{"id":"https://openalex.org/W2400997415","doi":"https://doi.org/10.1145/2901739.2901759","title":"A large-scale study on repetitiveness, containment, and composability of routines in open-source projects","display_name":"A large-scale study on repetitiveness, containment, and composability of routines in open-source projects","publication_year":2016,"publication_date":"2016-05-14","ids":{"openalex":"https://openalex.org/W2400997415","doi":"https://doi.org/10.1145/2901739.2901759","mag":"2400997415"},"language":"en","primary_location":{"id":"doi:10.1145/2901739.2901759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2901739.2901759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2901739.2901759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2901739.2901759","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065748190","display_name":"Anh Tuan Nguyen","orcid":"https://orcid.org/0000-0002-9235-4759"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anh Tuan Nguyen","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044339946","display_name":"Hoan Anh Nguyen","orcid":"https://orcid.org/0000-0002-6194-7930"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoan Anh Nguyen","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089000736","display_name":"Tien N. Nguyen","orcid":"https://orcid.org/0009-0006-7962-6090"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tien N. Nguyen","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"373"},"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":0.9980999827384949,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9957000017166138,"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/subroutine","display_name":"Subroutine","score":0.9579666256904602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925046682357788},{"id":"https://openalex.org/keywords/composability","display_name":"Composability","score":0.7489081025123596},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6583561301231384},{"id":"https://openalex.org/keywords/containment","display_name":"Containment (computer programming)","score":0.6064383387565613},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5542963743209839},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.5196341276168823},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5031902194023132},{"id":"https://openalex.org/keywords/program-slicing","display_name":"Program slicing","score":0.4996047019958496},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4809924364089966},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47406286001205444},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.458393931388855},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.43074753880500793},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3695230185985565},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3257940709590912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1121053397655487}],"concepts":[{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.9579666256904602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925046682357788},{"id":"https://openalex.org/C2778814252","wikidata":"https://www.wikidata.org/wiki/Q5156715","display_name":"Composability","level":2,"score":0.7489081025123596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6583561301231384},{"id":"https://openalex.org/C2777019822","wikidata":"https://www.wikidata.org/wiki/Q390066","display_name":"Containment (computer programming)","level":2,"score":0.6064383387565613},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5542963743209839},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.5196341276168823},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5031902194023132},{"id":"https://openalex.org/C91071405","wikidata":"https://www.wikidata.org/wiki/Q1413145","display_name":"Program slicing","level":3,"score":0.4996047019958496},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4809924364089966},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47406286001205444},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.458393931388855},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.43074753880500793},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3695230185985565},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3257940709590912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1121053397655487},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2901739.2901759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2901739.2901759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2901739.2901759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2901739.2901759","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2901739.2901759","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2901739.2901759","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1311026310","display_name":"CI-EN: Boa: Enhancing Infrastructure for Studying Software and its Evolution at a Large Scale","funder_award_id":"1513263","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2582085846","display_name":null,"funder_award_id":"CCF-1320578","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3707049760","display_name":"SHF: Large: Collaborative Research: Exploiting the Naturalness of Software","funder_award_id":"1413927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4427534540","display_name":"Improving Embedded System Education with Software Engineering Methodologies","funder_award_id":"0737029","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5039213523","display_name":"TWC: Small: Detection and Prevention of Prior Known Software Security Vulnerabilities","funder_award_id":"1223828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5742996192","display_name":null,"funder_award_id":"CCF-1349153","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6025416964","display_name":"SHF: Small: Find and Fix Similar Software Bugs","funder_award_id":"1018600","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6376484334","display_name":null,"funder_award_id":"CCF-1518897, CNS-1513263, CCF-1413927, CCF-1320578, CCF-1349153, TWC-1223828, CCF-1018600, and CCLI-0737029","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6960990826","display_name":null,"funder_award_id":"CCF-1518897, CNS-1513263, CCF-1413927, CCF-1320578, CCF-1349153, TWC-1223828, CCF-1018600, CCLI-0737029","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8311159335","display_name":"SHF: Large:Collaborative Research: Inferring Software Specifications from Open Source Repositories by Leveraging Data and Collective Community Expertise","funder_award_id":"1518897","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8438043792","display_name":"SHF:Small: Build Code Maintenance and Detecting, Testing, Locating Configuration and Build Errors","funder_award_id":"1320578","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G985604859","display_name":"EAGER: Boa: A Community Research Infrastructure for Mining Software Repositories","funder_award_id":"1349153","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2400997415.pdf","grobid_xml":"https://content.openalex.org/works/W2400997415.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W90447038","https://openalex.org/W1519220202","https://openalex.org/W1576818901","https://openalex.org/W1593203335","https://openalex.org/W1970607969","https://openalex.org/W1977971855","https://openalex.org/W1988643845","https://openalex.org/W1991411614","https://openalex.org/W2006996028","https://openalex.org/W2014577207","https://openalex.org/W2025677988","https://openalex.org/W2025791343","https://openalex.org/W2039168567","https://openalex.org/W2048668881","https://openalex.org/W2055936450","https://openalex.org/W2059215200","https://openalex.org/W2066688923","https://openalex.org/W2071088932","https://openalex.org/W2074529754","https://openalex.org/W2090432523","https://openalex.org/W2096491586","https://openalex.org/W2097001189","https://openalex.org/W2099677903","https://openalex.org/W2099866050","https://openalex.org/W2101832700","https://openalex.org/W2104301886","https://openalex.org/W2107697055","https://openalex.org/W2109943392","https://openalex.org/W2117227762","https://openalex.org/W2117642462","https://openalex.org/W2121818394","https://openalex.org/W2125260159","https://openalex.org/W2126359798","https://openalex.org/W2126399635","https://openalex.org/W2128698639","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2132944054","https://openalex.org/W2134829794","https://openalex.org/W2136128399","https://openalex.org/W2138756793","https://openalex.org/W2140609933","https://openalex.org/W2142403498","https://openalex.org/W2143051121","https://openalex.org/W2143960295","https://openalex.org/W2144344516","https://openalex.org/W2145373440","https://openalex.org/W2147088720","https://openalex.org/W2149864547","https://openalex.org/W2153150125","https://openalex.org/W2154021641","https://openalex.org/W2157532207","https://openalex.org/W2164233915","https://openalex.org/W2166732561","https://openalex.org/W3098037594"],"related_works":["https://openalex.org/W205579818","https://openalex.org/W2093568763","https://openalex.org/W2400997415","https://openalex.org/W1841737286","https://openalex.org/W2002897948","https://openalex.org/W2599733989","https://openalex.org/W2389146241","https://openalex.org/W2153923555","https://openalex.org/W1657001649","https://openalex.org/W2388410288"],"abstract_inverted_index":{"Source":[0],"code":[1,37,228],"in":[2,64,125,146,161,186,207],"software":[3],"systems":[4],"has":[5],"been":[6],"shown":[7],"to":[8,74,238],"have":[9,196],"a":[10,26,44,65,76,95,158,179,182,187,208],"good":[11],"degree":[12],"of":[13,35,48,98,105,121,141,153,175,193,198,205,235],"repetitiveness":[14,170],"at":[15,38,130],"the":[16,30,39,69,87,99,113,142],"lexical,":[17],"syntactical,":[18],"and":[19,33,78,103,139,160,171],"API":[20],"usage":[21],"levels.":[22],"This":[23],"paper":[24],"presents":[25],"large-scale":[27],"study":[28],"on":[29],"repetitiveness,":[31],"containment,":[32],"composability":[34],"source":[36],"semantic":[40],"level.":[41],"We":[42,91,134,214,230],"collected":[43,215],"large":[45],"dataset":[46],"consisting":[47],"9,224":[49],"Java":[50],"projects":[51,128],"with":[52,58,81,118,129],"2.79M":[53],"class":[54],"flies,":[55],"17.54M":[56],"methods":[57],"187M":[59],"SLOCs.":[60],"For":[61],"each":[62],"method":[63],"project,":[66,96],"we":[67,189],"build":[68],"program":[70],"dependency":[71],"graph":[72],"(PDG)":[73],"represent":[75],"routine,":[77],"compare":[79],"PDGs":[80],"one":[82],"another":[83],"as":[84,86,151,224],"well":[85],"subgraphs":[88],"within":[89,94,157],"them.":[90],"found":[92,136,190],"that":[93,137,191],"12.1%":[97],"routines":[100,114,143,195],"are":[101,115,144],"repeated,":[102],"most":[104,131],"them":[106,122],"repeat":[107],"from":[108],"2--7":[109],"times.":[110,133],"As":[111],"entirety,":[112],"quite":[116],"project-specific":[117],"only":[119],"3.3%":[120],"exactly":[123],"repeating":[124],"1--1":[126],"other":[127,147,154,162],"8":[132],"also":[135,231],"26.1%":[138],"7.27%":[140],"contained":[145],"routine(s),":[148],"i.e.,":[149],"implemented":[150],"part":[152],"routine(s)":[155],"elsewhere":[156],"project":[159],"projects,":[163],"respectively.":[164],"Except":[165],"for":[166,227],"trivial":[167],"routines,":[168],"their":[169,176,199],"containment":[172],"is":[173],"independent":[174],"complexity.":[177],"Defining":[178],"subroutine":[180],"via":[181],"per-variable":[183],"slicing":[184],"subgraph":[185],"PDG,":[188],"14.3%":[192],"all":[194,197],"subroutines":[200,206,218],"repeated.":[201],"A":[202],"high":[203],"percentage":[204],"routine":[209],"can":[210],"be":[211],"found/reused":[212],"elsewhere.":[213],"8,764,971":[216],"unique":[217,221],"(with":[219],"323,564":[220],"JDK":[222],"subroutines)":[223],"basic":[225],"units":[226],"searching/synthesis.":[229],"provide":[232],"practical":[233],"implications":[234],"our":[236],"findings":[237],"automated":[239],"tools.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
