{"id":"https://openalex.org/W2362126069","doi":"https://doi.org/10.1145/2884781.2884796","title":"CUSTODES","display_name":"CUSTODES","publication_year":2016,"publication_date":"2016-05-13","ids":{"openalex":"https://openalex.org/W2362126069","doi":"https://doi.org/10.1145/2884781.2884796","mag":"2362126069"},"language":"en","primary_location":{"id":"doi:10.1145/2884781.2884796","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th 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/A5034057959","display_name":"Shing-Chi Cheung","orcid":"https://orcid.org/0000-0002-3508-7172"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shing-Chi Cheung","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622539","display_name":"Wanjun Chen","orcid":"https://orcid.org/0000-0002-4937-1692"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wanjun Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084868951","display_name":"Yepang Liu","orcid":"https://orcid.org/0000-0001-8147-8126"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yepang Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052203980","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-6299-4704"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"464","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13197","display_name":"Spreadsheets and End-User Computing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T13197","display_name":"Spreadsheets and End-User Computing","score":0.9998000264167786,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9677000045776367,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534887790679932},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6653341054916382},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6390402913093567},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5704390406608582},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5456593036651611},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5301367044448853},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5069901943206787},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.43091824650764465},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42659637331962585},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42195022106170654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41297605633735657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34687525033950806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24549227952957153},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15463465452194214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10452133417129517},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0803145170211792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534887790679932},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6653341054916382},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6390402913093567},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5704390406608582},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5456593036651611},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5301367044448853},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5069901943206787},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.43091824650764465},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42659637331962585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42195022106170654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41297605633735657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34687525033950806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24549227952957153},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15463465452194214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10452133417129517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0803145170211792},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2884781.2884796","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884781.2884796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-79177","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=0270-5257&rft.volume=14&rft.issue=&rft.date=2016&rft.spage=464&rft.aulast=Cheung&rft.aufirst=S.-C.&rft.atitle=CUSTODES%3A+Automatic+spreadsheet+cell+clustering+and+smell+detection+using+strong+and+weak+features&rft.title=IEEE+International+Conference+on+Software+Engineering","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1369807653","display_name":null,"funder_award_id":"HKSAR RGC GRF 611811","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W21294403","https://openalex.org/W1532325895","https://openalex.org/W1533980247","https://openalex.org/W1551326568","https://openalex.org/W1594983789","https://openalex.org/W1657060916","https://openalex.org/W1711582795","https://openalex.org/W1804662178","https://openalex.org/W1808011207","https://openalex.org/W1958332869","https://openalex.org/W1970665021","https://openalex.org/W1987407028","https://openalex.org/W2003889154","https://openalex.org/W2006499508","https://openalex.org/W2010329982","https://openalex.org/W2010598806","https://openalex.org/W2022114557","https://openalex.org/W2026539153","https://openalex.org/W2080982416","https://openalex.org/W2093495548","https://openalex.org/W2095148351","https://openalex.org/W2097435116","https://openalex.org/W2111469656","https://openalex.org/W2112338634","https://openalex.org/W2128049346","https://openalex.org/W2129386590","https://openalex.org/W2133337392","https://openalex.org/W2134766084","https://openalex.org/W2135473121","https://openalex.org/W2137023796","https://openalex.org/W2138468895","https://openalex.org/W2140190241","https://openalex.org/W2144182447","https://openalex.org/W2150296413","https://openalex.org/W2150704968","https://openalex.org/W2152376725","https://openalex.org/W2153887189","https://openalex.org/W2156400118","https://openalex.org/W2171561334","https://openalex.org/W2186428165","https://openalex.org/W2200894932","https://openalex.org/W2408009809","https://openalex.org/W2434205482","https://openalex.org/W2966207845","https://openalex.org/W3145828585","https://openalex.org/W3204635089","https://openalex.org/W4213009331","https://openalex.org/W4235954694","https://openalex.org/W4239897033","https://openalex.org/W4252505056","https://openalex.org/W4254182148"],"related_works":["https://openalex.org/W2162899405","https://openalex.org/W3113091479","https://openalex.org/W941090075","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729","https://openalex.org/W2998615029","https://openalex.org/W4283752247"],"abstract_inverted_index":{"Various":[0],"techniques":[1,16],"have":[2],"been":[3],"proposed":[4],"to":[5,13,55,80,97,150],"detect":[6,18,86],"smells":[7,20,63,71,87,178],"in":[8,64,72,88,127,132,142,184],"spreadsheets,":[9],"which":[10,52],"are":[11,53],"susceptible":[12],"errors.":[14],"These":[15,109,160],"typically":[17],"spreadsheet":[19,66,83,103,129],"through":[21],"a":[22,26,128],"mechanism":[23,93],"based":[24,45],"on":[25,46],"fixed":[27,47],"set":[28],"of":[29,101,120,189],"patterns":[30,48],"or":[31,49],"metric":[32,50],"thresholds.":[33],"Unlike":[34],"conventional":[35],"programs,":[36],"tabulation":[37,58,99,121],"styles":[38,100],"vary":[39],"greatly":[40],"across":[41],"spreadsheets.":[42],"Smell":[43],"detection":[44],"thresholds,":[51],"insensitive":[54],"the":[56,98,115,157],"varying":[57],"styles,":[59,122],"can":[60,94,135,180],"miss":[61],"many":[62,69],"one":[65],"while":[67],"reporting":[68],"spurious":[70],"another.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"propose":[78],"CUSTODES":[79,149,171],"effectively":[81],"cluster":[82],"cells":[84,126],"and":[85,106,111,117,147],"these":[89],"clusters.":[90,166],"The":[91],"clustering":[92],"automatically":[95],"adapt":[96],"each":[102],"using":[104],"strong":[105,110],"weak":[107,112],"features.":[108],"features":[113],"capture":[114],"invariant":[116],"variant":[118],"parts":[119],"respectively.":[123],"As":[124],"smelly":[125],"normally":[130],"occur":[131],"minority,":[133],"they":[134],"be":[136],"mechanically":[137],"detected":[138,176],"as":[139],"clusters'":[140],"outliers":[141],"feature":[143],"spaces.":[144],"We":[145],"implemented":[146],"applied":[148],"70":[151],"spreadsheets":[152,161,185],"files":[153],"randomly":[154],"sampled":[155],"from":[156],"EUSES":[158],"corpus.":[159],"contain":[162],"1,610":[163],"formula":[164],"cell":[165],"Experimental":[167],"results":[168],"confirmed":[169],"that":[170,179],"is":[172],"effective.":[173],"It":[174],"successfully":[175],"harmful":[177],"induce":[181],"computation":[182],"anomalies":[183],"with":[186],"an":[187],"F-measure":[188],"0.72,":[190],"outperforming":[191],"state-of-the-art":[192],"techniques.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}