{"id":"https://openalex.org/W4328028680","doi":"https://doi.org/10.1109/qrs57517.2022.00098","title":"CodeBERT-nt: Code Naturalness via CodeBERT","display_name":"CodeBERT-nt: Code Naturalness via CodeBERT","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4328028680","doi":"https://doi.org/10.1109/qrs57517.2022.00098"},"language":"en","primary_location":{"id":"doi:10.1109/qrs57517.2022.00098","doi":"https://doi.org/10.1109/qrs57517.2022.00098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs57517.2022.00098","pdf_url":null,"source":{"id":"https://openalex.org/S4363608552","display_name":"IEEE International Conference on Software Quality, Reliability and Security (QRS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.06042","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075318858","display_name":"Ahmed Khanfir","orcid":"https://orcid.org/0000-0001-7471-6050","observed_orcids":["https://orcid.org/0000-0001-7471-6050"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Ahmed Khanfir","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101828371","display_name":"Matthieu Jimenez","orcid":"https://orcid.org/0000-0003-4061-1108","observed_orcids":["https://orcid.org/0000-0003-4061-1108"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Matthieu Jimenez","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081145634","display_name":"Mike Papadakis","orcid":"https://orcid.org/0000-0003-1852-2547","observed_orcids":["https://orcid.org/0000-0003-1852-2547"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Mike Papadakis","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040574362","display_name":"Yves Le Traon","orcid":"https://orcid.org/0000-0002-1045-4861","observed_orcids":["https://orcid.org/0000-0002-1045-4861"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Yves Le Traon","raw_affiliation_strings":["University of Luxembourg, Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":null,"apc_paid":null,"fwci":2.7613,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91969684,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"936","last_page":"947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/codebert","display_name":"CodeBERT","score":0.890999972820282},{"id":"https://openalex.org/keywords/token-masking","display_name":"token masking","score":0.6060000061988831},{"id":"https://openalex.org/keywords/code-completion","display_name":"code completion","score":0.41999998688697815},{"id":"https://openalex.org/keywords/embedding-similarity","display_name":"embedding similarity","score":0.718999981880188},{"id":"https://openalex.org/keywords/model-confidence","display_name":"model confidence","score":0.6370000243186951},{"id":"https://openalex.org/keywords/bug-prioritization","display_name":"bug prioritization","score":0.6800000071525574},{"id":"https://openalex.org/keywords/n-gram-language-models","display_name":"n-gram language models","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9396758079528809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260791301727295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5618084073066711},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5138716697692871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5114806890487671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4950041174888611},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4777916371822357},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.4424504041671753},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24804702401161194},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/qrs57517.2022.00098","doi":"https://doi.org/10.1109/qrs57517.2022.00098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs57517.2022.00098","pdf_url":null,"source":{"id":"https://openalex.org/S4363608552","display_name":"IEEE International Conference on Software Quality, Reliability and Security (QRS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.06042","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.06042","pdf_url":"https://arxiv.org/pdf/2208.06042","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:orbilu.uni.lu:10993/53506","doi":null,"is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/53506","pdf_url":"https://orbilu.uni.lu/bitstream/10993/53506/1/CodeBERT_nt___QRS_2022.pdf","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"22nd IEEE International Conference on Software Quality, Reliability and Security (QRS'22) (2022-12-05); 22nd IEEE International Conference on Software Quality, Reliability and Security (QRS'22), from 05-12-2022 to 09-12-2022","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"doi:10.48550/arxiv.2208.06042","doi":"https://doi.org/10.48550/arxiv.2208.06042","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.06042","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.06042","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.06042","pdf_url":"https://arxiv.org/pdf/2208.06042","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4328028680.pdf","grobid_xml":"https://content.openalex.org/works/W4328028680.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1771830246","https://openalex.org/W1934041838","https://openalex.org/W1962482270","https://openalex.org/W1995875735","https://openalex.org/W2079145130","https://openalex.org/W2108623177","https://openalex.org/W2148190602","https://openalex.org/W2158195707","https://openalex.org/W2514538448","https://openalex.org/W2626778328","https://openalex.org/W2731162050","https://openalex.org/W2754629507","https://openalex.org/W2887544264","https://openalex.org/W2888731859","https://openalex.org/W2896457183","https://openalex.org/W2921974495","https://openalex.org/W2954274464","https://openalex.org/W2963341956","https://openalex.org/W2995454814","https://openalex.org/W3098605233","https://openalex.org/W3106643019","https://openalex.org/W3130528814","https://openalex.org/W3134714752","https://openalex.org/W3146720657","https://openalex.org/W3153266893","https://openalex.org/W3177813494","https://openalex.org/W3183521984","https://openalex.org/W4232690755","https://openalex.org/W4238014149","https://openalex.org/W4252398070","https://openalex.org/W4284675318","https://openalex.org/W4312817595","https://openalex.org/W7119001154"],"related_works":["https://openalex.org/W4389524484","https://openalex.org/W4409161810","https://openalex.org/W1151032465","https://openalex.org/W4220722393","https://openalex.org/W4308641625","https://openalex.org/W4388212430","https://openalex.org/W4308627561","https://openalex.org/W4402954010","https://openalex.org/W3113043145","https://openalex.org/W3121922233"],"abstract_inverted_index":{"Much":[0],"of":[1,9,77,81,91,155,175,178,203,213,246],"recent":[2],"software-engineering":[3],"research":[4],"has":[5],"investigated":[6],"the":[7,11,69,89,159,173,179,183,187,195,201,204,208,214,250,268],"naturalness":[8,71,129,145],"code,":[10,14,191],"fact":[12],"that":[13,254],"in":[15,112],"small":[16,63],"code":[17,38,48,98,128,149,235],"snippets,":[18],"is":[19,125],"repetitive":[20],"and":[21,45,65,116,157,189,198,222,259,263],"can":[22,40],"be":[23,41],"predicted":[24,190],"using":[25,134],"statistical":[26],"language":[27,70,94,138],"models":[28,35,57,95,101],"like":[29],"n-gram.":[30],"Although":[31],"powerful,":[32],"training":[33],"such":[34],"on":[36,61,105,237,242],"large":[37],"corpus":[39,64],"tedious,":[42],"time":[43],"consuming":[44],"sensitive":[46],"to":[47,73,96,110,126,143,162,226,267],"patterns":[49],"(and":[50],"practices)":[51],"encountered":[52],"during":[53],"training.":[54],"Consequently,":[55],"these":[56,85],"are":[58,102,108],"often":[59,103],"trained":[60],"a":[62,74,153],"thus":[66],"only":[67],"estimate":[68],"relative":[72],"specific":[75],"style":[76],"programming":[78],"or":[79],"type":[80],"project.":[82],"To":[83],"overcome":[84],"issues,":[86],"we":[87,141],"investigate":[88],"use":[90,111],"pre-trained":[92,137],"generative":[93,136],"infer":[97,144],"naturalness.":[99,239],"Pre-trained":[100],"built":[104],"big":[106],"data,":[107],"easy":[109],"an":[113],"out-of-the-box":[114],"way":[115],"include":[117],"powerful":[118],"learning":[119],"associations":[120],"mechanisms.":[121],"Our":[122,240],"key":[123],"idea":[124],"quantify":[127],"through":[130],"its":[131,224,238],"predictability,":[132],"by":[133,146],"state-of-the-art":[135],"models.":[139,270],"Thus,":[140],"suggest":[142],"masking":[147],"(omitting)":[148],"tokens,":[150],"one":[151],"at":[152,194],"time,":[154],"code-sequences,":[156],"checking":[158],"models\u2019":[160],"ability":[161],"predict":[163],"them.":[164],"We":[165,216],"explore":[166],"three":[167],"different":[168],"predictability":[169],"metrics;":[170],"a)":[171],"measuring":[172],"number":[174],"exact":[176],"matches":[177],"predictions,":[180],"b)":[181],"computing":[182,200],"embedding":[184],"similarity":[185,193],"between":[186],"original":[188],"i.e.,":[192],"vector":[196],"space,":[197],"c)":[199],"confidence":[202],"model":[205],"when":[206,233],"doing":[207],"token":[209],"completion":[210],"task":[211],"regardless":[212],"outcome.":[215],"implement":[217],"this":[218],"workflow,":[219],"named":[220],"CODEBERT-NT,":[221],"evaluate":[223],"capability":[225],"prioritize":[227],"buggy":[228,244],"lines":[229],"over":[230],"non-buggy":[231],"ones":[232],"ranking":[234,261],"based":[236],"results,":[241],"2,510":[243],"versions":[245],"40":[247],"projects":[248],"from":[249],"SmartShark":[251],"dataset,":[252],"show":[253],"CODEBERTNT":[255],"outperforms":[256],"both,":[257],"random-uniform":[258],"complexity-based":[260],"techniques,":[262],"yields":[264],"comparable":[265],"results":[266],"n-gram":[269]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-03-22T00:00:00"}