{"id":"https://openalex.org/W4313563720","doi":"https://doi.org/10.1145/3551349.3561165","title":"Generalizability of Code Clone Detection on CodeBERT","display_name":"Generalizability of Code Clone Detection on CodeBERT","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4313563720","doi":"https://doi.org/10.1145/3551349.3561165"},"language":"en","primary_location":{"id":"doi:10.1145/3551349.3561165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3561165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3561165","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3561165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071262516","display_name":"Tim Sonnekalb","orcid":"https://orcid.org/0000-0002-0067-1790"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tim Sonnekalb","raw_affiliation_strings":["Institute of Datascience, German Aerospace Center (DLR), Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Datascience, German Aerospace Center (DLR), Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012533726","display_name":"Bernd Gruner","orcid":"https://orcid.org/0000-0002-4177-2993"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Gruner","raw_affiliation_strings":["Institute of Datascience, German Aerospace Center (DLR), Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Datascience, German Aerospace Center (DLR), Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055950864","display_name":"Clemens-Alexander Brust","orcid":"https://orcid.org/0000-0001-5419-1998"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clemens-Alexander Brust","raw_affiliation_strings":["Institute of Datascience, German Aerospace Center (DLR), Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Datascience, German Aerospace Center (DLR), Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063243817","display_name":"Patrick M\u00e4der","orcid":"https://orcid.org/0000-0001-6871-2707"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick M\u00e4der","raw_affiliation_strings":["Technische Universit\u00e4t Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Ilmenau, Germany","institution_ids":["https://openalex.org/I119449181"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071262516"],"corresponding_institution_ids":["https://openalex.org/I2898391981"],"apc_list":null,"apc_paid":null,"fwci":4.2421,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94888015,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"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":0.972000002861023,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9714999794960022,"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/generalizability-theory","display_name":"Generalizability theory","score":0.8002310991287231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582414746284485},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.7345414757728577},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6706053018569946},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6331930160522461},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5135636329650879},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.47133350372314453},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09713113307952881},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07776963710784912},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0616585910320282},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.05448955297470093}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8002310991287231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582414746284485},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.7345414757728577},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6706053018569946},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6331930160522461},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5135636329650879},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.47133350372314453},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09713113307952881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07776963710784912},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0616585910320282},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.05448955297470093},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3551349.3561165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3561165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3561165","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:www.db-thueringen.de:dbt_mods_00061512","is_oa":true,"landing_page_url":"https://www.db-thueringen.de/receive/dbt_mods_00061512","pdf_url":"https://www.db-thueringen.de/servlets/MCRFileNodeServlet/dbt_derivate_00063941/978-1-4503-9475-8_2022_143.pdf","source":{"id":"https://openalex.org/S4306400120","display_name":"Common Library Network (Der Gemeinsame Bibliotheksverbund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210149878","host_organization_name":"Verbundzentrale des GBV","host_organization_lineage":["https://openalex.org/I4210149878"],"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":"chapter"}],"best_oa_location":{"id":"doi:10.1145/3551349.3561165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551349.3561165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551349.3561165","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313563720.pdf","grobid_xml":"https://content.openalex.org/works/W4313563720.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2065053490","https://openalex.org/W2158439356","https://openalex.org/W2578208870","https://openalex.org/W2741705590","https://openalex.org/W2807866521","https://openalex.org/W3014339000","https://openalex.org/W3105535951","https://openalex.org/W3115871478","https://openalex.org/W3192256856"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W4384158943"],"abstract_inverted_index":{"Transformer":[0],"networks":[1],"such":[2],"as":[3],"CodeBERT":[4],"already":[5,24],"achieve":[6],"outstanding":[7],"results":[8],"for":[9],"code":[10,28,37],"clone":[11,29],"detection":[12,30],"in":[13,39],"benchmark":[14],"datasets,":[15],"so":[16],"one":[17],"could":[18],"assume":[19],"that":[20],"this":[21],"task":[22],"has":[23],"been":[25],"solved.":[26],"However,":[27],"is":[31],"not":[32],"a":[33],"trivial":[34],"task.":[35],"Semantic":[36],"clones,":[38],"particular,":[40],"are":[41],"challenging":[42],"to":[43],"detect.":[44]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
