{"id":"https://openalex.org/W4384154459","doi":"https://doi.org/10.1145/3597926.3598035","title":"CONCORD: Clone-Aware Contrastive Learning for Source Code","display_name":"CONCORD: Clone-Aware Contrastive Learning for Source Code","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384154459","doi":"https://doi.org/10.1145/3597926.3598035"},"language":"en","primary_location":{"id":"doi:10.1145/3597926.3598035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597926.3598035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064527453","display_name":"Yangruibo Ding","orcid":"https://orcid.org/0000-0003-3224-6876"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangruibo Ding","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074368173","display_name":"Saikat Chakraborty","orcid":"https://orcid.org/0000-0002-6889-7171"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saikat Chakraborty","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022631353","display_name":"Luca Buratti","orcid":"https://orcid.org/0009-0007-1468-9995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Buratti","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086021292","display_name":"Saurabh Pujar","orcid":"https://orcid.org/0000-0002-9772-3162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Pujar","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076968229","display_name":"Alessandro Morari","orcid":"https://orcid.org/0009-0005-5006-8817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Morari","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090171418","display_name":"Gail E. Kaiser","orcid":"https://orcid.org/0000-0002-8791-1178"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Kaiser","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064541855","display_name":"Baishakhi Ray","orcid":"https://orcid.org/0000-0003-3406-5235"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baishakhi Ray","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"38"},"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":0.9987000226974487,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9986000061035156,"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":0.7711208462715149},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6844381093978882},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5893300175666809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386360287666321},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.523999810218811},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5168914794921875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4621458947658539},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38812488317489624},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34435516595840454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711208462715149},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6844381093978882},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5893300175666809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386360287666321},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.523999810218811},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5168914794921875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4621458947658539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38812488317489624},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34435516595840454},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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":1,"locations":[{"id":"doi:10.1145/3597926.3598035","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597926.3598035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3700072604","display_name":null,"funder_award_id":"N66001-21-C-4018","funder_id":"https://openalex.org/F4320338406","funder_display_name":"Naval Information Warfare Center Pacific"},{"id":"https://openalex.org/G3967052620","display_name":null,"funder_award_id":"CCF-1815494, CCF-210740, CCF-1845893, IIS-222194","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5037498036","display_name":"SHF: Small: Preponderance of the Evidence for Behavioral Code Similarities","funder_award_id":"1815494","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5412059031","display_name":null,"funder_award_id":"N66001-21-C-4018","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5732220483","display_name":"FAI: Measuring and Mitigating Biases in Generic Image Representations","funder_award_id":"2221943","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6502924317","display_name":"CAREER: Systematic Software Testing for Deep Learning Applications","funder_award_id":"1845893","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7124914134","display_name":null,"funder_award_id":"Pacific N66001-21-C-4018","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338406","display_name":"Naval Information Warfare Center Pacific","ror":"https://ror.org/01gs1cg95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1771830246","https://openalex.org/W2018986336","https://openalex.org/W2025341678","https://openalex.org/W2065053490","https://openalex.org/W2119887272","https://openalex.org/W2124991517","https://openalex.org/W2136279823","https://openalex.org/W2142403498","https://openalex.org/W2156723666","https://openalex.org/W2157364932","https://openalex.org/W2282866165","https://openalex.org/W2541061885","https://openalex.org/W2559935471","https://openalex.org/W2634106992","https://openalex.org/W2741643261","https://openalex.org/W2806718802","https://openalex.org/W2883915502","https://openalex.org/W2902618648","https://openalex.org/W2930957955","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2978017171","https://openalex.org/W2979826702","https://openalex.org/W2999200532","https://openalex.org/W3011564318","https://openalex.org/W3025298766","https://openalex.org/W3098605233","https://openalex.org/W3103499786","https://openalex.org/W3121414853","https://openalex.org/W3155146092","https://openalex.org/W3163206498","https://openalex.org/W3166095789","https://openalex.org/W3170092793","https://openalex.org/W3188174680","https://openalex.org/W3198188208","https://openalex.org/W4205371973","https://openalex.org/W4221160134","https://openalex.org/W4221166942","https://openalex.org/W4242395378","https://openalex.org/W4243235114","https://openalex.org/W4285177871","https://openalex.org/W4288077069","https://openalex.org/W4299358159","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W2377327490","https://openalex.org/W2560253012","https://openalex.org/W1524590520","https://openalex.org/W2412288087","https://openalex.org/W2371792548","https://openalex.org/W1697705604","https://openalex.org/W2419862115","https://openalex.org/W2770713575","https://openalex.org/W2017092658","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"(DL)":[2],"models":[3],"to":[4],"analyze":[5],"source":[6],"code":[7,27],"have":[8],"shown":[9],"immense":[10],"promise":[11],"during":[12],"the":[13],"past":[14],"few":[15],"years.":[16],"More":[17],"recently,":[18],"self-supervised":[19],"pre-training":[20],"has":[21],"gained":[22],"traction":[23],"for":[24,30],"learning":[25],"generic":[26],"representations":[28],"valuable":[29],"many":[31],"downstream":[32],"SE":[33],"tasks,":[34],"such":[35],"as":[36],"clone":[37],"and":[38],"bug":[39],"detection.":[40]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}