{"id":"https://openalex.org/W3030932193","doi":"https://doi.org/10.1109/icde48307.2020.00140","title":"Data Sentinel: A Declarative Production-Scale Data Validation Platform","display_name":"Data Sentinel: A Declarative Production-Scale Data Validation Platform","publication_year":2020,"publication_date":"2020-04-01","ids":{"openalex":"https://openalex.org/W3030932193","doi":"https://doi.org/10.1109/icde48307.2020.00140","mag":"3030932193"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde48307.2020.00140","pdf_url":null,"source":{"id":"https://openalex.org/S4363607857","display_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5113484277","display_name":"Arun Swami","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Swami","raw_affiliation_strings":["LinkedIn Corporation, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Corporation, Sunnyvale, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103486798","display_name":"Sriram Vasudevan","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Vasudevan","raw_affiliation_strings":["LinkedIn Corporation, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Corporation, Sunnyvale, USA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024387022","display_name":"Joojay Huyn","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joojay Huyn","raw_affiliation_strings":["LinkedIn Corporation, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Corporation, Sunnyvale, USA","institution_ids":["https://openalex.org/I1316064682"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.467,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.999281,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9918,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9789,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-validation","display_name":"Data validation","score":0.5206232},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.49967098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084717},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.753206},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.55241024},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.5206232},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5000949},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.49967098},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4702068},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46443567},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45854974},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.45701885},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.456309},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.42782786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34517747},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30568075},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.18207902},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde48307.2020.00140","pdf_url":null,"source":{"id":"https://openalex.org/S4363607857","display_name":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":10,"referenced_works":["https://openalex.org/W1649645444","https://openalex.org/W2038412523","https://openalex.org/W2068376489","https://openalex.org/W2105947650","https://openalex.org/W2117366235","https://openalex.org/W2144982963","https://openalex.org/W2542459869","https://openalex.org/W2584555500","https://openalex.org/W2889249015","https://openalex.org/W2946595616"],"related_works":["https://openalex.org/W4309157347","https://openalex.org/W4233433221","https://openalex.org/W4212820174","https://openalex.org/W3176518448","https://openalex.org/W3172743089","https://openalex.org/W3082463427","https://openalex.org/W3035049364","https://openalex.org/W2797388296","https://openalex.org/W193233024","https://openalex.org/W1026360118"],"abstract_inverted_index":{"Many":[0],"organizations":[1],"process":[2],"big":[3],"data":[4,12,36,53,63,76,86,97,111,125,132,194,200,205,222],"for":[5,149,158,239],"important":[6],"business":[7],"operations":[8],"and":[9,72,74,117,134,152,177,198,203,235,244],"decisions.":[10],"Hence,":[11],"quality":[13,19,37,60,64,77,98],"greatly":[14],"affects":[15],"their":[16],"success.":[17],"Data":[18,106,128,144,166,170,184,217],"problems":[20],"continue":[21],"to":[22,66,69,79,138,161,174,191,233],"be":[23,67],"widespread,":[24],"costing":[25],"US":[26],"businesses":[27],"an":[28,139],"estimated":[29],"$600":[30],"billion":[31],"annually.":[32],"To":[33,95,168],"date,":[34],"addressing":[35],"in":[38,54,99,179],"production":[39,100,180,240],"environments":[40,101,241],"still":[41],"poses":[42],"many":[43],"challenges:":[44],"easily":[45,80,140],"defining":[46],"properties":[47],"of":[48,210],"high-quality":[49],"data;":[50,61],"validating":[51],"production-scale":[52,110,221],"a":[55,108,115,188,219],"timely":[56],"manner;":[57],"debugging":[58],"poor":[59],"designing":[62,75],"solutions":[65,78,88],"easy":[68,157],"use,":[70,175],"understand,":[71,176],"operate;":[73],"integrate":[81,164],"with":[82,165,251],"other":[83,159],"systems.":[84],"Current":[85],"validation":[87,112,201,223],"do":[89],"not":[90],"comprehensively":[91],"address":[92,96],"these":[93,131],"challenges.":[94],"at":[102,227],"LinkedIn,":[103],"we":[104,182],"developed":[105],"Sentinel,":[107,218],"declarative":[109,220],"platform.":[113],"In":[114],"simple":[116],"well-structured":[118],"configuration,":[119],"users":[120],"declaratively":[121],"specify":[122,193],"the":[123,136,150,214],"desired":[124],"checks.":[126],"Then,":[127],"Sentinel":[129,145,171,185],"performs":[130],"checks":[133],"writes":[135],"results":[137],"understandable":[141],"report.":[142,153],"Furthermore,":[143],"provides":[146],"well-defined":[147],"schemas":[148],"configuration":[151],"This":[154],"makes":[155],"it":[156],"systems":[160,238],"interface":[162],"or":[163],"Sentinel.":[167],"make":[169],"even":[172],"easier":[173],"operate":[178],"environments,":[181],"provide":[183],"Service":[186],"(DSS),":[187],"complementary":[189],"system":[190],"help":[192],"checks,":[195],"schedule,":[196],"deploy,":[197],"tune":[199],"jobs,":[202],"understand":[204],"checking":[206],"results.":[207],"The":[208],"contributions":[209],"this":[211],"paper":[212],"include":[213],"following:":[215],"1)":[216],"platform":[224],"successfully":[225],"deployed":[226],"LinkedIn":[228],"2)":[229],"A":[230],"generic":[231],"design":[232],"build":[234],"deploy":[236],"similar":[237,252],"3)":[242],"Experiences":[243],"lessons":[245],"learned":[246],"that":[247],"can":[248],"benefit":[249],"practitioners":[250],"objectives.":[253]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3030932193","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2024-12-13T02:46:20.949887","created_date":"2020-06-05"}