{"id":"https://openalex.org/W2899327512","doi":"https://doi.org/10.1145/3236024.3264586","title":"BigSift: automated debugging of big data analytics in data-intensive scalable computing","display_name":"BigSift: automated debugging of big data analytics in data-intensive scalable computing","publication_year":2018,"publication_date":"2018-10-26","ids":{"openalex":"https://openalex.org/W2899327512","doi":"https://doi.org/10.1145/3236024.3264586","mag":"2899327512"},"language":"en","primary_location":{"id":"doi:10.1145/3236024.3264586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3236024.3264586","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3236024.3264586","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3236024.3264586","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003747461","display_name":"Muhammad Ali Gulzar","orcid":"https://orcid.org/0000-0002-8007-8662"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhammad Ali Gulzar","raw_affiliation_strings":["University of California at Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077699788","display_name":"Siman Wang","orcid":"https://orcid.org/0000-0002-5172-2682"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siman Wang","raw_affiliation_strings":["Hunan University, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049451101","display_name":"Miryung Kim","orcid":"https://orcid.org/0000-0003-3802-1512"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miryung Kim","raw_affiliation_strings":["University of California at Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003747461"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":4.3728,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95570055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social 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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.9096845388412476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8352476358413696},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7590705156326294},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6505802273750305},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6416258811950684},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5956190824508667},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4993252754211426},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.43584173917770386},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4349145293235779},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41371122002601624},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4135134816169739},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3667164146900177},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34881582856178284},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3441700339317322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11344605684280396},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.10386413335800171}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.9096845388412476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352476358413696},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7590705156326294},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6505802273750305},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6416258811950684},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5956190824508667},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4993252754211426},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.43584173917770386},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4349145293235779},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41371122002601624},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4135134816169739},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3667164146900177},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34881582856178284},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3441700339317322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11344605684280396},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.10386413335800171},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3236024.3264586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3236024.3264586","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3236024.3264586","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3236024.3264586","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3236024.3264586","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3236024.3264586","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G2637195115","display_name":null,"funder_award_id":"4-18-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2709462027","display_name":null,"funder_award_id":"N00014-18-1-2037","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2901386681","display_name":null,"funder_award_id":"CCF-1460325","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3143604296","display_name":null,"funder_award_id":"CCF-1527923","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3323275448","display_name":"CAREER: Analysis and Automation of Systematic Software Modifications","funder_award_id":"1460325","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3400546487","display_name":null,"funder_award_id":"1764077","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3533218870","display_name":null,"funder_award_id":"CCF-1527923, CCF-1460325","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3993482102","display_name":null,"funder_award_id":"Gift","funder_id":"https://openalex.org/F4320322183","funder_display_name":"Huawei Technologies"},{"id":"https://openalex.org/G4169770854","display_name":null,"funder_award_id":"CCF-1764077, CCF-1527923, CCF-1460325, CCF-1723773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5679969530","display_name":null,"funder_award_id":"1723773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6237456029","display_name":null,"funder_award_id":"FA8750-15-2-0075","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G6535578548","display_name":null,"funder_award_id":"CCF-1723773","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6657142319","display_name":null,"funder_award_id":"Ph.D Fellowship 2017-18","funder_id":"https://openalex.org/F4320309327","funder_display_name":"Google"},{"id":"https://openalex.org/G8276749802","display_name":null,"funder_award_id":"N00014-18-1-2037","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899327512.pdf","grobid_xml":"https://content.openalex.org/works/W2899327512.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W135267584","https://openalex.org/W2000809552","https://openalex.org/W2030433745","https://openalex.org/W2121217767","https://openalex.org/W2131975293","https://openalex.org/W2170224888","https://openalex.org/W2294556882","https://openalex.org/W2384569204","https://openalex.org/W2758552291","https://openalex.org/W2949366051","https://openalex.org/W3125773275","https://openalex.org/W4365786623"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2480201319","https://openalex.org/W2387706296","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W2294325978","https://openalex.org/W2111708921"],"abstract_inverted_index":{"Developing":[0],"Big":[1],"Data":[2],"Analytics":[3],"often":[4,34],"involves":[5],"trial":[6],"and":[7,58,63],"error":[8],"debugging,":[9],"due":[10],"to":[11,103],"the":[12,38,73,79,93],"unclean":[13],"nature":[14],"of":[15,41,68,90,95],"datasets":[16],"or":[17],"wrong":[18],"assumptions":[19],"made":[20],"about":[21],"data.":[22],"When":[23],"errors":[24],"(e.g.":[25],"program":[26],"crash,":[27],"outlier":[28],"results,":[29],"etc.)":[30],"arise,":[31],"developers":[32],"are":[33],"interested":[35],"in":[36],"pinpointing":[37],"root":[39],"cause":[40],"errors.":[42],"To":[43],"address":[44],"this":[45],"problem,":[46],"BigSift":[47,91],"takes":[48],"an":[49],"Apache":[50],"Spark":[51],"program,":[52],"a":[53,59,65,104],"user-defined":[54],"test":[55,75],"oracle":[56],"function,":[57],"dataset":[60],"as":[61],"input":[62,69],"outputs":[64],"minimum":[66],"set":[67],"records":[70],"that":[71,98],"reproduces":[72],"same":[74],"failure":[76],"by":[77],"combining":[78],"insights":[80],"from":[81],"delta":[82],"debugging":[83,101],"with":[84],"data":[85,107],"provenance.":[86],"The":[87],"technical":[88],"contribution":[89],"is":[92],"design":[94],"systems":[96],"optimizations":[97],"bring":[99],"automated":[100],"closer":[102],"reality":[105],"for":[106],"intensive":[108],"scalable":[109],"computing.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
