{"id":"https://openalex.org/W3089867364","doi":"https://doi.org/10.1145/3377811.3380366","title":"Improving data scientist efficiency with provenance","display_name":"Improving data scientist efficiency with provenance","publication_year":2020,"publication_date":"2020-06-27","ids":{"openalex":"https://openalex.org/W3089867364","doi":"https://doi.org/10.1145/3377811.3380366","mag":"3089867364"},"language":"en","primary_location":{"id":"doi:10.1145/3377811.3380366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377811.3380366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3377811.3380366","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3377811.3380366","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070358948","display_name":"Jingmei Hu","orcid":"https://orcid.org/0000-0002-4434-5057"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingmei Hu","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007956374","display_name":"Jiwon Joung","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiwon Joung","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076992382","display_name":"Maia Jacobs","orcid":"https://orcid.org/0000-0001-8500-0277"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maia Jacobs","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010436269","display_name":"Krzysztof Z. Gajos","orcid":"https://orcid.org/0000-0002-1897-9048"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krzysztof Z. Gajos","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054751297","display_name":"Margo Seltzer","orcid":"https://orcid.org/0000-0002-2165-4658"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Margo I. Seltzer","raw_affiliation_strings":["University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1609,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91653327,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1086","last_page":"1097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10260","display_name":"Software Engineering Research","score":0.9952999949455261,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9932000041007996,"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":0.9164761304855347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8827089667320251},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8521076440811157},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.7583044171333313},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7462154030799866},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.7448461055755615},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.538214385509491},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.522144615650177},{"id":"https://openalex.org/keywords/algorithmic-program-debugging","display_name":"Algorithmic program debugging","score":0.4735024571418762},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.36725056171417236},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17860627174377441}],"concepts":[{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.9164761304855347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8827089667320251},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8521076440811157},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.7583044171333313},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7462154030799866},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.7448461055755615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.538214385509491},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.522144615650177},{"id":"https://openalex.org/C136388014","wikidata":"https://www.wikidata.org/wiki/Q17084976","display_name":"Algorithmic program debugging","level":3,"score":0.4735024571418762},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36725056171417236},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17860627174377441}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377811.3380366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377811.3380366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3377811.3380366","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3377811.3380366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3377811.3380366","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3377811.3380366","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1033007185","display_name":"SI2-SSI: Collaborative Research: Bringing End-to-End Provenance to Scientists","funder_award_id":"1450277","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4066417867","display_name":null,"funder_award_id":"FA8750-16-C-0045","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5105054357","display_name":null,"funder_award_id":"1450277","funder_id":"https://openalex.org/F4320309856","funder_display_name":"National Youth Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309856","display_name":"National Youth Science Foundation","ror":"https://ror.org/054yz2f06"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089867364.pdf","grobid_xml":"https://content.openalex.org/works/W3089867364.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W216692372","https://openalex.org/W269919247","https://openalex.org/W603668711","https://openalex.org/W1444906800","https://openalex.org/W1500842519","https://openalex.org/W1545590260","https://openalex.org/W1548254758","https://openalex.org/W1552694902","https://openalex.org/W1559528097","https://openalex.org/W1573589851","https://openalex.org/W1582521812","https://openalex.org/W1717300320","https://openalex.org/W1959365993","https://openalex.org/W1965171928","https://openalex.org/W1981811081","https://openalex.org/W1983704199","https://openalex.org/W1984186051","https://openalex.org/W2011055092","https://openalex.org/W2014171262","https://openalex.org/W2014888296","https://openalex.org/W2028423097","https://openalex.org/W2038899190","https://openalex.org/W2065073464","https://openalex.org/W2070948110","https://openalex.org/W2074760252","https://openalex.org/W2091543666","https://openalex.org/W2096458486","https://openalex.org/W2104444223","https://openalex.org/W2109598262","https://openalex.org/W2121044470","https://openalex.org/W2132347265","https://openalex.org/W2132874107","https://openalex.org/W2135445066","https://openalex.org/W2145209235","https://openalex.org/W2145217511","https://openalex.org/W2148238464","https://openalex.org/W2148649534","https://openalex.org/W2151905266","https://openalex.org/W2157289187","https://openalex.org/W2168270139","https://openalex.org/W2472803348","https://openalex.org/W2492142294","https://openalex.org/W2506528515","https://openalex.org/W2559768064","https://openalex.org/W2605310309","https://openalex.org/W2620387101","https://openalex.org/W2747669027","https://openalex.org/W2752857821","https://openalex.org/W2793231438","https://openalex.org/W2793232258","https://openalex.org/W2795247881","https://openalex.org/W2913256667","https://openalex.org/W3101089035","https://openalex.org/W3121991495","https://openalex.org/W4234733488","https://openalex.org/W4238127296","https://openalex.org/W4241491750","https://openalex.org/W6893724920"],"related_works":["https://openalex.org/W2396596882","https://openalex.org/W2098290990","https://openalex.org/W2119199043","https://openalex.org/W2801084903","https://openalex.org/W2377280071","https://openalex.org/W2168928134","https://openalex.org/W2112040168","https://openalex.org/W4241972157","https://openalex.org/W2053897590","https://openalex.org/W4242556954"],"abstract_inverted_index":{"Data":[0],"scientists":[1,65],"frequently":[2,66],"analyze":[3],"data":[4],"by":[5,91],"writing":[6],"scripts.":[7],"We":[8,77,140,176],"conducted":[9],"a":[10,22,49,80,116,122,126,137,148,174,188,194,208,228,235],"contextual":[11],"inquiry":[12],"with":[13],"interdisciplinary":[14],"researchers,":[15],"which":[16,57,215],"revealed":[17],"that":[18,27,82,129,142,181],"parameter":[19],"tuning":[20],"is":[21,29,193,217],"highly":[23],"iterative":[24],"process":[25,90],"and":[26,35,96,152,165,178,202],"debugging":[28,89,107,143],"time-consuming.":[30],"As":[31],"analysis":[32],"scripts":[33,69],"evolve":[34],"become":[36],"more":[37,195],"complex,":[38],"analysts":[39],"have":[40],"difficulty":[41],"conceptualizing":[42],"their":[43],"workflow.":[44],"In":[45],"particular,":[46],"after":[47],"editing":[48],"script,":[50,123],"it":[51,192,216],"becomes":[52],"difficult":[53],"to":[54,86,101,112,135,172,200,219,230],"determine":[55],"precisely":[56],"code":[58],"blocks":[59],"depend":[60],"on":[61],"the":[62,74,88,132,144,169],"edit.":[63],"Consequently,":[64],"re-run":[67],"entire":[68],"instead":[70],"of":[71,161,211,237],"re-running":[72],"only":[73,131],"necessary":[75,134,171],"parts.":[76],"present":[78],"ProvBuild,":[79],"tool":[81],"leverages":[83],"language-level":[84,212],"provenance":[85,111],"streamline":[87],"reducing":[92],"programmer":[93,222],"cognitive":[94,150,163],"load":[95,151,164],"decreasing":[97],"subsequent":[98],"runtimes,":[99],"leading":[100],"an":[102,119],"overall":[103],"reduction":[104],"in":[105,115,214],"elapsed":[106],"time.":[108],"ProvBuild":[109,124,184,206],"uses":[110],"track":[113],"dependencies":[114],"script.":[117,175],"When":[118],"analyst":[120],"debugs":[121],"generates":[125],"simplifed":[127],"script":[128,146],"contains":[130],"information":[133],"debug":[136,173,201],"particular":[138],"problem.":[139],"demonstrate":[141],"simplified":[145],"lowers":[147],"programmer's":[149],"permits":[153],"faster":[154],"re-execution":[155],"when":[156],"testing":[157],"changes.":[158],"The":[159],"combination":[160],"reduced":[162],"shorter":[166],"runtime":[167],"reduces":[168],"time":[170],"quantitatively":[177],"qualitatively":[179],"show":[180],"even":[182],"though":[183],"introduces":[185],"overhead":[186],"during":[187],"script's":[189],"first":[190],"execution,":[191],"efficient":[196],"way":[197,229],"for":[198],"users":[199],"tune":[203],"complex":[204],"workflows.":[205],"demonstrates":[207],"novel":[209],"use":[210],"provenance,":[213],"used":[218],"proactively":[220],"improve":[221],"productively":[223],"rather":[224],"than":[225],"merely":[226],"providing":[227],"retroactively":[231],"gain":[232],"insight":[233],"into":[234],"body":[236],"code.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}