{"id":"https://openalex.org/W4391682392","doi":"https://doi.org/10.1145/3644385","title":"Supporting Better Insights of Data Science Pipelines with Fine-grained Provenance","display_name":"Supporting Better Insights of Data Science Pipelines with Fine-grained Provenance","publication_year":2024,"publication_date":"2024-02-09","ids":{"openalex":"https://openalex.org/W4391682392","doi":"https://doi.org/10.1145/3644385"},"language":"en","primary_location":{"id":"doi:10.1145/3644385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3644385","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/A5013015057","display_name":"Adriane Chapman","orcid":"https://orcid.org/0000-0002-3814-2587"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Adriane Chapman","raw_affiliation_strings":["University of Southampton, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007249357","display_name":"Luca Lauro","orcid":"https://orcid.org/0009-0003-0845-9596"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Lauro","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018918066","display_name":"Paolo Missier","orcid":"https://orcid.org/0000-0002-0978-2446"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paolo Missier","raw_affiliation_strings":["Newcastle University, Newcastle upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005845219","display_name":"Riccardo Torlone","orcid":"https://orcid.org/0000-0003-1484-3693"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Torlone","raw_affiliation_strings":["Universit\u00e1 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e1 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013015057"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":null,"apc_paid":null,"fwci":8.6523,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97145898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"49","issue":"2","first_page":"1","last_page":"42"},"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/T11937","display_name":"Research Data Management Practices","score":0.996999979019165,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.986299991607666,"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/computer-science","display_name":"Computer science","score":0.8357373476028442},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7333716750144958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5587596893310547},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5386447906494141},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.5380681753158569},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5004007816314697},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4818240702152252},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47737976908683777},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4592873752117157},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.45118457078933716},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.44256287813186646},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4117136001586914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36131566762924194},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3549017310142517},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14485254883766174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13766959309577942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357373476028442},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7333716750144958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5587596893310547},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5386447906494141},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5380681753158569},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5004007816314697},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4818240702152252},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47737976908683777},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4592873752117157},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45118457078933716},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.44256287813186646},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4117136001586914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36131566762924194},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3549017310142517},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14485254883766174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13766959309577942},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3644385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3644385","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/468168","is_oa":false,"landing_page_url":"https://hdl.handle.net/11590/468168","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.uniroma3.it:11590/470752","is_oa":false,"landing_page_url":"https://hdl.handle.net/11590/470752","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1493590020","display_name":null,"funder_award_id":"EP/S028366/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1530537858","https://openalex.org/W1552694902","https://openalex.org/W1554105863","https://openalex.org/W1906647448","https://openalex.org/W2006453856","https://openalex.org/W2050876821","https://openalex.org/W2072269087","https://openalex.org/W2119325664","https://openalex.org/W2123942796","https://openalex.org/W2133470535","https://openalex.org/W2133986470","https://openalex.org/W2167541073","https://openalex.org/W2282821441","https://openalex.org/W2293299776","https://openalex.org/W2294556882","https://openalex.org/W2296703446","https://openalex.org/W2466173809","https://openalex.org/W2524620548","https://openalex.org/W2600741786","https://openalex.org/W2606811865","https://openalex.org/W2612069656","https://openalex.org/W2746538584","https://openalex.org/W2752857821","https://openalex.org/W2789980099","https://openalex.org/W2798535736","https://openalex.org/W2912325461","https://openalex.org/W2912411326","https://openalex.org/W2945295328","https://openalex.org/W2948447697","https://openalex.org/W2948742859","https://openalex.org/W2950063476","https://openalex.org/W2951565607","https://openalex.org/W2952851516","https://openalex.org/W2970449746","https://openalex.org/W2997591727","https://openalex.org/W3008570669","https://openalex.org/W3013778941","https://openalex.org/W3017205679","https://openalex.org/W3045754299","https://openalex.org/W3082494217","https://openalex.org/W3086791196","https://openalex.org/W3103438889","https://openalex.org/W3104149808","https://openalex.org/W3104533164","https://openalex.org/W3105684693","https://openalex.org/W3132433578","https://openalex.org/W3158459113","https://openalex.org/W3173683037","https://openalex.org/W4210354100","https://openalex.org/W4246215794","https://openalex.org/W4249285655","https://openalex.org/W4322619775","https://openalex.org/W4367310586","https://openalex.org/W4367311286","https://openalex.org/W6696916604"],"related_works":["https://openalex.org/W3086422166","https://openalex.org/W3010890513","https://openalex.org/W2053247611","https://openalex.org/W3165117444","https://openalex.org/W3016972457","https://openalex.org/W2605106030","https://openalex.org/W3117229956","https://openalex.org/W4394231753","https://openalex.org/W4220726286","https://openalex.org/W2487298868"],"abstract_inverted_index":{"Successful":[0],"data-driven":[1],"science":[2,95,138],"requires":[3],"complex":[4],"data":[5,13,40,49,87,94,115,137,159],"engineering":[6],"pipelines":[7,221],"to":[8,53,72,76,172,190,214,237],"clean,":[9],"transform,":[10],"and":[11,19,35,109,222],"alter":[12],"in":[14,29,62,97,153,192,217],"preparation":[15,88],"for":[16,79,106,158,201],"machine":[17],"learning,":[18],"robust":[20],"results":[21],"can":[22,32,234],"only":[23],"be":[24,33,77,235],"achieved":[25],"when":[26],"each":[27,60],"step":[28,61],"the":[30,39,63,66,69,118,129,202,208,231,255],"pipeline":[31,64,249],"justified,":[34],"its":[36],"effect":[37],"on":[38,207,254],"explained.":[41],"In":[42],"this":[43,98],"framework,":[44],"we":[45,100,141],"aim":[46],"at":[47,117],"providing":[48],"scientists":[50],"with":[51,175],"facilities":[52],"gain":[54],"an":[55,83,185],"in-depth":[56],"understanding":[57],"of":[58,86,114,120,132,136,150,184,210,241],"how":[59,230],"affects":[65],"data,":[67],"from":[68,82,128],"raw":[70],"input":[71],"training":[73],"sets":[74],"ready":[75],"used":[78,91,236],"learning.":[80],"Starting":[81],"extensible":[84],"set":[85,135],"operators":[89],"commonly":[90],"within":[92,123],"a":[93,102,133,143,148,155,165,181,193,239],"setting,":[96],"work":[99],"present":[101],"provenance":[103,144,168,187,197,216,233,242],"management":[104],"infrastructure":[105],"generating,":[107],"storing,":[108],"querying":[110],"very":[111],"granular":[112],"accounts":[113],"transformations,":[116],"level":[119],"individual":[121],"elements":[122],"datasets":[124],"whenever":[125],"possible.":[126],"Then,":[127],"formal":[130],"definition":[131],"core":[134],"preprocessing":[139],"operators,":[140],"derive":[142],"semantics":[145],"embodied":[146],"by":[147],"collection":[149],"templates":[151,163],"expressed":[152,253],"PROV,":[154],"standard":[156],"model":[157],"provenance.":[160],"Using":[161],"those":[162],"as":[164,252],"reference,":[166],"our":[167],"generation":[169],"algorithm":[170],"generalises":[171],"any":[173],"operator":[174],"observable":[176],"input/output":[177],"pairs.":[178],"We":[179,205,227],"provide":[180],"prototype":[182],"implementation":[183,213],"application-level":[186],"capture":[188,215],"library":[189],"produce,":[191],"semi-automatic":[194],"way,":[195],"complete":[196],"documents":[198],"that":[199,211,245],"account":[200],"entire":[203],"pipeline.":[204],"report":[206],"ability":[209],"reference":[212],"real":[218],"ML":[219],"benchmark":[220,243],"over":[223],"TCP-DI":[224],"synthetic":[225],"data.":[226],"finally":[228],"show":[229],"collected":[232],"answer":[238],"suite":[240],"queries":[244],"underpin":[246],"some":[247],"common":[248],"inspection":[250],"questions,":[251],"Data":[256],"Science":[257],"Stack":[258],"Exchange.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}