{"id":"https://openalex.org/W4396821472","doi":"https://doi.org/10.1145/3650203.3663327","title":"Towards Interactively Improving ML Data Preparation Code via \"Shadow Pipelines\"","display_name":"Towards Interactively Improving ML Data Preparation Code via \"Shadow Pipelines\"","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4396821472","doi":"https://doi.org/10.1145/3650203.3663327"},"language":"en","primary_location":{"id":"doi:10.1145/3650203.3663327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650203.3663327","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3650203.3663327","any_repository_has_fulltext":true},"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/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":"Stefan Grafberger","raw_affiliation_strings":["AIRLab, University of Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9884-9517","affiliations":[{"raw_affiliation_string":"AIRLab, University of Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"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, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0183-6910","affiliations":[{"raw_affiliation_string":"University of Amsterdam, The Netherlands","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, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4722-5840","affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Germany","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":2.1375,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86782609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9958999752998352,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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-transport","display_name":"Pipeline transport","score":0.8530381917953491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.821049690246582},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.777798056602478},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6164860725402832},{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.5843262672424316},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.56479412317276},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5360543727874756},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46641266345977783},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44151780009269714},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.38525113463401794},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28698837757110596},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22190740704536438},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10916677117347717}],"concepts":[{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.8530381917953491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821049690246582},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.777798056602478},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6164860725402832},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.5843262672424316},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.56479412317276},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5360543727874756},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46641266345977783},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44151780009269714},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.38525113463401794},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28698837757110596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22190740704536438},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10916677117347717},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3650203.3663327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650203.3663327","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.19591","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.19591","pdf_url":"https://arxiv.org/pdf/2404.19591","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire/32ed9ecf-0aba-4061-80b9-88ae5e15c43f","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/towards-interactively-improving-ml-data-preparation-code-via-shadow-pipelines(32ed9ecf-0aba-4061-80b9-88ae5e15c43f).html","pdf_url":"https://pure.uva.nl/ws/files/245897947/3650203.3663327.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Grafberger, S, Groth, P & Schelter, S 2024, Towards Interactively Improving ML Data Preparation Code via \u201cShadow Pipelines\u201d. in Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning (DEEM) : in conjunction with the 2024 ACM SIGMOD/PODS Conference, Santiago, Chile. New York, New York, pp. 7\u201311, 8th Workshop on Data Management for End-to-End Machine Learning, Santiago, Chile, 9/06/24. https://doi.org/10.1145/3650203.3663327","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3650203.3663327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650203.3663327","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2884061367","https://openalex.org/W2889249015","https://openalex.org/W2926314329","https://openalex.org/W2964116855","https://openalex.org/W3015276915","https://openalex.org/W3103264664","https://openalex.org/W3173326111","https://openalex.org/W4281400173","https://openalex.org/W4281770862","https://openalex.org/W4288359825","https://openalex.org/W4386768649"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"Data":[0],"scientists":[1,44],"develop":[2],"ML":[3],"pipelines":[4],"in":[5],"an":[6],"iterative":[7],"manner:":[8],"they":[9],"repeatedly":[10],"screen":[11],"a":[12],"pipeline":[13,55,74],"for":[14,54,85],"potential":[15,80,128],"issues,":[16,81],"debug":[17],"it,":[18],"and":[19,22,36,87,89,108,126],"then":[20],"revise":[21],"improve":[23],"its":[24],"code":[25],"according":[26],"to":[27,41,61,78,93,98,104,118],"their":[28],"findings.":[29],"However,":[30],"this":[31,46],"manual":[32],"process":[33],"is":[34],"tedious":[35],"error-prone.":[37],"Therefore,":[38],"we":[39],"propose":[40],"support":[42],"data":[43],"during":[45],"development":[47],"cycle":[48],"with":[49,65],"automatically":[50],"derived":[51],"interactive":[52],"suggestions":[53,64],"improvements.":[56],"We":[57,96,114],"discuss":[58],"our":[59,123,131],"vision":[60],"generate":[62],"these":[63,91],"so-called":[66],"shadow":[67,112],"pipelines,":[68],"hidden":[69],"variants":[70],"of":[71,110,122,130],"the":[72,94,111,120,127],"original":[73],"that":[75],"modify":[76],"it":[77],"auto-detect":[79],"try":[82],"out":[83],"modifications":[84,92],"improvements,":[86],"suggest":[88],"explain":[90],"user.":[95],"envision":[97],"apply":[99],"incremental":[100],"view":[101],"maintenance-based":[102],"optimisations":[103],"ensure":[105],"low-latency":[106],"computation":[107],"maintenance":[109],"pipelines.":[113],"conduct":[115],"preliminary":[116],"experiments":[117],"showcase":[119],"feasibility":[121],"envisioned":[124],"approach":[125],"benefits":[129],"proposed":[132],"optimisations.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}