{"id":"https://openalex.org/W2601737536","doi":"https://doi.org/10.1109/iwsc.2017.7880504","title":"Web-service for finding cloned files using b-bit minwise hashing","display_name":"Web-service for finding cloned files using b-bit minwise hashing","publication_year":2017,"publication_date":"2017-02-21","ids":{"openalex":"https://openalex.org/W2601737536","doi":"https://doi.org/10.1109/iwsc.2017.7880504","mag":"2601737536"},"language":"en","primary_location":{"id":"doi:10.1109/iwsc.2017.7880504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwsc.2017.7880504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 11th International Workshop on Software Clones (IWSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088839384","display_name":"Kaoru Ito","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaoru Ito","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031518343","display_name":"Takashi Ishio","orcid":"https://orcid.org/0000-0003-4106-699X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Ishio","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031083059","display_name":"Katsuro Inoue","orcid":"https://orcid.org/0000-0001-5424-0614"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuro Inoue","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987000226974487,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8276456594467163},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6886332035064697},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6869794130325317},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.6239303946495056},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5377912521362305},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5284543037414551},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4925914406776428},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.4471049904823303},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4350488483905792},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.41463702917099},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.41265174746513367},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3645660877227783},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15466603636741638},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13896825909614563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276456594467163},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6886332035064697},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6869794130325317},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.6239303946495056},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5377912521362305},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5284543037414551},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4925914406776428},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.4471049904823303},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4350488483905792},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.41463702917099},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.41265174746513367},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3645660877227783},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15466603636741638},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13896825909614563},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwsc.2017.7880504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwsc.2017.7880504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 11th International Workshop on Software Clones (IWSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G7916866909","display_name":"Program comprehension based on feature identification using hybrid program analysis","funder_award_id":"15H02683","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1225865527","https://openalex.org/W1983118588","https://openalex.org/W2012833704","https://openalex.org/W2043481183","https://openalex.org/W2140431670","https://openalex.org/W2151355400","https://openalex.org/W3143437309","https://openalex.org/W4230940751","https://openalex.org/W6627933761"],"related_works":["https://openalex.org/W2227807207","https://openalex.org/W2370014100","https://openalex.org/W4287264924","https://openalex.org/W3137108924","https://openalex.org/W1852009617","https://openalex.org/W2042819006","https://openalex.org/W2170165007","https://openalex.org/W1979110442","https://openalex.org/W2156660460","https://openalex.org/W2362866566"],"abstract_inverted_index":{"Source":[0],"code":[1,74],"reuse":[2,15],"is":[3,62,144],"a":[4,40,45,53,59,76,111,120,124,129,152],"common":[5],"practice":[6],"in":[7,33,135],"software":[8],"development.":[9],"Since":[10],"industrial":[11,65],"developers":[12,43,66],"may":[13,150],"accidentally":[14],"source":[16,21,31,36,50,73,125,133,138],"files":[17,32,134],"developed":[18],"by":[19],"open":[20,30,49,137],"software,":[22],"clone":[23,41,56],"detection":[24,57,113],"tools":[25],"are":[26,67],"used":[27],"to":[28,70,75,94],"detect":[29],"their":[34,72],"closed":[35],"project.":[37],"To":[38,82],"execute":[39],"detection,":[42],"need":[44],"database":[46,61],"of":[47,97,103,123,131,154],"existing":[48,136],"software.":[51,139],"While":[52],"web-service":[54],"providing":[55],"using":[58,99],"centralized":[60],"likely":[63],"useful,":[64],"not":[68],"allowed":[69],"submit":[71],"public":[77],"server":[78],"on":[79],"the":[80,84,104,107],"Internet.":[81],"solve":[83],"problem,":[85],"we":[86,109],"employ":[87],"b-bit":[88],"minwise":[89],"hashing":[90],"technique":[91],"that":[92],"enables":[93],"estimate":[95],"similarity":[96,149],"documents":[98],"only":[100],"hash":[101,121,141],"values":[102],"documents.":[105],"Using":[106],"method,":[108],"implemented":[110],"file-clone":[112],"web":[114],"service;":[115],"it":[116],"takes":[117],"as":[118],"input":[119],"value":[122],"file":[126],"and":[127],"returns":[128],"list":[130],"similar":[132],"Our":[140],"comparison":[142],"method":[143],"efficient,":[145],"although":[146],"an":[147],"estimated":[148],"have":[151],"margin":[153],"error.":[155]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
