{"id":"https://openalex.org/W3197255311","doi":"https://doi.org/10.18293/seke2021-032","title":"Leveraging Compiler Optimization for Code Clone Detection","display_name":"Leveraging Compiler Optimization for Code Clone Detection","publication_year":2021,"publication_date":"2021-07-09","ids":{"openalex":"https://openalex.org/W3197255311","doi":"https://doi.org/10.18293/seke2021-032","mag":"3197255311"},"language":"en","primary_location":{"id":"doi:10.18293/seke2021-032","is_oa":true,"landing_page_url":"http://doi.org/10.18293/seke2021-032","pdf_url":"https://doi.org/10.18293/seke2021-032","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.18293/seke2021-032","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108635473","display_name":"Shirish Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shirish Singh","raw_affiliation_strings":["Dept. of Computer Science Columbia University, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108635473"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.5508,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72955516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2021","issue":null,"first_page":"516","last_page":"521"},"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":0.9976999759674072,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8734661340713501},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8554123640060425},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.613241970539093},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5918243527412415},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.571269154548645},{"id":"https://openalex.org/keywords/redundant-code","display_name":"Redundant code","score":0.5543844699859619},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5448633432388306},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5114966630935669},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4816912114620209},{"id":"https://openalex.org/keywords/dead-code-elimination","display_name":"Dead code elimination","score":0.4775841534137726},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.45757150650024414},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4561426639556885},{"id":"https://openalex.org/keywords/dead-code","display_name":"Dead code","score":0.4500555992126465},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4397156238555908},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4286346137523651},{"id":"https://openalex.org/keywords/software-maintenance","display_name":"Software maintenance","score":0.4190226197242737},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.2663121819496155},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17801061272621155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734661340713501},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8554123640060425},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.613241970539093},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5918243527412415},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.571269154548645},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.5543844699859619},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5448633432388306},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5114966630935669},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4816912114620209},{"id":"https://openalex.org/C2144512","wikidata":"https://www.wikidata.org/wiki/Q1143090","display_name":"Dead code elimination","level":5,"score":0.4775841534137726},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.45757150650024414},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4561426639556885},{"id":"https://openalex.org/C47434764","wikidata":"https://www.wikidata.org/wiki/Q1770035","display_name":"Dead code","level":5,"score":0.4500555992126465},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4397156238555908},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4286346137523651},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.4190226197242737},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2663121819496155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17801061272621155},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/seke2021-032","is_oa":true,"landing_page_url":"http://doi.org/10.18293/seke2021-032","pdf_url":"https://doi.org/10.18293/seke2021-032","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18293/seke2021-032","is_oa":true,"landing_page_url":"http://doi.org/10.18293/seke2021-032","pdf_url":"https://doi.org/10.18293/seke2021-032","source":{"id":"https://openalex.org/S4220650826","display_name":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","issn_l":"2325-9000","issn":["2325-9000","2325-9086"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conferences on Software Engineering and Knowledge Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197255311.pdf","grobid_xml":"https://content.openalex.org/works/W3197255311.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2128888088","https://openalex.org/W2138756793","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2511803001","https://openalex.org/W2794872936","https://openalex.org/W2795143051","https://openalex.org/W2795197718","https://openalex.org/W2899171197","https://openalex.org/W2903211944","https://openalex.org/W2926178846","https://openalex.org/W2942293597","https://openalex.org/W2964150020","https://openalex.org/W3012514498","https://openalex.org/W3015439160","https://openalex.org/W3045279034","https://openalex.org/W3049230093","https://openalex.org/W3101433256","https://openalex.org/W3105540914","https://openalex.org/W3107551709","https://openalex.org/W3196001856","https://openalex.org/W4288080275"],"related_works":["https://openalex.org/W2161969548","https://openalex.org/W4244016640","https://openalex.org/W3008325674","https://openalex.org/W2036000779","https://openalex.org/W2112669344","https://openalex.org/W1539844444","https://openalex.org/W2011669306","https://openalex.org/W2045218056","https://openalex.org/W4231368563","https://openalex.org/W2341598935"],"abstract_inverted_index":{"Finding":[0],"similar":[1,46,50,86],"code":[2,14,19,22,47,70,145],"in":[3,28,87,91],"software":[4,9],"systems":[5],"can":[6,63,93,123],"guide":[7],"several":[8],"engineering":[10],"tasks":[11],"such":[12],"as":[13],"maintenance,":[15],"program":[16,131],"understanding,":[17],"and":[18,48],"reuse.":[20],"Similar":[21],"detection":[23],"has":[24],"been":[25],"actively":[26],"studied":[27],"the":[29,32,60,75,79,83,99,105,111,130,143],"past.":[30],"In":[31],"paper,":[33],"we":[34],"propose":[35],"a":[36],"novel":[37],"approach":[38],"that":[39,59,120],"leverages":[40],"compiler":[41,61],"optimizations":[42,62],"to":[43,66,97,109,126],"transform":[44],"semantically":[45],"detect":[49],"programs.":[51,100],"The":[52,89,116],"key":[53],"observation":[54],"of":[55,113,138],"our":[56,114,121],"work":[57],"is":[58,135],"be":[64,95],"used":[65,96],"smooth":[67],"out":[68],"source":[69,144],"level":[71,146],"idiosyncrasies":[72],"introduced":[73],"by":[74],"developers,":[76],"thus":[77],"making":[78],"optimized":[80],"programs,":[81],"for":[82],"same":[84],"task,":[85,133],"structure.":[88],"similarity":[90],"structure":[92],"then":[94],"classify":[98],"We":[101],"conducted":[102],"experiments":[103],"on":[104,129],"Google":[106],"CodeJam":[107],"dataset":[108],"demonstrate":[110],"effectiveness":[112],"approach.":[115],"experimental":[117],"results":[118],"show":[119],"technique":[122],"achieve":[124],"up":[125],"85%":[127],"accuracy":[128],"classification":[132],"which":[134],"an":[136],"improvement":[137],"more":[139],"than":[140],"25%":[141],"over":[142],"classification.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
