{"id":"https://openalex.org/W4410356619","doi":"https://doi.org/10.1145/3672608.3707807","title":"A Two-stage Approach for Structurally-similar Cross-language Code-pair Detection","display_name":"A Two-stage Approach for Structurally-similar Cross-language Code-pair Detection","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410356619","doi":"https://doi.org/10.1145/3672608.3707807"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707807","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","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/A5036512030","display_name":"Feng Dai","orcid":"https://orcid.org/0009-0006-0995-2536"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Feng Dai","raw_affiliation_strings":["The University of Tokyo, Bunkyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103031063","display_name":"Shigeru Chiba","orcid":"https://orcid.org/0000-0002-1058-5941"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I153327471","display_name":"Bunkyo University","ror":"https://ror.org/053h75930","country_code":"JP","type":"education","lineage":["https://openalex.org/I153327471"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeru Chiba","raw_affiliation_strings":["The University of Tokyo, Bunkyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036512030"],"corresponding_institution_ids":["https://openalex.org/I153327471","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16111706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1657","last_page":"1665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9988999962806702,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9883999824523926,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9782000184059143,"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":0.6983422636985779},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5491268634796143},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5065451860427856},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49051326513290405},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09770125150680542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983422636985779},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5491268634796143},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5065451860427856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49051326513290405},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09770125150680542},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672608.3707807","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2094622286","https://openalex.org/W2128782367","https://openalex.org/W2138756793","https://openalex.org/W2157331557","https://openalex.org/W2165739648","https://openalex.org/W2296036069","https://openalex.org/W2298313545","https://openalex.org/W2533695286","https://openalex.org/W2585680471","https://openalex.org/W2743862976","https://openalex.org/W2767717989","https://openalex.org/W2796335629","https://openalex.org/W2955127311","https://openalex.org/W2955426500","https://openalex.org/W2964150020","https://openalex.org/W3000135256","https://openalex.org/W3098605233","https://openalex.org/W3167900421","https://openalex.org/W4221166942","https://openalex.org/W4301168982","https://openalex.org/W4312465319","https://openalex.org/W4313563720","https://openalex.org/W4398186403"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"A":[0],"fast":[1],"and":[2,52,74,89],"reliable":[3],"tool":[4],"to":[5,49,83],"detect":[6],"structurally-similar":[7,70,95],"cross-language":[8,64,96],"code":[9,32,97],"pairs":[10,33,98],"is":[11],"crucial":[12],"when":[13],"maintaining":[14],"large":[15],"projects":[16],"across":[17],"different":[18],"programming":[19],"languages.":[20],"In":[21],"this":[22,79],"paper,":[23],"we":[24],"present":[25],"a":[26,36,62,85],"new":[27,63],"tool1":[28],"for":[29,57],"detecting":[30,94],"such":[31],"by":[34],"adopting":[35],"two-stage":[37],"approach.":[38],"Our":[39],"approach":[40,77],"first":[41],"uses":[42,53],"models":[43],"trained":[44],"on":[45,78],"two-level":[46],"generic":[47],"ASTs":[48],"filter":[50],"candidates,":[51],"tree-based":[54],"editing-distance":[55],"algorithm":[56],"accurate":[58],"comparison.":[59],"We":[60,81],"create":[61],"dataset,":[65],"including":[66],"Java-Python,":[67],"Java-C,":[68],"Python-C":[69],"method":[71],"body":[72],"pairs,":[73],"evaluate":[75],"our":[76],"dataset.":[80],"manage":[82],"obtain":[84],"much":[86],"faster":[87],"speed":[88],"similar":[90],"detection":[91],"accuracy":[92],"in":[93],"compared":[99],"with":[100],"the":[101],"state-of-the-art":[102],"technique.":[103]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}