{"id":"https://openalex.org/W2143960295","doi":"https://doi.org/10.1145/1882291.1882315","title":"A study of the uniqueness of source code","display_name":"A study of the uniqueness of source code","publication_year":2010,"publication_date":"2010-11-07","ids":{"openalex":"https://openalex.org/W2143960295","doi":"https://doi.org/10.1145/1882291.1882315","mag":"2143960295"},"language":"en","primary_location":{"id":"doi:10.1145/1882291.1882315","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882291.1882315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighteenth 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/A5064238062","display_name":"Mark Gabel","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Gabel","raw_affiliation_strings":["University of California at Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077610917","display_name":"Zhendong Su","orcid":"https://orcid.org/0000-0002-2970-1391"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhendong Su","raw_affiliation_strings":["University of California at Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064238062"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":26.4238,"has_fulltext":false,"cited_by_count":223,"citation_normalized_percentile":{"value":0.99432912,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.678249716758728},{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.6044566035270691},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5278156995773315},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5195227265357971},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4304543137550354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15518003702163696},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.059087902307510376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678249716758728},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.6044566035270691},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5278156995773315},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5195227265357971},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4304543137550354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15518003702163696},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.059087902307510376},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1882291.1882315","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1882291.1882315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighteenth ACM SIGSOFT international symposium on Foundations of software engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.6567","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.6567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucdavis.edu/~su/publications/fse10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5299999713897705,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1576818901","https://openalex.org/W1736209534","https://openalex.org/W2021242474","https://openalex.org/W2066521842","https://openalex.org/W2080579313","https://openalex.org/W2084887015","https://openalex.org/W2099677903","https://openalex.org/W2109943392","https://openalex.org/W2111295912","https://openalex.org/W2122947685","https://openalex.org/W2128782367","https://openalex.org/W2132944054","https://openalex.org/W2134092629","https://openalex.org/W2136099030","https://openalex.org/W2138756793","https://openalex.org/W2149864547","https://openalex.org/W2165027873","https://openalex.org/W2172244770","https://openalex.org/W2420370654","https://openalex.org/W6637593291"],"related_works":["https://openalex.org/W4243252198","https://openalex.org/W2118300983","https://openalex.org/W2112962394","https://openalex.org/W3137189469","https://openalex.org/W4235530921","https://openalex.org/W2382501300","https://openalex.org/W3162240892","https://openalex.org/W270927586","https://openalex.org/W283806354","https://openalex.org/W2137137834"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,6,10,17,28,61,99,105,131],"results":[4],"of":[5,9,12,19,22,31,40,44,51,55,74,82,97,102,107,117,124,137,147,160],"first":[7],"study":[8,93],"uniqueness":[11,18],"source":[13,23,45,113],"code.":[14,46,114],"We":[15,90],"define":[16],"a":[20,38,53,79,95,144],"unit":[21],"code":[24],"with":[25,37],"respect":[26],"to":[27,63,130,158,167],"entire":[29],"body":[30],"written":[32],"software,":[33],"which":[34,64,103,110],"we":[35,86,111,154,163],"approximate":[36],"corpus":[39],"420":[41],"million":[42],"lines":[43],"Our":[47,115],"high-level":[48],"methodology":[49],"consists":[50],"examining":[52],"collection":[54],"6,000":[56],"software":[57,140],"projects":[58],"and":[59,142,170],"measuring":[60],"degree":[62],"each":[65],"project":[66],"can":[67],"be":[68,159],"\u2018assembled":[69],"\u2019":[70,84],"solely":[71],"from":[72],"portions":[73],"this":[75],"corpus,":[76],"thus":[77],"providing":[78,127],"precise":[80],"measure":[81],"\u2018uniqueness":[83],"that":[85],"call":[87],"syntactic":[88],"redundancy.":[89],"parameterized":[91],"our":[92],"over":[94],"variety":[96],"variables,":[98],"most":[100],"important":[101],"being":[104],"level":[106,146],"granularity":[108,138],"at":[109,134,143],"view":[112],"suite":[116],"experiments":[118],"together":[119],"consumed":[120],"approximately":[121],"four":[122],"months":[123],"CPU":[125],"time,":[126],"quantitative":[128],"answers":[129],"following":[132],"questions:":[133],"what":[135],"levels":[136],"is":[139,151],"unique,":[141],"given":[145],"granularity,":[148],"how":[149],"unique":[150],"software?":[152],"While":[153],"believe":[155],"these":[156],"questions":[157],"intrinsic":[161],"interest,":[162],"discuss":[164],"possible":[165],"applications":[166],"genetic":[168],"programming":[169],"developer":[171],"productivity":[172],"tools.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
