{"id":"https://openalex.org/W2109943392","doi":"https://doi.org/10.1109/wcre.1995.514697","title":"On finding duplication and near-duplication in large software systems","display_name":"On finding duplication and near-duplication in large software systems","publication_year":2002,"publication_date":"2002-11-19","ids":{"openalex":"https://openalex.org/W2109943392","doi":"https://doi.org/10.1109/wcre.1995.514697","mag":"2109943392"},"language":"en","primary_location":{"id":"doi:10.1109/wcre.1995.514697","doi":"https://doi.org/10.1109/wcre.1995.514697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcre.1995.514697","pdf_url":null,"source":{"id":"https://openalex.org/S4210227819","display_name":"Working Conference on Reverse Engineering (WCRE)","issn_l":"1095-1350","issn":["1095-1350","2375-5369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2nd Working Conference on Reverse Engineering","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2109943392"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"B.S. Baker","raw_affiliation_strings":["AT&T Bell Laboratories Engineering Research Center, Murray Hill, NJ, USA","AT&T Bell Laboratories,, Murray Hill, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Bell Laboratories Engineering Research Center, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Bell Laboratories,, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108392571"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":19.3121,"has_fulltext":false,"cited_by_count":724,"citation_normalized_percentile":{"value":0.99562562,"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":"86","last_page":"95"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.0,"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/code-duplication","display_name":"code duplication","score":0.8870000243186951},{"id":"https://openalex.org/keywords/software-reengineering","display_name":"software reengineering","score":0.5529999732971191},{"id":"https://openalex.org/keywords/large-scale-software-systems","display_name":"large software systems","score":0.7009999752044678},{"id":"https://openalex.org/keywords/software-debugging","display_name":"software debugging","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C48737797","wikidata":"https://www.wikidata.org/wiki/Q5315910","display_name":"dup","level":4,"score":0.8700729608535767},{"id":"https://openalex.org/C7602840","wikidata":"https://www.wikidata.org/wiki/Q746284","display_name":"Gene duplication","level":3,"score":0.7457298040390015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648918390274048},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6184548735618591},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5398669838905334},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.49476951360702515},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.4742885231971741},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.44928786158561707},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39968761801719666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3952716588973999},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15714240074157715},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08751949667930603},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wcre.1995.514697","doi":"https://doi.org/10.1109/wcre.1995.514697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcre.1995.514697","pdf_url":null,"source":{"id":"https://openalex.org/S4210227819","display_name":"Working Conference on Reverse Engineering (WCRE)","issn_l":"1095-1350","issn":["1095-1350","2375-5369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2nd Working Conference on Reverse Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.133.6440","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.6440","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/wcre95-baker.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W220982185","https://openalex.org/W1609518033","https://openalex.org/W1964169783","https://openalex.org/W1973828066","https://openalex.org/W1974930421","https://openalex.org/W1976892921","https://openalex.org/W1997953464","https://openalex.org/W2013007594","https://openalex.org/W2017661493","https://openalex.org/W2026024229","https://openalex.org/W2053978297","https://openalex.org/W2062314640","https://openalex.org/W2087920662","https://openalex.org/W2101811680","https://openalex.org/W2107745473","https://openalex.org/W2118024368","https://openalex.org/W2121252285","https://openalex.org/W3000604864","https://openalex.org/W4255982026"],"related_works":["https://openalex.org/W7096045724","https://openalex.org/W2102543548","https://openalex.org/W2128698639","https://openalex.org/W1587241967","https://openalex.org/W7095224512","https://openalex.org/W7095232417","https://openalex.org/W7005236776","https://openalex.org/W17908730","https://openalex.org/W1593203335","https://openalex.org/W2809635894"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"how":[3],"a":[4,19],"program":[5],"called":[6],"dup":[7,71,82],"can":[8],"be":[9,84,101],"used":[10],"to":[11,83,114,117],"locate":[12],"instances":[13],"of":[14,28,41,44,56,74,97,106,110],"duplication":[15,89,107],"or":[16],"near-duplication":[17],"in":[18],"software":[20,79],"system.":[21],"Dup":[22],"reports":[23],"both":[24,85],"textually":[25,36],"identical":[26],"sections":[27,31,55,96],"code":[29,57,98],"and":[30,47,90,119],"that":[32,58,99],"are":[33,59],"the":[34,60,111],"same":[35,61],"except":[37,62],"for":[38,49,63],"systematic":[39],"substitution":[40],"one":[42],"set":[43],"variable":[45],"names":[46],"constants":[48],"another.":[50],"Further":[51],"processing":[52],"locates":[53],"longer":[54],"other":[64],"small":[65],"modifications.":[66],"Experimental":[67],"results":[68],"from":[69,76],"running":[70],"on":[72],"millions":[73],"lines":[75],"two":[77],"large":[78],"systems":[80],"show":[81],"effective":[86],"at":[87],"locating":[88],"fast.":[91],"Applications":[92],"could":[93],"include":[94,115],"identifying":[95],"should":[100],"replaced":[102],"by":[103],"procedures,":[104],"elimination":[105],"during":[108],"reengineering":[109],"system,":[112],"redocumentation":[113],"references":[116],"copies,":[118],"debugging.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":36},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":38},{"year":2014,"cited_by_count":36},{"year":2013,"cited_by_count":51},{"year":2012,"cited_by_count":45}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}