{"id":"https://openalex.org/W4301168982","doi":"https://doi.org/10.1145/2884781.2884877","title":"SourcererCC","display_name":"SourcererCC","publication_year":2016,"publication_date":"2016-05-13","ids":{"openalex":"https://openalex.org/W4301168982","doi":"https://doi.org/10.1145/2884781.2884877"},"language":"en","primary_location":{"id":"doi:10.1145/2884781.2884877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"preprint","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/A5015641612","display_name":"Hitesh Sajnani","orcid":"https://orcid.org/0009-0004-9973-6241"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hitesh Sajnani","raw_affiliation_strings":["School of Information and Computer Science, UC Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Computer Science, UC Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846745","display_name":"Vaibhav Saini","orcid":"https://orcid.org/0000-0002-6107-9504"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Saini","raw_affiliation_strings":["School of Information and Computer Science, UC Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Computer Science, UC Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006573523","display_name":"Jeffrey Svajlenko","orcid":"https://orcid.org/0000-0001-9738-7421"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jeffrey Svajlenko","raw_affiliation_strings":["University of Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102756770","display_name":"Chanchal K. Roy","orcid":"https://orcid.org/0000-0003-0519-6164"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chanchal K. Roy","raw_affiliation_strings":["University of Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103284742","display_name":"Cristina Videira Lopes","orcid":"https://orcid.org/0000-0003-0551-3908"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristina V. Lopes","raw_affiliation_strings":["School of Information and Computer Science, UC Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Computer Science, UC Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":71.1073,"has_fulltext":false,"cited_by_count":427,"citation_normalized_percentile":{"value":0.99918689,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1157","last_page":"1168"},"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":0.9912999868392944,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.803193986415863},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7028818726539612},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6761689782142639},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6572585105895996},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5998345017433167},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5782400369644165},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5589940547943115},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5010788440704346},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49540865421295166},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4681582450866699},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4615516662597656},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4214904308319092},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33596864342689514},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2929580807685852},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2725587487220764},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20087698101997375},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.18179115653038025},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.17555022239685059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803193986415863},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7028818726539612},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6761689782142639},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6572585105895996},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5998345017433167},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5782400369644165},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5589940547943115},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5010788440704346},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49540865421295166},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4681582450866699},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4615516662597656},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4214904308319092},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33596864342689514},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2929580807685852},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2725587487220764},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20087698101997375},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.18179115653038025},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.17555022239685059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2884781.2884877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1512615396","https://openalex.org/W1972466226","https://openalex.org/W1980867644","https://openalex.org/W1983316175","https://openalex.org/W2007818470","https://openalex.org/W2019374535","https://openalex.org/W2025962632","https://openalex.org/W2041190309","https://openalex.org/W2043169794","https://openalex.org/W2065053490","https://openalex.org/W2065622239","https://openalex.org/W2087343574","https://openalex.org/W2088211982","https://openalex.org/W2088479623","https://openalex.org/W2097184821","https://openalex.org/W2098230348","https://openalex.org/W2100060170","https://openalex.org/W2101832700","https://openalex.org/W2120326119","https://openalex.org/W2121516976","https://openalex.org/W2124173249","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2131477050","https://openalex.org/W2134852596","https://openalex.org/W2138756793","https://openalex.org/W2142403498","https://openalex.org/W2144886241","https://openalex.org/W2158439356","https://openalex.org/W2161276236","https://openalex.org/W2162436321","https://openalex.org/W2172244770","https://openalex.org/W2495436614","https://openalex.org/W4386707048","https://openalex.org/W6697318023"],"related_works":["https://openalex.org/W2377327490","https://openalex.org/W2124379162","https://openalex.org/W2560253012","https://openalex.org/W4388335561","https://openalex.org/W2001919569","https://openalex.org/W2921323488","https://openalex.org/W2100060170","https://openalex.org/W2158439356","https://openalex.org/W2804385550","https://openalex.org/W2888789210"],"abstract_inverted_index":{"Despite":[0],"a":[1,9,30,48,63,104,137,146,170,178],"decade":[2],"of":[3,62,80,85,98,116,140,149,151],"active":[4],"research,":[5],"there":[6],"has":[7,158],"been":[8],"marked":[10],"lack":[11],"in":[12],"clone":[13,32],"detection":[14],"techniques":[15],"that":[16,35],"scale":[17,168],"to":[18,56,75,89,102,121,167,169],"large":[19,44,171],"repositories":[20,46],"for":[21],"detecting":[22],"near-miss":[23,41],"clones.":[24,154],"In":[25],"this":[26],"paper,":[27],"we":[28,131],"present":[29],"token-based":[31],"detector,":[33],"SourcererCC,":[34,117],"can":[36],"detect":[37,90],"both":[38,159],"exact":[39],"and":[40,114,118,125,144,162,164],"clones":[42,61],"from":[43],"inter-project":[45,172],"using":[47,177],"standard":[49,179],"workstation.":[50,180],"It":[51],"exploits":[52],"an":[53],"optimized":[54],"inverted-index":[55],"quickly":[57],"query":[58],"the":[59,78,81,83,91,96,109],"potential":[60,105],"given":[64],"code":[65],"block.":[66],"Filtering":[67],"heuristics":[68],"based":[69],"on":[70],"token":[71],"ordering":[72],"are":[73],"used":[74],"significantly":[76],"reduce":[77],"size":[79],"index,":[82],"number":[84,97],"code-block":[86],"comparisons":[87],"needed":[88,101],"clones,":[92,142],"as":[93,95],"well":[94],"required":[99],"token-comparisons":[100],"judge":[103],"clone.":[106],"We":[107,155],"evaluate":[108],"scalability,":[110],"execution":[111],"time,":[112],"recall":[113,161],"precision":[115],"compare":[119],"it":[120],"four":[122],"publicly":[123],"available":[124],"state-of-the-art":[126],"tools.":[127],"To":[128],"measure":[129],"recall,":[130],"use":[132],"two":[133],"recent":[134],"benchmarks:":[135],"(1)":[136],"big":[138],"benchmark":[139],"real":[141],"BigCloneBench,":[143],"(2)":[145],"Mutation/Injection-based":[147],"framework":[148],"thousands":[150],"fine-grained":[152],"artificial":[153],"find":[156],"SourcererCC":[157],"high":[160],"precision,":[163],"is":[165],"able":[166],"repository":[173],"(25K":[174],"projects,":[175],"250MLOC)":[176]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":53},{"year":2022,"cited_by_count":56},{"year":2021,"cited_by_count":59},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":41},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":9}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2022-10-04T00:00:00"}
