{"id":"https://openalex.org/W2030433745","doi":"https://doi.org/10.1145/2523616.2523619","title":"Scalable lineage capture for debugging DISC analytics","display_name":"Scalable lineage capture for debugging DISC analytics","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2030433745","doi":"https://doi.org/10.1145/2523616.2523619","mag":"2030433745"},"language":"en","primary_location":{"id":"doi:10.1145/2523616.2523619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2523616.2523619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th annual Symposium on Cloud 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/A5006816032","display_name":"Dionysios Logothetis","orcid":"https://orcid.org/0009-0006-2501-1074"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dionysios Logothetis","raw_affiliation_strings":["Telefonica Research","Telefonica Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telefonica Research","institution_ids":["https://openalex.org/I4210134591"]},{"raw_affiliation_string":"Telefonica Research#TAB#","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070289315","display_name":"Soumyarupa De","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Soumyarupa De","raw_affiliation_strings":["Microsoft, Inc","MICROSOFT INC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Inc","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"raw_affiliation_string":"MICROSOFT INC","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113537993","display_name":"Kenneth Yocum","orcid":null},"institutions":[{"id":"https://openalex.org/I178645029","display_name":"Illumina (United States)","ror":"https://ror.org/05k34t975","country_code":"US","type":"company","lineage":["https://openalex.org/I178645029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Yocum","raw_affiliation_strings":["U.C. San Diego and Illumina, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U.C. San Diego and Illumina, Inc","institution_ids":["https://openalex.org/I178645029"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5226,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96910969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/scalability","display_name":"Scalability","score":0.8372533321380615},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.8044006824493408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8002928495407104},{"id":"https://openalex.org/keywords/lineage","display_name":"Lineage (genetic)","score":0.6414691209793091},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6363168954849243},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6011813879013062},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43331417441368103},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.421356737613678},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3547458350658417},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33680105209350586},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23667922616004944},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06472837924957275}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8372533321380615},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.8044006824493408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002928495407104},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.6414691209793091},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6363168954849243},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6011813879013062},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43331417441368103},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.421356737613678},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3547458350658417},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33680105209350586},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23667922616004944},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06472837924957275},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2523616.2523619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2523616.2523619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th annual Symposium on Cloud Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.278.4110","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.278.4110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucsd.edu/%7Edlogothetis/docs/tr-cse2012-0990.pdf","raw_type":"text"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt2hm9z9d2","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/2hm9z9d2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[{"id":"https://openalex.org/G1887681546","display_name":null,"funder_award_id":"CCF-1048296, CNS-1219220","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G4863352445","display_name":null,"funder_award_id":"CCF-1048296, CNS-1219220","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W135267584","https://openalex.org/W161296890","https://openalex.org/W1538427300","https://openalex.org/W1963763518","https://openalex.org/W1978239142","https://openalex.org/W2037069087","https://openalex.org/W2053703914","https://openalex.org/W2083541728","https://openalex.org/W2098935637","https://openalex.org/W2100153179","https://openalex.org/W2100830825","https://openalex.org/W2112582917","https://openalex.org/W2115501618","https://openalex.org/W2123009189","https://openalex.org/W2124985265","https://openalex.org/W2133986470","https://openalex.org/W2135361281","https://openalex.org/W2137567142","https://openalex.org/W2157814900","https://openalex.org/W2167541073","https://openalex.org/W2170646878","https://openalex.org/W2400796894","https://openalex.org/W6605500462","https://openalex.org/W6606537055"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W2387706296","https://openalex.org/W2480201319","https://openalex.org/W2294325978","https://openalex.org/W2890345561"],"abstract_inverted_index":{"A":[0],"fundamental":[1],"challenge":[2],"for":[3,22],"big-data":[4],"analytics":[5],"is":[6],"how":[7],"to":[8,29,42],"efficiently":[9],"tune":[10],"and":[11,24,31,77],"debug":[12],"multi-step":[13],"dataflows.":[14],"This":[15],"paper":[16],"presents":[17],"Newt,":[18],"a":[19,48,72],"scalable":[20,53],"architecture":[21],"capturing":[23],"using":[25],"record-level":[26],"data":[27,51,62],"lineage":[28,46,75],"discover":[30],"resolve":[32],"errors":[33],"in":[34],"analytics.":[35],"Newt's":[36],"flexible":[37],"instrumentation":[38],"allows":[39],"system":[40],"developers":[41],"collect":[43],"this":[44,69],"fine-grain":[45],"from":[47],"range":[49],"of":[50,61],"intensive":[52],"computing":[54],"(DISC)":[55],"architectures,":[56],"actively":[57],"recording":[58],"the":[59],"flow":[60],"through":[63],"multi-step,":[64],"user-defined":[65],"transformations.":[66],"Newt":[67],"pairs":[68],"API":[70],"with":[71],"scale-out,":[73],"fault-tolerant":[74],"store":[76],"query":[78],"engine.":[79]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
