{"id":"https://openalex.org/W4244324234","doi":"https://doi.org/10.1109/iwsc.2013.6613042","title":"A parallel and efficient approach to large scale clone detection","display_name":"A parallel and efficient approach to large scale clone detection","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W4244324234","doi":"https://doi.org/10.1109/iwsc.2013.6613042"},"language":"en","primary_location":{"id":"doi:10.1109/iwsc.2013.6613042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwsc.2013.6613042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th International Workshop on Software Clones (IWSC)","raw_type":"proceedings-article"},"type":"article","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":["Donald Bren School of Information and Computer Science, University of California, Irvine, Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donald Bren School of Information and Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"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 Lopes","raw_affiliation_strings":["Donald Bren School of Information and Computer Science, University of California, Irvine, Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donald Bren School of Information and Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6724,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90484322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"52"},"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":0.9968000054359436,"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":0.9968000054359436,"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/scalability","display_name":"Scalability","score":0.7797378301620483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739921808242798},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6406147480010986},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5757392048835754},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.49224939942359924},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48173168301582336},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43869876861572266},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4311612546443939},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4108726382255554},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40852147340774536},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3820692002773285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34545087814331055},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16148686408996582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14424055814743042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09677812457084656}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7797378301620483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739921808242798},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6406147480010986},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5757392048835754},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.49224939942359924},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48173168301582336},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43869876861572266},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4311612546443939},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4108726382255554},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40852147340774536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3820692002773285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34545087814331055},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16148686408996582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14424055814743042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09677812457084656},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwsc.2013.6613042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwsc.2013.6613042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th International Workshop on Software Clones (IWSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W37320347","https://openalex.org/W1974446554","https://openalex.org/W1983316175","https://openalex.org/W2021655726","https://openalex.org/W2029565819","https://openalex.org/W2042849148","https://openalex.org/W2056830820","https://openalex.org/W2088211982","https://openalex.org/W2101832700","https://openalex.org/W2117508687","https://openalex.org/W2120326119","https://openalex.org/W2124173249","https://openalex.org/W2127675794","https://openalex.org/W2128888088","https://openalex.org/W2134852596","https://openalex.org/W2144886241","https://openalex.org/W2162436321","https://openalex.org/W2166697934","https://openalex.org/W2172244770","https://openalex.org/W3003280364","https://openalex.org/W6669100502","https://openalex.org/W6681626296"],"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/W2017092658","https://openalex.org/W2783065147","https://openalex.org/W4312723892"],"abstract_inverted_index":{"Over":[0],"the":[1,12,51,72,95,115,117,125,160,174,180,194],"past":[2],"few":[3],"years,":[4],"researchers":[5],"have":[6,46],"implemented":[7],"various":[8],"algorithms":[9,20],"to":[10,68,86,113,123,149,163,193],"improve":[11],"scalability":[13],"of":[14,18,43,54,61,74,127,136,176,187,200],"clone":[15,44,89],"detection.":[16],"Most":[17],"these":[19,62,76],"focus":[21],"on":[22,25,197],"scaling":[23],"vertically":[24],"a":[26,55,84,120,185,198],"single":[27,56],"machine,":[28],"and":[29,139,178],"require":[30,103],"complex":[31,106],"intermediate":[32,107],"data":[33,77,108],"structures":[34],"(e.g.,":[35],"suffix":[36],"tree,":[37],"etc.).":[38],"However,":[39],"several":[40],"new":[41],"use-cases":[42],"detection":[45,90],"emerged,":[47],"which":[48],"are":[49],"beyond":[50],"computational":[52],"capacity":[53],"machine.":[57],"Moreover,":[58,110],"for":[59,203],"some":[60],"usecases":[63],"it":[64,140],"may":[65],"be":[66,142],"expensive":[67],"invest":[69],"upfront":[70],"in":[71,111,144],"cost":[73],"building":[75,104],"structures.":[78,109],"In":[79,153],"this":[80],"paper,":[81],"we":[82,156,172],"propose":[83],"technique":[85,100,118],"horizontally":[87],"scale":[88],"across":[91],"multiple":[92],"machines":[93],"using":[94],"popular":[96],"MapReduce":[97],"framework.":[98],"The":[99,131],"does":[101],"not":[102,188],"any":[105],"order":[112],"increase":[114,150],"efficiency,":[116],"uses":[119],"filtering":[121,132],"heuristic":[122,133],"prune":[124],"number":[126,175],"code":[128],"block":[129],"comparisons.":[130],"is":[134,182],"independent":[135],"our":[137,154],"approach":[138],"can":[141],"used":[143],"conjunction":[145],"with":[146,184],"other":[147],"approaches":[148],"their":[151],"efficiency.":[152],"experiments,":[155],"found":[157],"that:":[158],"(i)":[159],"computation":[161],"time":[162,171],"detect":[164],"clones":[165],"decreases":[166],"by":[167],"almost":[168],"half":[169],"every":[170],"double":[173],"nodes;":[177],"(ii)":[179],"scaleup":[181],"linear,":[183],"decline":[186],"more":[189],"than":[190],"70%":[191],"compared":[192],"ideal":[195],"case,":[196],"cluster":[199],"2-32":[201],"nodes":[202],"150-2800":[204],"projects.":[205]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}