{"id":"https://openalex.org/W3198871417","doi":"https://doi.org/10.14778/3476311.3476331","title":"Debugging missing answers for spark queries over nested data with breadcrumb","display_name":"Debugging missing answers for spark queries over nested data with breadcrumb","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3198871417","doi":"https://doi.org/10.14778/3476311.3476331","mag":"3198871417"},"language":"en","primary_location":{"id":"doi:10.14778/3476311.3476331","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476331","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5041289033","display_name":"Ralf Diestelk\u00e4mper","orcid":null},"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":true,"raw_author_name":"Ralf Diestelk\u00e4mper","raw_affiliation_strings":["University of Stuttgart - IPVS, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart - IPVS, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079405484","display_name":"Seokki Lee","orcid":"https://orcid.org/0000-0002-5637-252X"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seokki Lee","raw_affiliation_strings":["University of Cincinnati"],"affiliations":[{"raw_affiliation_string":"University of Cincinnati","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061858093","display_name":"Boris Glavic","orcid":"https://orcid.org/0000-0003-2887-2452"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Glavic","raw_affiliation_strings":["Illinois Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087589863","display_name":"Melanie Herschel","orcid":"https://orcid.org/0009-0007-9821-5921"},"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":"Melanie Herschel","raw_affiliation_strings":["University of Stuttgart - IPVS, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart - IPVS, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041289033"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":1.4056,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90089845,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":"12","first_page":"2731","last_page":"2734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9986000061035156,"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":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9958000183105469,"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":0.8170243501663208},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7998560667037964},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.6091427803039551},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5608089566230774},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5481654405593872},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5462878942489624},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5310108065605164},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4647587537765503},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4515804052352905},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4309540390968323},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3356897830963135},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33356237411499023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170243501663208},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7998560667037964},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.6091427803039551},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5608089566230774},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5481654405593872},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5462878942489624},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5310108065605164},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4647587537765503},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4515804052352905},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4309540390968323},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3356897830963135},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33356237411499023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3476311.3476331","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476311.3476331","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1998982581","https://openalex.org/W2029138494","https://openalex.org/W2089434603","https://openalex.org/W2100153179","https://openalex.org/W2103598815","https://openalex.org/W2159720813","https://openalex.org/W2403572391","https://openalex.org/W2766945679","https://openalex.org/W2889190943","https://openalex.org/W3177222803","https://openalex.org/W4230159918","https://openalex.org/W4246215794"],"related_works":["https://openalex.org/W1587224678","https://openalex.org/W2350026801","https://openalex.org/W2098306546","https://openalex.org/W2368479705","https://openalex.org/W2363027842","https://openalex.org/W2106319245","https://openalex.org/W4251884638","https://openalex.org/W1581365825","https://openalex.org/W1505756205","https://openalex.org/W1495819418"],"abstract_inverted_index":{"We":[0],"present":[1],"Breadcrumb,":[2],"a":[3,20],"system":[4],"that":[5,36,51,81],"aids":[6],"developers":[7,53],"in":[8,32,96],"debugging":[9,59],"queries":[10,97],"through":[11],"query-based":[12],"explanations":[13,50,92],"for":[14,39,93],"missing":[15,45],"answers.":[16],"Given":[17],"as":[18],"input":[19,34],"query":[21,27,35],"and":[22,87,100],"an":[23],"expected,":[24],"but":[25],"missing,":[26],"result,":[28],"Breadcrumb":[29,68],"identifies":[30],"operators":[31,48],"the":[33,40,44,66,79],"are":[37],"responsible":[38],"failure":[41],"to":[42,83],"derive":[43],"answer.":[46],"These":[47],"form":[49],"guide":[52],"who":[54],"can":[55],"then":[56],"focus":[57],"their":[58],"efforts":[60],"on":[61,71,106],"fixing":[62],"these":[63],"parts":[64],"of":[65,73,90],"query.":[67],"is":[69,78,88],"implemented":[70],"top":[72],"Apache":[74],"Spark.":[75],"Our":[76],"approach":[77],"first":[80],"scales":[82],"big":[84],"data":[85],"dimensions":[86],"capable":[89],"finding":[91],"common":[94],"errors":[95,104],"over":[98],"nested":[99],"de-normalized":[101],"data,":[102],"e.g.,":[103],"based":[105],"misinterpreting":[107],"schema":[108],"semantics.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
