{"id":"https://openalex.org/W3090530797","doi":"https://doi.org/10.1145/3377811.3380416","title":"Near-duplicate detection in web app model inference","display_name":"Near-duplicate detection in web app model inference","publication_year":2020,"publication_date":"2020-06-27","ids":{"openalex":"https://openalex.org/W3090530797","doi":"https://doi.org/10.1145/3377811.3380416","mag":"3090530797"},"language":"en","primary_location":{"id":"doi:10.1145/3377811.3380416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377811.3380416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering","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/A5109474506","display_name":"Rahulkrishna Yandrapally","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rahulkrishna Yandrapally","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058345649","display_name":"Andrea Stocco","orcid":"https://orcid.org/0000-0001-8956-3894"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrea Stocco","raw_affiliation_strings":["Universit\u00e0 della Svizzera italiana, Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana, Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023086966","display_name":"Ali Mesbah","orcid":"https://orcid.org/0000-0002-8783-7967"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ali Mesbah","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7671,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95087402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9997000098228455,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9965999722480774,"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/T10260","display_name":"Software Engineering Research","score":0.9922999739646912,"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":0.8186144828796387},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6467351913452148},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6281536817550659},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5620720386505127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4979977607727051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47683945298194885},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4312765598297119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41491806507110596},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40465104579925537},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2791319489479065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186144828796387},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6467351913452148},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6281536817550659},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5620720386505127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4979977607727051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47683945298194885},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4312765598297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41491806507110596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40465104579925537},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2791319489479065},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377811.3380416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377811.3380416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on 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":49,"referenced_works":["https://openalex.org/W89570574","https://openalex.org/W106254352","https://openalex.org/W133698269","https://openalex.org/W1508506413","https://openalex.org/W1647641001","https://openalex.org/W1647671624","https://openalex.org/W2011539648","https://openalex.org/W2012833704","https://openalex.org/W2021963610","https://openalex.org/W2025635041","https://openalex.org/W2028509346","https://openalex.org/W2040975718","https://openalex.org/W2043034431","https://openalex.org/W2043042437","https://openalex.org/W2048236564","https://openalex.org/W2049365470","https://openalex.org/W2064716575","https://openalex.org/W2085922539","https://openalex.org/W2101311572","https://openalex.org/W2105994593","https://openalex.org/W2107211792","https://openalex.org/W2113867182","https://openalex.org/W2119174985","https://openalex.org/W2124386111","https://openalex.org/W2124722556","https://openalex.org/W2125000816","https://openalex.org/W2131241448","https://openalex.org/W2133471969","https://openalex.org/W2133665775","https://openalex.org/W2137313854","https://openalex.org/W2139532006","https://openalex.org/W2152565070","https://openalex.org/W2153273516","https://openalex.org/W2162495634","https://openalex.org/W2170505850","https://openalex.org/W2185917628","https://openalex.org/W2194917080","https://openalex.org/W2397104696","https://openalex.org/W2408216925","https://openalex.org/W2514303331","https://openalex.org/W2523673022","https://openalex.org/W2600031682","https://openalex.org/W2898893292","https://openalex.org/W2968540777","https://openalex.org/W2999905431","https://openalex.org/W3041537557","https://openalex.org/W3102003703","https://openalex.org/W3173108600","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W4321636575","https://openalex.org/W2613685774","https://openalex.org/W3112355890","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W1986418932"],"abstract_inverted_index":{"Automated":[0],"web":[1,9,142,150,166],"testing":[2,19],"techniques":[3,134],"infer":[4],"models":[5,44],"from":[6,91,97,135],"a":[7,18,86,161],"given":[8,165],"app,":[10],"which":[11],"are":[12,33,47],"used":[13,73],"for":[14,120,163],"test":[15],"generation.":[16],"From":[17],"viewpoint,":[20],"such":[21],"an":[22],"inferred":[23,45],"model":[24,77,162],"should":[25],"contain":[26],"the":[27,38,54,66,115,155,174],"minimal":[28],"set":[29],"of":[30,53,69,89,94,117],"states":[31],"that":[32,113,171],"distinct,":[34],"yet,":[35],"adequately":[36],"cover":[37],"app's":[39],"main":[40],"functionalities.":[41],"In":[42],"practice,":[43],"automatically":[46,159],"affected":[48],"by":[49,60,84],"near-duplicates,":[50],"i.e.,":[51],"replicas":[52],"same":[55],"functional":[56,82,185],"webpage":[57],"differing":[58],"only":[59],"small":[61],"insignificant":[62],"changes.":[63],"We":[64,79,109,124],"present":[65],"first":[67,80],"study":[68,153],"near-duplicate":[70,132],"detection":[71,122,133],"algorithms":[72],"in":[74,158],"within":[75,187],"app":[76],"inference.":[78],"characterize":[81],"near-duplicates":[83,186],"classifying":[85],"random":[87],"sample":[88],"state-pairs,":[90],"493k":[92],"pairs":[93],"webpages":[95],"obtained":[96],"over":[98],"6,000":[99],"websites,":[100],"into":[101],"three":[102,136],"categories,":[103],"namely":[104],"clone,":[105],"near-duplicate,":[106],"and":[107,144],"distinct.":[108],"systematically":[110],"compute":[111],"thresholds":[112,128],"define":[114],"boundaries":[116],"these":[118,127],"categories":[119],"each":[121],"technique.":[123],"then":[125],"use":[126],"to":[129,181],"evaluate":[130],"10":[131],"different":[137],"domains,":[138],"namely,":[139],"information":[140],"retrieval,":[141],"testing,":[143],"computer":[145],"vision":[146],"on":[147],"nine":[148],"open-source":[149],"apps.":[151],"Our":[152,168],"highlights":[154],"challenges":[156],"posed":[157],"inferring":[160],"any":[164],"app.":[167],"findings":[169],"show":[170],"even":[172],"with":[173],"best":[175],"thresholds,":[176],"no":[177],"algorithm":[178],"is":[179],"able":[180],"accurately":[182],"detect":[183],"all":[184],"apps,":[188],"without":[189],"sacrificing":[190],"coverage.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}