{"id":"https://openalex.org/W2258726425","doi":"https://doi.org/10.1145/2901739.2901766","title":"The unreasonable effectiveness of traditional information retrieval in crash report deduplication","display_name":"The unreasonable effectiveness of traditional information retrieval in crash report deduplication","publication_year":2016,"publication_date":"2016-05-14","ids":{"openalex":"https://openalex.org/W2258726425","doi":"https://doi.org/10.1145/2901739.2901766","mag":"2258726425"},"language":"en","primary_location":{"id":"doi:10.1145/2901739.2901766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2901739.2901766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","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/A5079340620","display_name":"Joshua Charles Campbell","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joshua Charles Campbell","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048601698","display_name":"Eddie Antonio Santos","orcid":"https://orcid.org/0000-0001-5337-715X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eddie Antonio Santos","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070785370","display_name":"Abram Hindle","orcid":"https://orcid.org/0000-0002-4373-4958"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abram Hindle","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.8344,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86149738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"269","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9973999857902527,"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/crash","display_name":"Crash","score":0.854713499546051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8055871725082397},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6600540280342102},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5090612769126892},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49345865845680237},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44967228174209595},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4184761941432953},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3755539357662201},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3459606170654297},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3449585437774658},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3349660038948059},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11771941184997559}],"concepts":[{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.854713499546051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055871725082397},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6600540280342102},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5090612769126892},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49345865845680237},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44967228174209595},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4184761941432953},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3755539357662201},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3459606170654297},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3449585437774658},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3349660038948059},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11771941184997559}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2901739.2901766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2901739.2901766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320327705","display_name":"Mozilla Foundation","ror":"https://ror.org/01y8r3379"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W185086179","https://openalex.org/W1956559956","https://openalex.org/W1967936510","https://openalex.org/W2022675432","https://openalex.org/W2033472898","https://openalex.org/W2037230564","https://openalex.org/W2047165792","https://openalex.org/W2053158571","https://openalex.org/W2072240081","https://openalex.org/W2077537588","https://openalex.org/W2096598529","https://openalex.org/W2107316307","https://openalex.org/W2122850635","https://openalex.org/W2123659430","https://openalex.org/W2127176799","https://openalex.org/W2130343490","https://openalex.org/W2132994900","https://openalex.org/W2139664301","https://openalex.org/W2149234515","https://openalex.org/W2162376048","https://openalex.org/W2169597130","https://openalex.org/W2476375650"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W12581771"],"abstract_inverted_index":{"Organizations":[0],"like":[1],"Mozilla,":[2],"Microsoft,":[3],"and":[4,81,104],"Apple":[5],"are":[6,25,39,65,111,144],"flooded":[7],"with":[8,56,137],"thousands":[9],"of":[10,52,60,83,93,150,168,175],"automated":[11,73,161],"crash":[12,17,37,61,74,86,97,138,151,162],"reports":[13,18,38],"per":[14],"day.":[15],"Although":[16],"contain":[19],"valuable":[20],"information":[21,127],"for":[22,29,147,170],"debugging,":[23],"there":[24],"often":[26,40],"too":[27],"many":[28],"developers":[30],"to":[31,134],"examine":[32],"individually.":[33],"Therefore,":[34],"in":[35,44,120,173],"industry,":[36],"automatically":[41],"grouped":[42],"together":[43],"buckets.":[45],"Ubuntu's":[46,71],"repository":[47],"contains":[48],"crashes":[49],"from":[50],"hundreds":[51],"software":[53],"systems":[54],"available":[55],"Ubuntu.":[57],"A":[58,91],"variety":[59],"report":[62],"bucketing":[63,152,163],"methods":[64,106],"evaluated":[66,112],"using":[67,125],"data":[68],"collected":[69],"by":[70],"Apport":[72],"reporting":[75],"system.":[76],"The":[77,117],"trade-off":[78],"between":[79],"precision":[80],"recall":[82],"numerous":[84],"scalable":[85],"deduplication":[87,98],"techniques":[88,142],"is":[89,102],"explored.":[90],"set":[92],"criteria":[94,110],"that":[95,107,124,130,160],"a":[96,114,166],"method":[99],"must":[100],"meet":[101,108],"presented":[103,119],"several":[105],"these":[109],"on":[113],"new":[115],"dataset.":[116],"evaluations":[118],"this":[121],"paper":[122],"show":[123],"off-the-shelf":[126],"retrieval":[128],"techniques,":[129],"were":[131],"not":[132],"designed":[133,146],"be":[135],"used":[136],"reports,":[139],"outperform":[140],"other":[141],"which":[143],"specifically":[145],"the":[148],"task":[149],"at":[153],"realistic":[154],"industrial":[155],"scales.":[156],"This":[157],"research":[158],"indicates":[159],"still":[164],"has":[165],"lot":[167],"room":[169],"improvement,":[171],"especially":[172],"terms":[174],"identifier":[176],"tokenization.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
