{"id":"https://openalex.org/W3015109388","doi":"https://doi.org/10.1145/3379597.3387447","title":"Using Large-Scale Anomaly Detection on Code to Improve Kotlin Compiler","display_name":"Using Large-Scale Anomaly Detection on Code to Improve Kotlin Compiler","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3015109388","doi":"https://doi.org/10.1145/3379597.3387447","mag":"3015109388"},"language":"en","primary_location":{"id":"doi:10.1145/3379597.3387447","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387447","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.01618","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Timofey Bryksin","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains Research, Saint Petersburg State University","institution_ids":["https://openalex.org/I172901346"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Victor Petukhov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Victor Petukhov","raw_affiliation_strings":["JetBrains"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ilya Alexin","orcid":null},"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":"Ilya Alexin","raw_affiliation_strings":["Saint Petersburg State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Petersburg State University","institution_ids":["https://openalex.org/I172901346"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stanislav Prikhodko","orcid":null},"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":"Stanislav Prikhodko","raw_affiliation_strings":["Saint Petersburg State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Petersburg State University","institution_ids":["https://openalex.org/I172901346"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alexey Shpilman","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":"Alexey Shpilman","raw_affiliation_strings":["JetBrains Research, Higher School of Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains Research, Higher School of Economics","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vladimir Kovalenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Kovalenko","raw_affiliation_strings":["JetBrains Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains Research,","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Nikita Povarov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Povarov","raw_affiliation_strings":["JetBrains"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JetBrains","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9494,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89346024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"455","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9977999925613403,"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/bytecode","display_name":"Bytecode","score":0.607200026512146},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6069999933242798},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5982999801635742},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5275999903678894},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5236999988555908},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.48910000920295715},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.42910000681877136},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4235000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276000022888184},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.8062999844551086},{"id":"https://openalex.org/C2779818221","wikidata":"https://www.wikidata.org/wiki/Q837330","display_name":"Bytecode","level":3,"score":0.607200026512146},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5982999801635742},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5275999903678894},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.48910000920295715},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C2777472213","wikidata":"https://www.wikidata.org/wiki/Q137496","display_name":"Java bytecode","level":5,"score":0.3621000051498413},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C50951305","wikidata":"https://www.wikidata.org/wiki/Q2482534","display_name":"Unreachable code","level":5,"score":0.29910001158714294},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C33857546","wikidata":"https://www.wikidata.org/wiki/Q80006","display_name":"Computer programming","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3379597.3387447","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387447","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:2004.01618","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.01618","pdf_url":"https://arxiv.org/pdf/2004.01618","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:2004.01618","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.01618","pdf_url":"https://arxiv.org/pdf/2004.01618","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":18,"referenced_works":["https://openalex.org/W51582649","https://openalex.org/W1485912969","https://openalex.org/W1673310716","https://openalex.org/W1968788085","https://openalex.org/W1995443851","https://openalex.org/W2025677988","https://openalex.org/W2096657610","https://openalex.org/W2099581008","https://openalex.org/W2102632804","https://openalex.org/W2122646361","https://openalex.org/W2122992911","https://openalex.org/W2123840312","https://openalex.org/W2128782367","https://openalex.org/W2143119899","https://openalex.org/W2514538448","https://openalex.org/W2605284977","https://openalex.org/W2883359218","https://openalex.org/W4238083723"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,78],"work,":[2],"we":[3,80],"apply":[4],"anomaly":[5,25,150],"detection":[6,105,151],"to":[7,12,48,72,93,103,119],"source":[8,98],"code":[9,28,35,44,99,110],"and":[10,20,52,90,100,102,128,149,153,159,171],"byte-code":[11],"facilitate":[13],"the":[14,62,84,104,136,168,172],"development":[15],"of":[16,97,106,123,147,156],"a":[17,27,38,115],"programming":[18,40,86],"language":[19,50,75,163,180],"its":[21],"compiler.":[22],"We":[23,88,139,165],"define":[24],"as":[26,83],"fragment":[29],"that":[30,117,132,143,167],"is":[31,46],"different":[32,145],"from":[33],"typical":[34],"written":[36],"in":[37,74,135],"particular":[39],"language.":[41,87],"Identifying":[42],"such":[43],"fragments":[45],"beneficial":[47],"both":[49],"developers":[51],"end":[53],"users,":[54],"since":[55],"anomalies":[56,69,107,127,131,158,170],"may":[57],"indicate":[58],"potential":[59],"issues":[60],"with":[61,65],"compiler":[63],"or":[64],"runtime":[66],"performance.":[67],"Moreover,":[68],"could":[70],"correspond":[71],"problems":[73],"design.":[76],"For":[77],"study,":[79],"choose":[81],"Kotlin":[82],"target":[85],"outline":[89],"discuss":[91,154],"approaches":[92],"obtaining":[94],"vector":[95],"representations":[96],"bytecode":[101],"across":[108],"vectorized":[109],"snippets.":[111],"The":[112],"paper":[113],"presents":[114],"method":[116],"aims":[118],"detect":[120],"two":[121],"types":[122,155],"anomalies:":[124],"syntax":[125],"tree":[126],"so-called":[129],"compiler-induced":[130],"arise":[133],"only":[134],"compiled":[137],"bytecode.":[138],"describe":[140],"several":[141],"experiments":[142],"employ":[144],"combinations":[146],"vectorization":[148],"techniques":[152],"detected":[157],"their":[160],"usefulness":[161],"for":[162,179],"developers.":[164],"demonstrate":[166],"extracted":[169],"underlying":[173],"extraction":[174],"technique":[175],"provide":[176],"additional":[177],"value":[178],"development.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2020-04-10T00:00:00"}