{"id":"https://openalex.org/W1967957721","doi":"https://doi.org/10.1145/1851476.1851558","title":"Monitoring data quality in Kepler","display_name":"Monitoring data quality in Kepler","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W1967957721","doi":"https://doi.org/10.1145/1851476.1851558","mag":"1967957721"},"language":"en","primary_location":{"id":"doi:10.1145/1851476.1851558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","raw_type":"proceedings-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/A5089984404","display_name":"Aisa Na'im","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Aisa Na'im","raw_affiliation_strings":["Monash University, Caulfield East, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Caulfield East, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002534857","display_name":"Daniel Crawl","orcid":"https://orcid.org/0000-0003-1013-8241"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Crawl","raw_affiliation_strings":["San Diego Supercomputer Centre, San Diego, CA","San Diego Supercomputer Centre, San Diego, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Centre, San Diego, CA","institution_ids":["https://openalex.org/I181653535"]},{"raw_affiliation_string":"San Diego Supercomputer Centre, San Diego, CA#TAB#","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054393020","display_name":"Maria Indrawan","orcid":"https://orcid.org/0000-0001-5072-9826"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Maria Indrawan","raw_affiliation_strings":["Monash University, Caulfield East, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Caulfield East, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028701796","display_name":"\u0130lkay Alt\u0131nta\u015f","orcid":"https://orcid.org/0000-0002-2196-0305"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilkay Altintas","raw_affiliation_strings":["San Diego Supercomputer Centre, San Diego, CA","San Diego Supercomputer Centre, San Diego, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Centre, San Diego, CA","institution_ids":["https://openalex.org/I181653535"]},{"raw_affiliation_string":"San Diego Supercomputer Centre, San Diego, CA#TAB#","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109141637","display_name":"Shulei Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shulei Sun","raw_affiliation_strings":["University of California San Diego","University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089984404"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":3.3345,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92769993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2008","issue":null,"first_page":"560","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9908000230789185,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.980400025844574,"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":0.886585533618927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129390478134155},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6256869435310364},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5717630982398987},{"id":"https://openalex.org/keywords/kepler","display_name":"Kepler","score":0.5394045114517212},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5375992655754089},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.5209245085716248},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5174620747566223},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.4608646631240845},{"id":"https://openalex.org/keywords/scientific-instrument","display_name":"Scientific instrument","score":0.45545971393585205},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.451550155878067},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43247532844543457},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.4263465404510498},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4124356210231781},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3593007028102875},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.11642524600028992}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.886585533618927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129390478134155},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6256869435310364},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5717630982398987},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.5394045114517212},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5375992655754089},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.5209245085716248},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5174620747566223},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.4608646631240845},{"id":"https://openalex.org/C207520454","wikidata":"https://www.wikidata.org/wiki/Q3099911","display_name":"Scientific instrument","level":2,"score":0.45545971393585205},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.451550155878067},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43247532844543457},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.4263465404510498},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4124356210231781},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3593007028102875},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.11642524600028992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1851476.1851558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W126044612","https://openalex.org/W628672609","https://openalex.org/W1549493899","https://openalex.org/W1780933788","https://openalex.org/W1964956995","https://openalex.org/W1983833794","https://openalex.org/W2042893247","https://openalex.org/W2046813315","https://openalex.org/W2057404362","https://openalex.org/W2061680337","https://openalex.org/W2092618176","https://openalex.org/W2098028511","https://openalex.org/W2120886598","https://openalex.org/W2169180789","https://openalex.org/W6684629497"],"related_works":["https://openalex.org/W2379425324","https://openalex.org/W2373541195","https://openalex.org/W2376410910","https://openalex.org/W2091596831","https://openalex.org/W2365658322","https://openalex.org/W2352344200","https://openalex.org/W329008868","https://openalex.org/W2367975678","https://openalex.org/W2375552622","https://openalex.org/W2906819665"],"abstract_inverted_index":{"Data":[0],"quality":[1,43,115],"is":[2,38,86],"an":[3,104],"important":[4],"component":[5],"of":[6,20,33,44],"modern":[7],"scientific":[8,11,35,57,109],"discovery.":[9],"Many":[10],"discovery":[12],"processes":[13],"consume":[14],"data":[15,63,81,114],"from":[16],"a":[17,34],"diverse":[18],"array":[19],"resources":[21],"such":[22],"as":[23],"streaming":[24],"sensor":[25],"networks,":[26],"web":[27],"services,":[28],"and":[29,67,78,116,122],"databases.":[30],"The":[31],"validity":[32],"computation's":[36],"results":[37],"highly":[39],"dependent":[40],"on":[41],"the":[42,80,107],"these":[45,99],"input":[46],"data.":[47],"Scientific":[48],"workflow":[49,84,110],"systems":[50],"are":[51],"being":[52],"increasingly":[53],"used":[54],"to":[55,96],"automate":[56],"computations":[58],"by":[59],"facilitating":[60],"experiment":[61],"design,":[62],"capture,":[64],"integration,":[65],"processing,":[66],"analysis.":[68],"These":[69],"workflows":[70],"may":[71],"execute":[72],"in":[73,91,106],"grid":[74],"or":[75,89],"cloud":[76],"environments,":[77],"if":[79],"produced":[82],"during":[83],"execution":[85,93],"deemed":[87],"unusable":[88],"low":[90],"quality,":[92],"should":[94],"stop":[95],"prevent":[97],"wasting":[98],"valuable":[100],"resources.":[101],"We":[102],"propose":[103],"approach":[105],"Kepler":[108],"system":[111],"for":[112,120],"monitoring":[113],"demonstrate":[117],"its":[118],"use":[119],"oceanography":[121],"bioinformatics":[123],"domains.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
