{"id":"https://openalex.org/W2073449237","doi":"https://doi.org/10.1145/2786805.2786866","title":"A method to identify and correct problematic software activity data: exploiting capacity constraints and data redundancies","display_name":"A method to identify and correct problematic software activity data: exploiting capacity constraints and data redundancies","publication_year":2015,"publication_date":"2015-08-26","ids":{"openalex":"https://openalex.org/W2073449237","doi":"https://doi.org/10.1145/2786805.2786866","mag":"2073449237"},"language":"en","primary_location":{"id":"doi:10.1145/2786805.2786866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2786805.2786866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 10th Joint Meeting on 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/A5072346492","display_name":"Qimu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qimu Zheng","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067199285","display_name":"Audris Mockus","orcid":"https://orcid.org/0000-0002-7987-7598"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Audris Mockus","raw_affiliation_strings":["University of Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065977454","display_name":"Minghui Zhou","orcid":"https://orcid.org/0000-0001-6324-3964"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Zhou","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072346492"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":3.1784,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92737483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"637","last_page":"648"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9997000098228455,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7509715557098389},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.6683595776557922},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5908746123313904},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5449867844581604},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5293484330177307},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.5073317885398865},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.4170764982700348},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3543314039707184},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.35190635919570923},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.34002941846847534},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2145279347896576},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1328817903995514},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08063402771949768},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07785835862159729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509715557098389},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.6683595776557922},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5908746123313904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5449867844581604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5293484330177307},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.5073317885398865},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.4170764982700348},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3543314039707184},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35190635919570923},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.34002941846847534},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2145279347896576},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1328817903995514},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08063402771949768},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07785835862159729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2786805.2786866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2786805.2786866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5600000023841858,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1970588407","https://openalex.org/W1989862714","https://openalex.org/W1993088274","https://openalex.org/W1995012521","https://openalex.org/W2001245517","https://openalex.org/W2018871545","https://openalex.org/W2022585969","https://openalex.org/W2027602529","https://openalex.org/W2045064676","https://openalex.org/W2045530509","https://openalex.org/W2065314038","https://openalex.org/W2067490448","https://openalex.org/W2079317829","https://openalex.org/W2079404749","https://openalex.org/W2097886687","https://openalex.org/W2098950049","https://openalex.org/W2107277166","https://openalex.org/W2110229593","https://openalex.org/W2115918232","https://openalex.org/W2119731669","https://openalex.org/W2124100711","https://openalex.org/W2127577307","https://openalex.org/W2129164226","https://openalex.org/W2133368849","https://openalex.org/W2137130182","https://openalex.org/W2139885493","https://openalex.org/W2140952846","https://openalex.org/W2149783794","https://openalex.org/W2162815086","https://openalex.org/W2165022036","https://openalex.org/W2172232422"],"related_works":["https://openalex.org/W2078744341","https://openalex.org/W2029555411","https://openalex.org/W2159730313","https://openalex.org/W2774439323","https://openalex.org/W3151530686","https://openalex.org/W1509265476","https://openalex.org/W2981446648","https://openalex.org/W2183678285","https://openalex.org/W2476117260","https://openalex.org/W4383568364"],"abstract_inverted_index":{"Mining":[0],"software":[1,7,33,57,164],"repositories":[2,23],"to":[3,48,60,97,108,112,154,160],"understand":[4],"and":[5,15,59,73,90,100,168],"improve":[6],"development":[8,34,58],"is":[9],"a":[10,142],"common":[11],"approach":[12,47,70,150],"in":[13,85,166,169],"research":[14],"practice.":[16],"The":[17],"operational":[18,158],"data":[19,65,75,84,134,140,159],"obtained":[20],"from":[21,42],"these":[22],"often":[24],"do":[25],"not":[26],"faithfully":[27],"represent":[28],"the":[29,39,54,69,92,105,113,125,138,149],"intended":[30],"aspects":[31],"of":[32,56,76,88,94,117,127,157,163],"and,":[35],"therefore,":[36],"may":[37,151],"jeopardize":[38],"conclusions":[40],"derived":[41],"it.":[43],"We":[44,67,103,146],"propose":[45],"an":[46],"identify":[49],"problematic":[50,83,95],"values":[51,63,96,107],"based":[52],"on":[53],"constraints":[55],"correct":[61],"such":[62],"using":[64,71],"redundancies.":[66],"investigate":[68],"issue":[72],"commit":[74],"Mozilla":[77],"project.":[78],"In":[79],"particular,":[80],"we":[81,122],"identified":[82],"four":[86],"types":[87,156],"events":[89],"found":[91,104,123],"fraction":[93],"exceed":[98],"10%":[99],"rapidly":[101],"rising.":[102],"corrected":[106,139],"be":[109,152],"50%":[110],"closer":[111],"most":[114],"accurate":[115],"estimate":[116],"task":[118],"completion":[119],"time.":[120],"Finally,":[121],"that":[124],"models":[126],"time":[128],"until":[129],"fix":[130],"changed":[131],"substantially":[132],"when":[133],"were":[135],"corrected,":[136],"with":[137],"providing":[141],"20%":[143],"better":[144],"fit.":[145],"discuss":[147],"how":[148],"generalized":[153],"other":[155],"increase":[161],"fidelity":[162],"measurement":[165],"practice":[167],"research.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}