{"id":"https://openalex.org/W2903709763","doi":"https://doi.org/10.1145/3359591.3359735","title":"The adverse effects of code duplication in machine learning models of code","display_name":"The adverse effects of code duplication in machine learning models of code","publication_year":2019,"publication_date":"2019-10-10","ids":{"openalex":"https://openalex.org/W2903709763","doi":"https://doi.org/10.1145/3359591.3359735","mag":"2903709763"},"language":"en","primary_location":{"id":"doi:10.1145/3359591.3359735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3359591.3359735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software","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/1812.06469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080221214","display_name":"Miltiadis Allamanis","orcid":"https://orcid.org/0000-0002-5819-9900"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Miltiadis Allamanis","raw_affiliation_strings":["Microsoft Research, UK","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, UK","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080221214"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":5.2777,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95731245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9943000078201294,"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":0.9926999807357788,"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":0.7907063364982605},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6791398525238037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5612747073173523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5435370206832886},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.501697301864624},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.46029412746429443},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45270416140556335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3780639171600342},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.36290767788887024},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.2992185950279236},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20429709553718567},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.16239595413208008},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08237865567207336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907063364982605},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6791398525238037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5612747073173523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435370206832886},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.501697301864624},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.46029412746429443},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45270416140556335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3780639171600342},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36290767788887024},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2992185950279236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20429709553718567},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.16239595413208008},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08237865567207336},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3359591.3359735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3359591.3359735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.06469","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.06469","pdf_url":"https://arxiv.org/pdf/1812.06469","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2903709763","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1812.06469v6","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.1812.06469","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.06469","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"},{"id":"mag:3157061691","is_oa":false,"landing_page_url":"https://www.microsoft.com/en-us/research/publication/the-adverse-effects-of-code-duplication-in-machine-learning-models-of-code/","pdf_url":null,"source":{"id":"https://openalex.org/S4306420881","display_name":"SIGPLAN symposium on New ideas, new paradigms, and reflections on programming and software","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"SIGPLAN symposium on New ideas, new paradigms, and reflections on programming and software","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.06469","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.06469","pdf_url":"https://arxiv.org/pdf/1812.06469","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W2903709763.pdf","grobid_xml":"https://content.openalex.org/works/W2903709763.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1551431154","https://openalex.org/W2060384944","https://openalex.org/W2090432523","https://openalex.org/W2095938258","https://openalex.org/W2142403498","https://openalex.org/W2143861926","https://openalex.org/W2148190602","https://openalex.org/W2156981320","https://openalex.org/W2238673293","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2444132761","https://openalex.org/W2516621648","https://openalex.org/W2728773317","https://openalex.org/W2740130862","https://openalex.org/W2762844179","https://openalex.org/W2887364112","https://openalex.org/W2890397703","https://openalex.org/W2891332953","https://openalex.org/W2899384793","https://openalex.org/W2962936887","https://openalex.org/W2962995178","https://openalex.org/W2963499994","https://openalex.org/W2963935794","https://openalex.org/W2964150020","https://openalex.org/W3005855585","https://openalex.org/W4285719527","https://openalex.org/W4301168982","https://openalex.org/W6680532216"],"related_works":["https://openalex.org/W2963403868","https://openalex.org/W2142403498","https://openalex.org/W2064675550","https://openalex.org/W2962995178","https://openalex.org/W2762844179","https://openalex.org/W2018389835","https://openalex.org/W2010608861","https://openalex.org/W2758313244","https://openalex.org/W656101134","https://openalex.org/W2058214118","https://openalex.org/W3089621332","https://openalex.org/W3102725096","https://openalex.org/W2087419855","https://openalex.org/W2926727016","https://openalex.org/W3105005311","https://openalex.org/W2952829418","https://openalex.org/W795501845","https://openalex.org/W2100310618","https://openalex.org/W3196819515","https://openalex.org/W2299852975"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,10,43,51,74,114],"big":[3],"code":[4,11,45,52,75,97,115,135],"relies":[5],"on":[6,46,77,95,103,142],"mining":[7],"large":[8,41],"corpora":[9,98,105,136],"to":[12,27,91,100,148],"perform":[13],"some":[14],"learning":[15,62,79,112,140],"task":[16],"towards":[17],"creating":[18],"better":[19],"tools":[20,147],"for":[21,64,126,133],"software":[22,119],"engineers.":[23,120],"A":[24],"significant":[25],"threat":[26],"this":[28,68,153],"approach":[29],"was":[30],"recently":[31],"identified":[32],"by":[33,58,89,118],"Lopes":[34],"et":[35],"al.":[36],"(2017)":[37],"who":[38],"found":[39],"a":[40,123],"amount":[42],"near-duplicate":[44],"GitHub.":[47],"However,":[48],"the":[49,72,101,150],"impact":[50],"duplication":[53,76,124],"has":[54],"not":[55],"been":[56],"noticed":[57],"researchers":[59],"devising":[60],"machine":[61,78,111,139],"models":[63,80,113,141],"source":[65],"code.":[66],"In":[67],"work,":[69],"we":[70,145],"explore":[71],"effects":[73],"showing":[81],"that":[82],"reported":[83],"performance":[84,102],"metrics":[85],"are":[86,116],"sometimes":[87],"inflated":[88],"up":[90],"100%":[92],"when":[93],"testing":[94],"duplicated":[96],"compared":[99],"de-duplicated":[104],"which":[106],"more":[107],"accurately":[108],"represent":[109],"how":[110],"used":[117,128],"We":[121],"present":[122],"index":[125],"widely":[127],"datasets,":[129],"list":[130],"best":[131],"practices":[132],"collecting":[134],"and":[137],"evaluating":[138],"them.":[143],"Finally,":[144],"release":[146],"help":[149],"community":[151],"avoid":[152],"problem":[154],"in":[155],"future":[156],"research.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}