{"id":"https://openalex.org/W4394745382","doi":"https://doi.org/10.1145/3597503.3639074","title":"Unveiling Memorization in Code Models","display_name":"Unveiling Memorization in Code Models","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394745382","doi":"https://doi.org/10.1145/3597503.3639074"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3639074","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3639074","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639074","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 IEEE/ACM 46th International Conference on 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/10.1145/3597503.3639074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008695791","display_name":"Zhou Yang","orcid":"https://orcid.org/0000-0001-5938-1918"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Zhou Yang","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5938-1918","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675629","display_name":"Zhipeng Zhao","orcid":"https://orcid.org/0000-0002-1701-0286"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zhipeng Zhao","raw_affiliation_strings":["University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-1701-0286","affiliations":[{"raw_affiliation_string":"University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052920267","display_name":"Chenyu Wang","orcid":"https://orcid.org/0009-0003-2436-5899"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenyu Wang","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-2436-5899","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002667771","display_name":"Jieke Shi","orcid":"https://orcid.org/0000-0002-0799-5018"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jieke Shi","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0799-5018","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067772621","display_name":"Dongsun Kim","orcid":"https://orcid.org/0000-0003-0272-6860"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongsun Kim","raw_affiliation_strings":["Kyungpook National University, Daegu, Korea"],"raw_orcid":"https://orcid.org/0000-0003-0272-6860","affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054365831","display_name":"DongGyun Han","orcid":"https://orcid.org/0000-0002-8599-2197"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Donggyun Han","raw_affiliation_strings":["Royal Holloway, University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8599-2197","affiliations":[{"raw_affiliation_string":"Royal Holloway, University of London, London, United Kingdom","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4367-7201","affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5008695791"],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":24.618,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.99541254,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.659252405166626},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5457219481468201},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5314029455184937},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.45516905188560486},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16148802638053894},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08912530541419983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659252405166626},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5457219481468201},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5314029455184937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.45516905188560486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16148802638053894},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08912530541419983},{"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:10.1145/3597503.3639074","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3639074","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639074","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 IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/5a86703c-743d-4d22-8a26-95be84e9c872","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/5a86703c-743d-4d22-8a26-95be84e9c872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"Yang , Z , Zhao , Z , Wang , C , Shi , J , Kim , D , Han , D & Lo , D 2024 , Unveiling Memorization in Code Models . in Proceedings - 2024 ACM/IEEE 44th International Conference on Software Engineering, ICSE 2024 . IEEE Computer Society Press , pp. 867-879 , 44th ACM/IEEE International Conference on Software Engineering, ICSE 2024 , Lisbon , Portugal , 14/04/2024 . https://doi.org/10.1145/3597503.3639074","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3597503.3639074","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3639074","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639074","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 IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2830144834","display_name":null,"funder_award_id":"2021R1I1A3048013","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4447486136","display_name":null,"funder_award_id":"2021R1A5A1021944","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5332036567","display_name":null,"funder_award_id":"NRF-NRFI08-2022-0002","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G7169835300","display_name":null,"funder_award_id":"NRF-NRFI08-2022-0002","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G7369723383","display_name":null,"funder_award_id":"2021R1A5A1021944","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G875168909","display_name":null,"funder_award_id":"NRF-NRFI08-2022","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321272","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394745382.pdf","grobid_xml":"https://content.openalex.org/works/W4394745382.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W2158195707","https://openalex.org/W2163004671","https://openalex.org/W2298313545","https://openalex.org/W2350778671","https://openalex.org/W2535690855","https://openalex.org/W2884943453","https://openalex.org/W2930957955","https://openalex.org/W2963341956","https://openalex.org/W2963919731","https://openalex.org/W2979792666","https://openalex.org/W3004658838","https://openalex.org/W3011159643","https://openalex.org/W3035261884","https://openalex.org/W3071470454","https://openalex.org/W3106051020","https://openalex.org/W3106873467","https://openalex.org/W3109966548","https://openalex.org/W3123684396","https://openalex.org/W3131641316","https://openalex.org/W3199249334","https://openalex.org/W3210860486","https://openalex.org/W3212496002","https://openalex.org/W3217001695","https://openalex.org/W4205678875","https://openalex.org/W4206334468","https://openalex.org/W4220722393","https://openalex.org/W4221159558","https://openalex.org/W4284664377","https://openalex.org/W4285490465","https://openalex.org/W4287265163","https://openalex.org/W4295646147","https://openalex.org/W4307932649","https://openalex.org/W4308627220","https://openalex.org/W4308643152","https://openalex.org/W4312044266","https://openalex.org/W4312565886","https://openalex.org/W4313563661","https://openalex.org/W4313936359","https://openalex.org/W4384009645","https://openalex.org/W4385270018","https://openalex.org/W4385302156","https://openalex.org/W4385573947","https://openalex.org/W6602680078"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3093895509","https://openalex.org/W3163481960","https://openalex.org/W2323394100","https://openalex.org/W280704926","https://openalex.org/W2476068070","https://openalex.org/W4323971310","https://openalex.org/W2893372175"],"abstract_inverted_index":{"The":[0,23],"availability":[1],"of":[2,27,29,31],"large-scale":[3],"datasets,":[4],"advanced":[5],"architectures,":[6],"and":[7,36,43,63],"powerful":[8],"computational":[9],"resources":[10],"have":[11],"led":[12],"to":[13,60],"effective":[14],"code":[15,32,40,46,55],"models":[16],"that":[17],"automate":[18],"diverse":[19],"software":[20],"engineering":[21],"activities.":[22],"datasets":[24],"usually":[25],"consist":[26],"billions":[28],"lines":[30],"from":[33],"both":[34],"open-source":[35],"private":[37],"repositories.":[38],"A":[39],"model":[41],"memorizes":[42],"produces":[44],"source":[45],"verbatim,":[47],"which":[48],"potentially":[49],"contains":[50],"vulnerabilities,":[51],"sensitive":[52],"information,":[53],"or":[54],"with":[56],"strict":[57],"licenses,":[58],"leading":[59],"potential":[61],"security":[62],"privacy":[64],"issues.":[65]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}