"at":[146],"class":[148],"level":[149],"(e.g.,":[150],"identification":[153],"malicious":[155],"classes).":[157],"Both":[158],"shortcomings":[159],"are":[160,252],"addressed":[161],"research":[164,257],"presented":[165],"this":[167],"paper.":[168],"We":[169],"investigate":[170],"effect":[172],"obfuscating":[174,227],"during":[177],"training":[178],"model":[182,233],"force":[184],"structure":[190],"rather":[194],"than":[195],"specific":[196],"consider":[199],"simple":[201],"creating":[204],"class-level":[205],"embeddings":[206],"aggregating":[208],"sets":[209],"embeddings.":[212],"Our":[213],"results,":[214],"obtained":[215],"challenging":[218],"new":[219],"source-code":[222],"classification":[223],"problems,":[224],"indicate":[225],"produces":[230],"both":[236],"impervious":[237],"naming":[240],"more":[242],"accurately":[243],"reflects":[244],"semantics.":[246],"The":[247],"datasets,":[248],"models,":[249],"shared1":[253],"further":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-07-28T00:00:00"}