{"id":"https://openalex.org/W2023288969","doi":"https://doi.org/10.1145/1081706.1081733","title":"Detecting higher-level similarity patterns in programs","display_name":"Detecting higher-level similarity patterns in programs","publication_year":2005,"publication_date":"2005-09-01","ids":{"openalex":"https://openalex.org/W2023288969","doi":"https://doi.org/10.1145/1081706.1081733","mag":"2023288969"},"language":"en","primary_location":{"id":"doi:10.1145/1081706.1081733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081706.1081733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th European software engineering conference held jointly with 13th ACM SIGSOFT international symposium on Foundations of software engineering","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/A5039252859","display_name":"Hamid Abdul Basit","orcid":"https://orcid.org/0000-0002-1684-4262"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hamid Abdul Basit","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113533321","display_name":"Stan Jarzabek","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Stan Jarzabek","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039252859"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":29.6817,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.99486298,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"165"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.996399998664856,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9961000084877014,"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":0.7598385214805603},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6030141711235046},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5817242860794067},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5768802165985107},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5481970906257629},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5428277850151062},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.49010810256004333},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48907309770584106},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.4575336277484894},{"id":"https://openalex.org/keywords/software-maintenance","display_name":"Software maintenance","score":0.44645512104034424},{"id":"https://openalex.org/keywords/software-system","display_name":"Software system","score":0.3936651945114136},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3231973648071289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.260913223028183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598385214805603},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6030141711235046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5817242860794067},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5768802165985107},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5481970906257629},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5428277850151062},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.49010810256004333},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48907309770584106},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4575336277484894},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.44645512104034424},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.3936651945114136},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3231973648071289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.260913223028183},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1081706.1081733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081706.1081733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th European software engineering conference held jointly with 13th ACM SIGSOFT international symposium on Foundations of software engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/41209","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/41209","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.9800","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.9800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~stan/PAPERS/Clone%20Miner.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.3180","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.3180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://plg.uwaterloo.ca/~migod/846/papers/jarzabek-fse05-CloneMiner.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W117230746","https://openalex.org/W159524162","https://openalex.org/W208128215","https://openalex.org/W1489909987","https://openalex.org/W1495956867","https://openalex.org/W1496073286","https://openalex.org/W1497529086","https://openalex.org/W1500382227","https://openalex.org/W1512285202","https://openalex.org/W1523197392","https://openalex.org/W1523521467","https://openalex.org/W1543263356","https://openalex.org/W1593203335","https://openalex.org/W1599310603","https://openalex.org/W1649645444","https://openalex.org/W1698439592","https://openalex.org/W1964795700","https://openalex.org/W1966467209","https://openalex.org/W1974930421","https://openalex.org/W2021481978","https://openalex.org/W2029360780","https://openalex.org/W2063022796","https://openalex.org/W2066688923","https://openalex.org/W2096491586","https://openalex.org/W2109943392","https://openalex.org/W2118024368","https://openalex.org/W2128698639","https://openalex.org/W2130564474","https://openalex.org/W2138756793","https://openalex.org/W2140190241","https://openalex.org/W2142038400","https://openalex.org/W2157532207","https://openalex.org/W2158874082","https://openalex.org/W2159707167","https://openalex.org/W2275023529","https://openalex.org/W2289119746","https://openalex.org/W2294305189","https://openalex.org/W4239812996","https://openalex.org/W4285719527","https://openalex.org/W6629824143"],"related_works":["https://openalex.org/W2111305209","https://openalex.org/W2799156456","https://openalex.org/W2049138229","https://openalex.org/W972988137","https://openalex.org/W3137169100","https://openalex.org/W2013638584","https://openalex.org/W2921593623","https://openalex.org/W2747474147","https://openalex.org/W2033840206","https://openalex.org/W2040868764"],"abstract_inverted_index":{"Cloning":[0],"in":[1,25,41,163],"software":[2,10,42],"systems":[3],"is":[4,36,201],"known":[5],"to":[6,17,98,123,178,189,191,207,225],"create":[7],"problems":[8],"during":[9],"maintenance.":[11],"Several":[12],"techniques":[13,97,206],"have":[14],"been":[15],"proposed":[16],"detect":[18,147,179,208],"the":[19,31,70,100,112,124,158,167,245],"same":[20],"or":[21,84,143],"similar":[22,141,184],"code":[23],"fragments":[24],"software,":[26],"so-called":[27,64],"simple":[28,34,61,103,148],"clones.":[29],"While":[30],"knowledge":[32],"of":[33,60,72,81,102,126,133,139,160,182,198,203],"clones":[35,62,66,88,149,162,221],"useful,":[37,131],"detecting":[38,127],"design-level":[39,74,134,193],"similarities":[40,135],"could":[43],"ease":[44],"maintenance":[45],"even":[46],"further,":[47],"and":[48,106,222,247],"also":[49],"help":[50],"us":[51],"identify":[52],"reuse":[53],"opportunities.":[54],"We":[55],"observed":[56],"that":[57,89,186,214,243],"recurring":[58],"patterns":[59,80,159],"-":[63,67],"structural":[65,87,220,234],"often":[68],"indicate":[69],"presence":[71],"interesting":[73],"similarities.":[75,211],"An":[76],"example":[77],"would":[78],"be":[79],"collaborating":[82],"classes":[83,142],"components.":[85],"Finding":[86],"signify":[90],"potentially":[91],"useful":[92,219],"design":[93,209],"information":[94],"requires":[95],"efficient":[96],"analyze":[99],"bulk":[101],"clone":[104,235],"data":[105,204],"making":[107],"non-trivial":[108],"inferences":[109],"based":[110],"on":[111],"abstracted":[113],"information.":[114],"In":[115],"this":[116],"paper,":[117],"we":[118,146,156,174],"describe":[119],"a":[120,192,237],"practical":[121],"solution":[122],"problem":[125],"some":[128],"basic,":[129],"but":[130],"types":[132],"such":[136],"as":[137],"groups":[138],"highly":[140,183],"files.":[144],"First,":[145],"by":[150],"applying":[151],"conventional":[152],"token-based":[153],"techniques.":[154],"Then":[155],"find":[157],"co-occurring":[161],"different":[164],"files":[165,185],"using":[166],"Frequent":[168],"Itemset":[169],"Mining":[170],"(FIM)":[171],"technique.":[172],"Finally,":[173],"perform":[175],"file":[176],"clustering":[177],"those":[180],"clusters":[181],"are":[187],"likely":[188],"contribute":[190],"similarity":[194],"pattern.":[195],"The":[196,228],"novelty":[197],"our":[199,215,231],"approach":[200],"application":[202],"mining":[205],"level":[210],"Experiments":[212],"confirmed":[213],"method":[216,232,246],"finds":[217],"many":[218],"scales":[223],"up":[224],"big":[226],"programs.":[227],"paper":[229],"describes":[230],"for":[233],"detection,":[236],"prototype":[238],"tool":[239],"called":[240],"Clone":[241],"Miner":[242],"implements":[244],"experimental":[248],"results.":[249]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
