{"id":"https://openalex.org/W2922230063","doi":"https://doi.org/10.1109/access.2019.2903727","title":"Why-Diff: Exploiting Provenance to Understand Outcome Differences From Non-Identical Reproduced Workflows","display_name":"Why-Diff: Exploiting Provenance to Understand Outcome Differences From Non-Identical Reproduced Workflows","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2922230063","doi":"https://doi.org/10.1109/access.2019.2903727","mag":"2922230063"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2903727","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2903727","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08662612.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08662612.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068813254","display_name":"Priyaa Thavasimani","orcid":"https://orcid.org/0000-0002-4846-1661"},"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":"Priyaa Thavasimani","raw_affiliation_strings":["School of Computing, Newcastle University, Newcastle upon Tyne, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4846-1661","affiliations":[{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052190130","display_name":"Jacek Ca\u0142a","orcid":"https://orcid.org/0000-0002-8322-4370"},"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":"Jacek Cala","raw_affiliation_strings":["School of Computing, Newcastle University, Newcastle upon Tyne, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"last","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":["School of Computing, Newcastle University, Newcastle upon Tyne, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, U.K","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84884186"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.2725,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89414285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"34973","last_page":"34990"},"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":0.9948999881744385,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9894999861717224,"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/workflow","display_name":"Workflow","score":0.9417828917503357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7942864894866943},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.6392215490341187},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5440002083778381},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.4690081775188446},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.41659313440322876},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3720349669456482},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35106444358825684},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31289321184158325},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2933398485183716},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.21644890308380127},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20317357778549194}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9417828917503357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942864894866943},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6392215490341187},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5440002083778381},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.4690081775188446},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.41659313440322876},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3720349669456482},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35106444358825684},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31289321184158325},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2933398485183716},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.21644890308380127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20317357778549194},{"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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/access.2019.2903727","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2903727","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08662612.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8277c902be1c4539ab15d66da8c02365","is_oa":true,"landing_page_url":"https://doaj.org/article/8277c902be1c4539ab15d66da8c02365","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 34973-34990 (2019)","raw_type":"article"},{"id":"pmh:oai:eprint.ncl.ac.uk:256703","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402485","display_name":"Newcastle University ePrints (Newcastle Univesity)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I84884186","host_organization_name":"Newcastle University","host_organization_lineage":["https://openalex.org/I84884186"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/7d61fc82-088f-453f-9553-294a50065af8","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/7d61fc82-088f-453f-9553-294a50065af8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Thavasimani, P, Cala, J & Missier, P 2019, 'Why-Diff: Exploiting Provenance to Understand Outcome Differences From Non-Identical Reproduced Workflows', IEEE Access. https://doi.org/10.1109/ACCESS.2019.2903727","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/face317b-9ddd-4c7c-872e-d272e135e98f","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/face317b-9ddd-4c7c-872e-d272e135e98f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Thavasimani , P , Cala , J & Missier , P 2019 , ' Why-Diff : Exploiting Provenance to Understand Outcome Differences from Non-Identical Reproduced Workflows ' , IEEE Access , vol. 7 , 8662612 , pp. 34973-34990 . https://doi.org/10.1109/ACCESS.2019.2903727","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:publications/7d61fc82-088f-453f-9553-294a50065af8","is_oa":true,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/whydiff-exploiting-provenance-to-understand-outcome-differences-from-nonidentical-reproduced-workflows(7d61fc82-088f-453f-9553-294a50065af8).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Thavasimani, P, Cala, J & Missier, P 2019, 'Why-Diff: Exploiting Provenance to Understand Outcome Differences From Non-Identical Reproduced Workflows', IEEE Access. https://doi.org/10.1109/ACCESS.2019.2903727","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2903727","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2903727","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08662612.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2961310300","display_name":null,"funder_award_id":"EP/N01426X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320295","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2922230063.pdf","grobid_xml":"https://content.openalex.org/works/W2922230063.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W242548698","https://openalex.org/W1529006120","https://openalex.org/W1636538241","https://openalex.org/W1970640098","https://openalex.org/W1977690765","https://openalex.org/W1978802375","https://openalex.org/W1983833794","https://openalex.org/W2001907377","https://openalex.org/W2028817191","https://openalex.org/W2116783139","https://openalex.org/W2145154883","https://openalex.org/W2146054955","https://openalex.org/W2156517224","https://openalex.org/W2172143128","https://openalex.org/W2221287604","https://openalex.org/W2346143774","https://openalex.org/W2406493898","https://openalex.org/W2462343204","https://openalex.org/W2467189103","https://openalex.org/W2585397740","https://openalex.org/W2620485168","https://openalex.org/W2784233715","https://openalex.org/W2908032717","https://openalex.org/W2962678654","https://openalex.org/W4254560685","https://openalex.org/W4321508270","https://openalex.org/W6636833595"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2384715785","https://openalex.org/W2349624418","https://openalex.org/W2064459023","https://openalex.org/W3200266554","https://openalex.org/W4320341575"],"abstract_inverted_index":{"Data":[0],"analytics":[1],"processes":[2],"such":[3],"as":[4,94,114,125,127,194,196],"scientific":[5],"workflows":[6,124,193],"tend":[7],"to":[8,39,59,87,158],"be":[9,83,156],"executed":[10],"repeatedly,":[11],"with":[12,174],"varying":[13],"dependencies":[14],"and":[15],"input":[16],"datasets.":[17],"The":[18],"case":[19],"has":[20],"been":[21],"made":[22],"in":[23,80,103,122],"the":[24,28,31,36,48,63,95,104,123,137,163,183],"past":[25],"for":[26],"tracking":[27],"provenance":[29,51,142],"of":[30,68,97,101,140,162,165,182,191],"final":[32],"information":[33],"products":[34],"through":[35],"workflow":[37,76,111,147,166,186],"steps,":[38],"enable":[40],"their":[41,130],"reproducibility.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,117,179],"explore":[47,88],"hypothesis":[49],"that":[50,154],"traces":[52,143],"recorded":[53],"during":[54],"execution":[55],"are":[56],"also":[57],"instrumental":[58],"answering":[60],"questions":[61],"about":[62],"observed":[64,169],"differences":[65,79,167],"between":[66,185],"sets":[67],"results":[69,187],"obtained":[70],"from":[71,145],"similar":[72],"but":[73],"not":[74],"identical":[75],"configurations.":[77],"Such":[78],"configurations":[81],"may":[82],"introduced":[84],"deliberately,":[85],"i.e.,":[86],"process":[89],"variations":[90,121,128],"or":[91,100],"accidentally,":[92],"typically":[93],"result":[96],"porting":[98],"efforts":[99],"changes":[102],"computing":[105],"environment.":[106],"Using":[107],"a":[108,115,151,189],"commonly":[109],"used":[110,157],"programming":[112],"model":[113],"reference,":[116],"consider":[118],"both":[119],"structural":[120],"well":[126,195],"within":[129],"individual":[131],"components.":[132],"Our":[133],"why-diff":[134],"algorithm":[135],"compares":[136],"graph":[138,153,176],"representations":[139],"two":[141,146],"derived":[144],"variations.":[148],"It":[149],"produces":[150],"delta":[152],"can":[155],"produce":[159],"human-readable":[160],"explanations":[161,181],"impact":[164],"on":[168],"output":[170],"differences.":[171],"We":[172],"report":[173,180],"Neo4j":[175],"database.":[177],"Further,":[178],"difference":[184],"using":[188],"suite":[190],"synthetic":[192],"real-world":[197],"workflows.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}