{"id":"https://openalex.org/W3084564478","doi":"https://doi.org/10.14778/3415478.3415527","title":"Debugging large-scale data science pipelines using dagger","display_name":"Debugging large-scale data science pipelines using dagger","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3084564478","doi":"https://doi.org/10.14778/3415478.3415527","mag":"3084564478"},"language":"en","primary_location":{"id":"doi:10.14778/3415478.3415527","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3415478.3415527","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/134157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004937696","display_name":"El Kindi Rezig","orcid":"https://orcid.org/0000-0002-5187-3499"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"El Kindi Rezig","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049848172","display_name":"Ashrita Brahmaroutu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashrita Brahmaroutu","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002085554","display_name":"Nesime Tatbul","orcid":"https://orcid.org/0000-0002-0416-7022"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nesime Tatbul","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["HBKU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HBKU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["HBKU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HBKU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048097160","display_name":"Timothy G. Mattson","orcid":"https://orcid.org/0000-0002-6106-8717"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Timothy Mattson","raw_affiliation_strings":["Intel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Stonebraker","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7346,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94553051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"12","first_page":"2993","last_page":"2996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.996999979019165,"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":0.996999979019165,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9900000095367432,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9882000088691711,"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/debugging","display_name":"Debugging","score":0.9076135158538818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7404689788818359},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6719551086425781},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5696032047271729},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.47064441442489624},{"id":"https://openalex.org/keywords/algorithmic-program-debugging","display_name":"Algorithmic program debugging","score":0.4353233575820923},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4218832552433014},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4108818471431732},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39863550662994385},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3378562927246094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16307011246681213}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.9076135158538818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404689788818359},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6719551086425781},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5696032047271729},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.47064441442489624},{"id":"https://openalex.org/C136388014","wikidata":"https://www.wikidata.org/wiki/Q17084976","display_name":"Algorithmic program debugging","level":3,"score":0.4353233575820923},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4218832552433014},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4108818471431732},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39863550662994385},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3378562927246094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16307011246681213},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3415478.3415527","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3415478.3415527","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"},{"id":"pmh:oai:dspace.mit.edu:1721.1/134157","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/134157","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"VLDB Endowment","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/134157","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/134157","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"VLDB Endowment","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2112182680","https://openalex.org/W2544486974","https://openalex.org/W2585438896","https://openalex.org/W2798535736","https://openalex.org/W2885678825","https://openalex.org/W2889073286","https://openalex.org/W2948234719","https://openalex.org/W2970228335","https://openalex.org/W3013864782","https://openalex.org/W3104024780","https://openalex.org/W6733170484","https://openalex.org/W6775011611"],"related_works":["https://openalex.org/W2119199043","https://openalex.org/W2396596882","https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2801084903","https://openalex.org/W2377280071","https://openalex.org/W2060682672","https://openalex.org/W2782165897","https://openalex.org/W2375626968","https://openalex.org/W2098290990"],"abstract_inverted_index":{"Data":[0],"pipelines":[1],"are":[2,62],"the":[3,14,59,89],"new":[4,10],"code.":[5],"Consequently,":[6],"data":[7,36,41,76,110],"scientists":[8,111],"need":[9],"tools":[11],"to":[12,29,50,105,112],"support":[13],"often":[15],"time-consuming":[16],"process":[17],"of":[18,122],"debugging":[19],"their":[20],"pipelines.":[21],"We":[22],"introduce":[23],"Dagger":[24,54,108],",":[25],"an":[26],"end-to-end":[27],"system":[28],"debug":[30,75],"and":[31,115],"mitigate":[32,116],"data-centric":[33,117],"errors":[34],"in":[35,78],"pipelines,":[37],"such":[38],"as":[39,64,67,69],"a":[40,46,92],"transformation":[42],"gone":[43],"wrong":[44],"or":[45],"classifier":[47],"underperforming":[48],"due":[49],"noisy":[51],"training":[52],"data.":[53],"supports":[55],"inter-module":[56],"debugging,":[57,71],"where":[58,72],"pipeline":[60,123],"blocks":[61],"treated":[63],"black":[65],"boxes,":[66],"well":[68],"intra-module":[70],"users":[73],"can":[74],"objects":[77],"Python":[79],"scripts":[80],"(e.g.,":[81],"DataFrames).":[82],"In":[83],"this":[84],"demo,":[85],"we":[86],"will":[87],"walk":[88],"audience":[90],"through":[91],"rich,":[93],"real-world":[94],"business":[95],"intelligence":[96],"use":[97],"case":[98],"from":[99],"our":[100],"industrial":[101],"collaborators":[102],"at":[103,119],"Intel,":[104],"highlight":[106],"how":[107],"enables":[109],"productively":[113],"identify":[114],"problems":[118],"different":[120],"stages":[121],"development.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}