{"id":"https://openalex.org/W2899171197","doi":"https://doi.org/10.1145/3236024.3236068","title":"DeepSim: deep learning code functional similarity","display_name":"DeepSim: deep learning code functional similarity","publication_year":2018,"publication_date":"2018-10-26","ids":{"openalex":"https://openalex.org/W2899171197","doi":"https://doi.org/10.1145/3236024.3236068","mag":"2899171197"},"language":"en","primary_location":{"id":"doi:10.1145/3236024.3236068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236024.3236068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the 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/A5059053709","display_name":"Gang Zhao","orcid":"https://orcid.org/0000-0001-5985-6709"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gang Zhao","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103035835","display_name":"Jeff Huang","orcid":"https://orcid.org/0000-0003-1393-0752"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Huang","raw_affiliation_strings":["Texas A&M University, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059053709"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":41.5872,"has_fulltext":false,"cited_by_count":264,"citation_normalized_percentile":{"value":0.99753404,"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":"141","last_page":"151"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9889000058174133,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9815999865531921,"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/computer-science","display_name":"Computer science","score":0.7816809415817261},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6097604036331177},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.600390613079071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5118657946586609},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5065244436264038},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4518815279006958},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.4246354103088379},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3517284691333771},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.29710516333580017},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2748350501060486},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.26783695816993713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08005186915397644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816809415817261},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6097604036331177},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.600390613079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5118657946586609},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5065244436264038},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4518815279006958},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.4246354103088379},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3517284691333771},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29710516333580017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2748350501060486},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.26783695816993713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08005186915397644},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3236024.3236068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3236024.3236068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W125217267","https://openalex.org/W183494281","https://openalex.org/W1412775481","https://openalex.org/W1423339008","https://openalex.org/W1475493299","https://openalex.org/W1498436455","https://openalex.org/W1545038039","https://openalex.org/W1553894716","https://openalex.org/W1567790484","https://openalex.org/W1964169783","https://openalex.org/W1972466226","https://openalex.org/W1978777139","https://openalex.org/W1983316175","https://openalex.org/W1986601961","https://openalex.org/W2008085811","https://openalex.org/W2017212970","https://openalex.org/W2025768430","https://openalex.org/W2025791343","https://openalex.org/W2060055745","https://openalex.org/W2064675550","https://openalex.org/W2065053490","https://openalex.org/W2088479623","https://openalex.org/W2096491586","https://openalex.org/W2100495367","https://openalex.org/W2101606071","https://openalex.org/W2101832700","https://openalex.org/W2106568252","https://openalex.org/W2107697055","https://openalex.org/W2108629523","https://openalex.org/W2125260159","https://openalex.org/W2128782367","https://openalex.org/W2133564696","https://openalex.org/W2134092629","https://openalex.org/W2138756793","https://openalex.org/W2143960295","https://openalex.org/W2157532207","https://openalex.org/W2165739648","https://openalex.org/W2169952536","https://openalex.org/W2176412452","https://openalex.org/W2215690963","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2338839503","https://openalex.org/W2461136558","https://openalex.org/W2511803001","https://openalex.org/W2525778437","https://openalex.org/W2741705590","https://openalex.org/W2763000180","https://openalex.org/W2767717989","https://openalex.org/W2998704965","https://openalex.org/W3015970086","https://openalex.org/W3104227690","https://openalex.org/W3122078363","https://openalex.org/W3146803896","https://openalex.org/W4285719527","https://openalex.org/W4299828299","https://openalex.org/W4301168982","https://openalex.org/W6680532216"],"related_works":["https://openalex.org/W194942058","https://openalex.org/W2991900792","https://openalex.org/W2088986462","https://openalex.org/W1985388819","https://openalex.org/W3081644756","https://openalex.org/W2765199869","https://openalex.org/W1638297612","https://openalex.org/W2034043169","https://openalex.org/W4288111983","https://openalex.org/W2972453626"],"abstract_inverted_index":{"Measuring":[0],"code":[1,11,22,28,45,77,91,103,115],"similarity":[2,24,30,79],"is":[3,59],"fundamental":[4],"for":[5],"many":[6],"software":[7],"engineering":[8],"tasks,":[9],"e.g.,":[10],"search,":[12],"refactoring":[13],"and":[14,48,67],"reuse.":[15],"However,":[16],"most":[17],"existing":[18],"techniques":[19],"focus":[20],"on":[21,81],"syntactical":[23],"only,":[25],"while":[26],"measuring":[27],"functional":[29,78],"remains":[31],"a":[32,40,52,60,70,90],"challenging":[33],"problem.":[34],"In":[35],"this":[36,82,93],"paper,":[37],"we":[38,68],"propose":[39],"novel":[41],"approach":[42],"that":[43,75],"encodes":[44],"control":[46],"flow":[47,50],"data":[49],"into":[51],"semantic":[53],"matrix":[54],"in":[55],"which":[56,107],"each":[57],"element":[58],"high":[61],"dimensional":[62],"sparse":[63],"binary":[64,105],"feature":[65],"vector,":[66],"design":[69],"new":[71,94],"deep":[72],"learning":[73],"model":[74,95],"measures":[76],"based":[80],"representation.":[83],"By":[84],"concatenating":[85],"hidden":[86],"representations":[87],"learned":[88],"from":[89],"pair,":[92],"transforms":[96],"the":[97],"problem":[98],"of":[99],"detecting":[100],"functionally":[101,113],"similar":[102,114],"to":[104],"classification,":[106],"can":[108],"effectively":[109],"learn":[110],"patterns":[111],"between":[112],"with":[116],"very":[117],"different":[118],"syntactics.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":50},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":14}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}