{"id":"https://openalex.org/W4414266725","doi":"https://doi.org/10.14778/3750601.3750671","title":"mlidea: Interactively Improving ML Data Preparation Code via \"Shadow Pipelines\"","display_name":"mlidea: Interactively Improving ML Data Preparation Code via \"Shadow Pipelines\"","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414266725","doi":"https://doi.org/10.14778/3750601.3750671"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750671","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750671","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/A5081322278","display_name":"Stefan Grafberger","orcid":"https://orcid.org/0000-0002-9884-9517"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Grafberger","raw_affiliation_strings":["BIFOLD & TU Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034924491","display_name":"Paul Groth","orcid":"https://orcid.org/0000-0003-0183-6910"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul Groth","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["BIFOLD & TU Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23193561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"12","first_page":"5359","last_page":"5362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9968000054359436,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9837999939918518,"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/pipeline","display_name":"Pipeline (software)","score":0.6491000056266785},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.5805000066757202},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5302000045776367},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5257999897003174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5189999938011169},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.40860000252723694},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4047999978065491},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.40220001339912415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144000172615051},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6491000056266785},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5302000045776367},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5159000158309937},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4607999920845032},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.40220001339912415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.29260000586509705},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3750601.3750671","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750671","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:dare.uva.nl:openaire/7ce6cb30-e87a-460c-91b9-5720aa17697b","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mlidea-interactively-improving-ml-data-preparation-code-via-shadow-pipelines(7ce6cb30-e87a-460c-91b9-5720aa17697b).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grafberger, S, Groth, P & Schelter, S 2025, 'mlidea: Interactively Improving ML Data Preparation Code via \"Shadow Pipelines\"', Proceedings of the VLDB Endowment, vol. 18, no. 12, pp. 5359\u20135362. https://doi.org/10.14778/3750601.3750671","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2288788587","https://openalex.org/W2437990191","https://openalex.org/W2884061367","https://openalex.org/W2905588001","https://openalex.org/W2970773487","https://openalex.org/W4288359825","https://openalex.org/W4381328970"],"related_works":[],"abstract_inverted_index":{"Data":[0],"scientists":[1,47,110],"develop":[2],"ML":[3],"pipelines":[4,72],"in":[5],"an":[6],"iterative":[7],"manner:":[8],"they":[9],"repeatedly":[10],"screen":[11],"a":[12,63],"pipeline":[13,54,79,152],"for":[14,53,90,133],"potential":[15,85],"issues,":[16,86],"debug":[17],"it,":[18],"and":[19,22,36,92,94,117,150],"then":[20],"revise":[21],"improve":[23],"its":[24],"code":[25,116,132],"according":[26],"to":[27,44,65,83,98,107,111,118],"their":[28,115],"findings.":[29],"However,":[30],"this":[31,40,57],"manual":[32],"process":[33],"is":[34],"tedious":[35],"error-prone.":[37],"To":[38],"address":[39],"challenge,":[41],"we":[42],"propose":[43],"assist":[45],"data":[46,109,147,155],"with":[48,69,136,157],"automatically":[49],"derived":[50],"interactive":[51,67,138],"suggestions":[52,68],"improvements":[55],"during":[56],"development":[58],"cycle.":[59],"We":[60,126],"demonstrate":[61,127],"mlidea,":[62],"library":[64],"generate":[66],"so-called":[70],"shadow":[71,124,139],",":[73],"hidden":[74],"variants":[75],"of":[76,122],"the":[77,99,123],"original":[78],"that":[80],"modify":[81],"it":[82],"auto-detect":[84],"try":[87],"out":[88],"modifications":[89,97],"improvements,":[91],"suggest":[93],"explain":[95],"these":[96],"user.":[100],"Our":[101],"system":[102,130],"uses":[103],"incremental":[104],"view":[105],"maintenance":[106,121],"enable":[108],"quickly":[112],"iterate":[113],"on":[114,154],"ensure":[119],"low-latency":[120],"pipelines.":[125],"how":[128],"our":[129],"improves":[131],"various":[134],"domains":[135],"three":[137],"pipelines:":[140],"fixing":[141],"mislabeled":[142],"rows,":[143],"enhancing":[144],"robustness":[145],"against":[146],"quality":[148],"problems,":[149],"improving":[151],"performance":[153],"slices":[156],"subpar":[158],"predictions.":[159]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}