{"id":"https://openalex.org/W2102543548","doi":"https://doi.org/10.1109/tse.2007.70720","title":"Finding Clones with Dup: Analysis of an Experiment","display_name":"Finding Clones with Dup: Analysis of an Experiment","publication_year":2007,"publication_date":"2007-08-22","ids":{"openalex":"https://openalex.org/W2102543548","doi":"https://doi.org/10.1109/tse.2007.70720","mag":"2102543548"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2007.70720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2007.70720","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-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/A5108392571","display_name":"Brenda S. Baker","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brenda S. Baker","raw_affiliation_strings":["Berkeley Heights, NJ, USA","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley Heights, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108392571"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":6.7497,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.97391304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"9","first_page":"608","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dup","display_name":"dup","score":0.9890607595443726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7316445112228394},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7156266570091248},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6394258737564087},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5417395830154419},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4217588007450104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3923284411430359},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35415491461753845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3388458490371704},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28540539741516113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.28331083059310913},{"id":"https://openalex.org/keywords/gene-duplication","display_name":"Gene duplication","score":0.11230292916297913},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08738964796066284}],"concepts":[{"id":"https://openalex.org/C48737797","wikidata":"https://www.wikidata.org/wiki/Q5315910","display_name":"dup","level":4,"score":0.9890607595443726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7316445112228394},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7156266570091248},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6394258737564087},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5417395830154419},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4217588007450104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3923284411430359},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35415491461753845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3388458490371704},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28540539741516113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28331083059310913},{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.11230292916297913},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08738964796066284},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2007.70720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2007.70720","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W642038236","https://openalex.org/W1496038746","https://openalex.org/W1698439592","https://openalex.org/W1964169783","https://openalex.org/W2026024229","https://openalex.org/W2028654948","https://openalex.org/W2066688923","https://openalex.org/W2096491586","https://openalex.org/W2109943392","https://openalex.org/W2115534035","https://openalex.org/W2121252285","https://openalex.org/W2128698639","https://openalex.org/W2128888088","https://openalex.org/W2138756793","https://openalex.org/W2139674137","https://openalex.org/W2157532207","https://openalex.org/W2158026392"],"related_works":["https://openalex.org/W2402520171","https://openalex.org/W3141501618","https://openalex.org/W2164529612","https://openalex.org/W1812865535","https://openalex.org/W2948552261","https://openalex.org/W2161368430","https://openalex.org/W2099969795","https://openalex.org/W3120493416","https://openalex.org/W2098192829","https://openalex.org/W3081644756"],"abstract_inverted_index":{"An":[0],"experiment":[1,100],"was":[2],"carried":[3],"out":[4],"by":[5],"a":[6,33,106],"group":[7],"of":[8,59,94],"scientists":[9],"to":[10,98,108],"compare":[11],"different":[12],"tools":[13],"and":[14,64,74,88,101],"techniques":[15],"for":[16,39,56],"detecting":[17],"duplicated":[18],"or":[19,52],"near-duplicated":[20],"source":[21],"code.":[22],"The":[23],"overall":[24],"comparative":[25],"results":[26,38,71,79],"are":[27,48,72],"presented":[28],"elsewhere.":[29],"This":[30],"paper":[31],"takes":[32],"closer":[34],"look":[35],"at":[36],"the":[37,50,53,70,78,92,99],"one":[40],"tool,":[41],"Dup,":[42],"which":[43],"finds":[44],"code":[45],"sections":[46],"that":[47,68],"textually":[49],"same":[51,54],"except":[55],"systematic":[57],"substitution":[58],"parameters":[60],"such":[61],"as":[62],"identifiers":[63],"constants.":[65],"Various":[66],"factors":[67],"influenced":[69],"identified":[73],"their":[75],"impact":[76],"on":[77],"is":[80],"assessed":[81],"via":[82],"rerunning":[83],"Dup":[84,95],"with":[85,96,111],"changed":[86],"options":[87],"modifications.":[89],"These":[90],"improve":[91],"performance":[93],"regard":[97],"could":[102],"be":[103,109],"incorporated":[104],"into":[105],"postprocessor":[107],"used":[110],"other":[112],"tools.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
