{"id":"https://openalex.org/W4402993176","doi":"https://doi.org/10.1007/s13222-024-00483-4","title":"Automated Provenance-Based Screening of ML Data Preparation Pipelines","display_name":"Automated Provenance-Based Screening of ML Data Preparation Pipelines","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4402993176","doi":"https://doi.org/10.1007/s13222-024-00483-4"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-024-00483-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-024-00483-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-024-00483-4.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13222-024-00483-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840"},"institutions":[{"id":"https://openalex.org/I4210088352","display_name":"Berliner Institut f\u00fcr Sozialforschung","ror":"https://ror.org/0043ncq27","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088352"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4722-5840","affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4210088352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066160649","display_name":"Shubha Guha","orcid":"https://orcid.org/0000-0002-9156-1561"},"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":"Shubha Guha","raw_affiliation_strings":["University of Amsterdam, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081322278","display_name":"Stefan Grafberger","orcid":"https://orcid.org/0000-0002-9884-9517"},"institutions":[{"id":"https://openalex.org/I4210088352","display_name":"Berliner Institut f\u00fcr Sozialforschung","ror":"https://ror.org/0043ncq27","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088352"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Grafberger","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4210088352"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090934117"],"corresponding_institution_ids":["https://openalex.org/I4210088352"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":3.1676,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93639994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"24","issue":"3","first_page":"187","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11937","display_name":"Research Data Management Practices","score":0.9936000108718872,"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/T11719","display_name":"Data Quality and Management","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8246681690216064},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7294499278068542},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5953772068023682},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5597812533378601},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.42921581864356995},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4285949170589447},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.35154691338539124},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22094428539276123},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11913910508155823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246681690216064},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7294499278068542},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5953772068023682},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5597812533378601},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.42921581864356995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4285949170589447},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35154691338539124},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22094428539276123},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11913910508155823},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13222-024-00483-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-024-00483-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-024-00483-4.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s13222-024-00483-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13222-024-00483-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-024-00483-4.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324094","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402993176.pdf","grobid_xml":"https://content.openalex.org/works/W4402993176.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2101234009","https://openalex.org/W2131975293","https://openalex.org/W2189162242","https://openalex.org/W2293299776","https://openalex.org/W2612139288","https://openalex.org/W2743948853","https://openalex.org/W2766945679","https://openalex.org/W2807251972","https://openalex.org/W2898158860","https://openalex.org/W2905588001","https://openalex.org/W2926314329","https://openalex.org/W2970773487","https://openalex.org/W3013601656","https://openalex.org/W3086663505","https://openalex.org/W3105684693","https://openalex.org/W3148888152","https://openalex.org/W3173683037","https://openalex.org/W3181414820","https://openalex.org/W4200015620","https://openalex.org/W4210354100","https://openalex.org/W4280494175","https://openalex.org/W4379390538","https://openalex.org/W4381328970","https://openalex.org/W4386768649","https://openalex.org/W4391682392","https://openalex.org/W4391785473","https://openalex.org/W4396821472","https://openalex.org/W6696841567","https://openalex.org/W6967489659"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":{"Summary":[0],"Software":[1],"systems":[2],"that":[3,78,123,154],"learn":[4],"from":[5,109,145],"data":[6,27,44,80,110,131,139,169,184,210],"via":[7],"machine":[8],"learning":[9,217],"(ML)":[10],"are":[11,124],"being":[12],"deployed":[13],"in":[14,17,50,215],"increasing":[15],"numbers":[16],"real":[18],"world":[19],"application":[20],"scenarios.":[21],"These":[22],"ML":[23,85],"applications":[24,86],"contain":[25],"complex":[26],"preparation":[28,81,140,185],"pipelines,":[29],"which":[30,58],"take":[31],"several":[32,224],"raw":[33],"inputs,":[34],"integrate,":[35],"filter":[36],"and":[37,56,70,92,107,112,151,173,187,208,219],"encode":[38],"them":[39],"to":[40,53,73,88,137,148,158,181,204],"produce":[41],"the":[42,79,127,130,190,206,209],"input":[43],"for":[45,83,163],"model":[46,138],"training.":[47],"This":[48],"is":[49,67],"stark":[51],"contrast":[52],"academic":[54],"studies":[55],"benchmarks,":[57],"typically":[59],"work":[60],"with":[61,126,227],"static,":[62],"already":[63],"prepared":[64],"datasets.":[65],"It":[66],"a":[68,101,178],"difficult":[69],"tedious":[71],"task":[72],"ensure":[74],"at":[75],"development":[76],"time":[77,108],"pipelines":[82,141,162,186,226],"such":[84,183,196],"adhere":[87],"sound":[89],"experimentation":[90],"practices":[91],"compliance":[93],"requirements.":[94],"Identifying":[95],"potential":[96],"correctness":[97,166],"issues":[98,167],"currently":[99],"requires":[100],"high":[102],"degree":[103],"of":[104,129,193,212],"discipline,":[105],"knowledge,":[106],"scientists,":[111],"they":[113],"often":[114],"only":[115],"implement":[116],"one-off":[117],"solutions,":[118],"based":[119],"on":[120,223],"specialised":[121],"frameworks":[122],"incompatible":[125],"rest":[128],"science":[132],"ecosystem.":[133],"We":[134,176,201],"discuss":[135,202],"how":[136,203],"as":[142,197],"dataflow":[143],"computations":[144],"relational":[146],"inputs":[147],"matrix":[149],"outputs,":[150],"propose":[152],"techniques":[153],"use":[155],"record-level":[156],"provenance":[157,211],"automatically":[159],"screen":[160,182],"these":[161],"many":[164],"common":[165,213],"(e.g.,":[168],"leakage":[170],"between":[171],"train":[172],"test":[174],"data).":[175],"design":[177],"prototypical":[179],"system":[180,222],"furthermore":[188],"enable":[189],"automatic":[191],"computation":[192],"important":[194],"metadata":[195],"group":[198],"fairness":[199],"metrics.":[200],"extract":[205],"semantics":[207],"artifacts":[214],"supervised":[216],"tasks":[218],"evaluate":[220],"our":[221],"example":[225],"real-world":[228],"data.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}