{"id":"https://openalex.org/W3043171079","doi":"https://doi.org/10.1145/3395363.3397356","title":"Scaffle: bug localization on millions of files","display_name":"Scaffle: bug localization on millions of files","publication_year":2020,"publication_date":"2020-07-13","ids":{"openalex":"https://openalex.org/W3043171079","doi":"https://doi.org/10.1145/3395363.3397356","mag":"3043171079"},"language":"en","primary_location":{"id":"doi:10.1145/3395363.3397356","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395363.3397356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis","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/A5013438083","display_name":"Michael Pradel","orcid":"https://orcid.org/0000-0003-1623-498X"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Pradel","raw_affiliation_strings":["University of Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051545971","display_name":"Vijayaraghavan Murali","orcid":"https://orcid.org/0009-0009-1374-7334"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayaraghavan Murali","raw_affiliation_strings":["Facebook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014742037","display_name":"Rebecca Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rebecca Qian","raw_affiliation_strings":["Facebook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001038577","display_name":"Mateusz Machalica","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mateusz Machalica","raw_affiliation_strings":["Facebook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074555535","display_name":"Erik Meijer","orcid":"https://orcid.org/0000-0001-7959-4670"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Meijer","raw_affiliation_strings":["Facebook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101965118","display_name":"Satish Chandra","orcid":"https://orcid.org/0000-0003-2546-9000"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish Chandra","raw_affiliation_strings":["Facebook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4051,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96742779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9980999827384949,"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/T12127","display_name":"Software System Performance and Reliability","score":0.994700014591217,"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":0.8226131200790405},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.7954584360122681},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6672666668891907},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6424471139907837},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5765640735626221},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5257751941680908},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.510494589805603},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.49551546573638916},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4726497232913971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44660666584968567},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42344382405281067},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42225033044815063},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3626413941383362},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35064762830734253},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3240172863006592},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30843186378479004},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1458895206451416},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13299620151519775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226131200790405},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.7954584360122681},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6672666668891907},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6424471139907837},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5765640735626221},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5257751941680908},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.510494589805603},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.49551546573638916},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4726497232913971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44660666584968567},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42344382405281067},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42225033044815063},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3626413941383362},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35064762830734253},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3240172863006592},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30843186378479004},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1458895206451416},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13299620151519775},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3395363.3397356","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395363.3397356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1912151884","https://openalex.org/W1967936510","https://openalex.org/W1968882522","https://openalex.org/W1985947101","https://openalex.org/W2000518393","https://openalex.org/W2012380206","https://openalex.org/W2017485217","https://openalex.org/W2037230564","https://openalex.org/W2052501516","https://openalex.org/W2058230372","https://openalex.org/W2130343490","https://openalex.org/W2131346202","https://openalex.org/W2132994900","https://openalex.org/W2145302217","https://openalex.org/W2153418968","https://openalex.org/W2153579005","https://openalex.org/W2162045655","https://openalex.org/W2249980257","https://openalex.org/W2336438358","https://openalex.org/W2343875716","https://openalex.org/W2515360277","https://openalex.org/W2592057610","https://openalex.org/W2741358034","https://openalex.org/W2767527821","https://openalex.org/W2795260929","https://openalex.org/W2805788202","https://openalex.org/W2886117034","https://openalex.org/W2888230423","https://openalex.org/W2898817152","https://openalex.org/W2998011150","https://openalex.org/W3149255455","https://openalex.org/W3149901392"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2401723157","https://openalex.org/W626940945","https://openalex.org/W2952904874","https://openalex.org/W4297690216","https://openalex.org/W1690653314"],"abstract_inverted_index":{"Despite":[0],"all":[1,206],"efforts":[2],"to":[3,19,28,40,74,108,114,125,127,196,200,203],"avoid":[4],"bugs,":[5],"software":[6],"sometimes":[7],"crashes":[8],"in":[9,53,118],"the":[10,16,21,30,61,71,76,101,119,129,139,146,190,194,210],"field,":[11],"leaving":[12],"crash":[13,35,94,143,159,207],"traces":[14,160,208],"as":[15],"only":[17],"information":[18,110,231],"localize":[20],"problem.":[22],"Prior":[23],"approaches":[24],"on":[25,70],"localizing":[26,100],"where":[27],"fix":[29,197],"root":[31],"cause":[32],"of":[33,49,91,141,156,158,173,184,205,229,237],"a":[34,83,92,142,163,226,235],"do":[36],"not":[37,134],"scale":[38],"well":[39],"ultra-large":[41],"scale,":[42],"heterogeneous":[43],"code":[44,50,120,166],"bases":[45],"that":[46,148,170,178,189],"contain":[47],"millions":[48,172],"files":[51],"written":[52],"multiple":[54],"programming":[55],"languages.":[56],"This":[57],"paper":[58],"presents":[59],"Scaffle,":[60],"first":[62],"scalable":[63,227],"bug":[64,175],"localization":[65],"technique,":[66],"which":[67,89,123],"is":[68],"based":[69],"key":[72],"insight":[73],"divide":[75],"problem":[77],"into":[78],"two":[79],"easier":[80],"sub-problems.":[81],"First,":[82],"trained":[84],"machine":[85],"learning":[86],"model":[87],"predicts":[88,193],"lines":[90,105],"raw":[93],"trace":[95,144],"are":[96,106],"most":[97],"informative":[98],"for":[99,198],"bug.":[102],"Then,":[103],"these":[104],"fed":[107],"an":[109,222],"retrieval-based":[111,232],"search":[112],"engine":[113],"retrieve":[115],"file":[116,124,195],"paths":[117],"base,":[121],"predicting":[122],"change":[126],"address":[128],"crash.":[130],"The":[131,186],"approach":[132,191],"does":[133],"make":[135],"any":[136],"assumptions":[137],"about":[138],"format":[140],"or":[145],"language":[147],"produces":[149],"it.":[150],"We":[151],"evaluate":[152],"Scaffle":[153,215],"with":[154],"tens":[155],"thousands":[157],"produced":[161],"by":[162,182],"large-scale":[164],"industrial":[165],"base":[167],"at":[168],"Facebook":[169],"contains":[171],"possible":[174],"locations":[176],"and":[177,234],"powers":[179],"tools":[180],"used":[181],"billions":[183],"people.":[185],"results":[187],"show":[188],"correctly":[192],"40%":[199],"60%":[201],"(50%":[202],"70%)":[204],"within":[209],"top-1":[211],"(top-5)":[212],"predictions.":[213],"Moreover,":[214],"improves":[216],"over":[217],"several":[218],"baseline":[219],"approaches,":[220,233],"including":[221],"existing":[223,230],"classification-based":[224],"approach,":[225],"variant":[228],"set":[236],"hand-tuned,":[238],"industrially":[239],"deployed":[240],"heuristics.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}