{"id":"https://openalex.org/W4292159036","doi":"https://doi.org/10.1145/3546930.3547494","title":"Enabling useful provenance in scripting languages with a human-in-the-loop","display_name":"Enabling useful provenance in scripting languages with a human-in-the-loop","publication_year":2022,"publication_date":"2022-06-12","ids":{"openalex":"https://openalex.org/W4292159036","doi":"https://doi.org/10.1145/3546930.3547494"},"language":"en","primary_location":{"id":"doi:10.1145/3546930.3547494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546930.3547494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Human-In-the-Loop Data Analytics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/146449","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052174054","display_name":"Yuze Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuze Lou","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052174054"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11483401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976000189781189,"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/T11937","display_name":"Research Data Management Practices","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8967319130897522},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8498104810714722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8282296657562256},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7427970170974731},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5863840579986572},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4368259012699127},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.42858558893203735},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.426542729139328},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4114898145198822},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.38885462284088135},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2820911407470703}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8967319130897522},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8498104810714722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282296657562256},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7427970170974731},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5863840579986572},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4368259012699127},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.42858558893203735},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.426542729139328},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4114898145198822},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.38885462284088135},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2820911407470703}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3546930.3547494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546930.3547494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Human-In-the-Loop Data Analytics","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/146449","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/146449","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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Workshop on Human-In-the-Loop Data Analytics","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/146449","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/146449","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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Workshop on Human-In-the-Loop Data Analytics","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1573942047","display_name":null,"funder_award_id":"2132318","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W269919247","https://openalex.org/W1527356121","https://openalex.org/W1543562288","https://openalex.org/W1629033356","https://openalex.org/W1720961861","https://openalex.org/W1906647448","https://openalex.org/W1984248430","https://openalex.org/W2005835674","https://openalex.org/W2059385647","https://openalex.org/W2093721629","https://openalex.org/W2119325664","https://openalex.org/W2185907055","https://openalex.org/W2293299776","https://openalex.org/W2296703446","https://openalex.org/W2581905020","https://openalex.org/W2600741786","https://openalex.org/W2609517807","https://openalex.org/W2766945679","https://openalex.org/W2885678825","https://openalex.org/W2948447697","https://openalex.org/W2948742859","https://openalex.org/W3032244227","https://openalex.org/W3045754299","https://openalex.org/W3104024780","https://openalex.org/W3105684693","https://openalex.org/W3132433578","https://openalex.org/W3176771520","https://openalex.org/W4231488651","https://openalex.org/W4237328017","https://openalex.org/W4243044468","https://openalex.org/W6632472780"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2782165897","https://openalex.org/W1582950852","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W1024825291","https://openalex.org/W4254242184"],"abstract_inverted_index":{"Most":[0],"data":[1,6,28,48,59,76,86],"scientists":[2],"must":[3],"build":[4],"substantial":[5,93],"pipelines":[7,16],"using":[8],"scripting":[9,89],"languages":[10,90],"like":[11],"Python":[12],"and":[13,36],"R.":[14],"These":[15],"are":[17,41],"hard":[18],"to":[19,23,56,75,96],"get":[20],"correct":[21],"due":[22],"the":[24,32,37,64,68,97],"large":[25],"volume":[26],"of":[27,46],"they":[29,40],"process":[30],"(thus":[31],"long":[33],"execution":[34],"time),":[35],"fact":[38],"that":[39,103],"tested":[42],"mainly":[43],"by":[44],"inspection":[45],"output":[47],"quality.":[49],"It":[50],"is":[51,73,104],"therefore":[52],"crucial":[53],"for":[54,84,88,107],"developers":[55],"reason":[57],"about":[58],"through":[60],"each":[61],"step":[62],"in":[63,78],"pipeline,":[65],"starting":[66],"from":[67],"raw":[69],"input;":[70],"this":[71],"information":[72,102],"akin":[74],"provenance":[77,87],"a":[79],"relational":[80],"setting.":[81],"Past":[82],"efforts":[83],"capturing":[85],"have":[91],"required":[92],"manual":[94],"modifications":[95],"scripts,":[98],"or":[99],"else":[100],"yield":[101],"too":[105],"inflexible":[106],"many":[108],"debugging":[109],"tasks.":[110]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}