{"id":"https://openalex.org/W2288788587","doi":"https://doi.org/10.14778/2994509.2994530","title":"Explaining outputs in modern data analytics","display_name":"Explaining outputs in modern data analytics","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2288788587","doi":"https://doi.org/10.14778/2994509.2994530","mag":"2288788587"},"language":"en","primary_location":{"id":"doi:10.14778/2994509.2994530","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2994509.2994530","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/113810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045921596","display_name":"Zaheer Chothia","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zaheer Chothia","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050016902","display_name":"John Liagouris","orcid":"https://orcid.org/0000-0003-4692-3022"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Liagouris","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038292473","display_name":"Frank McSherry","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Frank McSherry","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072227627","display_name":"Timothy Roscoe","orcid":"https://orcid.org/0000-0002-8298-1126"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Timothy Roscoe","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":17.2609,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9874155,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"12","first_page":"1137","last_page":"1148"},"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":0.996399998664856,"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":0.9945999979972839,"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/dataflow","display_name":"Dataflow","score":0.9598953723907471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8410749435424805},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.7292481660842896},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7003977298736572},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6004544496536255},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.524774968624115},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4946865737438202},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.4526013731956482},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4434354305267334},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41782164573669434},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3796631693840027},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35613977909088135},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2746717929840088},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2699151337146759}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9598953723907471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410749435424805},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.7292481660842896},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7003977298736572},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6004544496536255},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.524774968624115},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4946865737438202},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.4526013731956482},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4434354305267334},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41782164573669434},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3796631693840027},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35613977909088135},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2746717929840088},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2699151337146759}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2994509.2994530","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2994509.2994530","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/113810","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/113810","pdf_url":"http://hdl.handle.net/20.500.11850/113810","source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"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":"","raw_type":"info:eu-repo/semantics/report"},{"id":"doi:10.3929/ethz-a-010601932","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-a-010601932","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"report"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/113810","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/113810","pdf_url":"http://hdl.handle.net/20.500.11850/113810","source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"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":"","raw_type":"info:eu-repo/semantics/report"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2288788587.pdf","grobid_xml":"https://content.openalex.org/works/W2288788587.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W22495568","https://openalex.org/W89955767","https://openalex.org/W135267584","https://openalex.org/W1486776102","https://openalex.org/W1552694902","https://openalex.org/W1791611415","https://openalex.org/W1976055110","https://openalex.org/W1983178058","https://openalex.org/W2008865455","https://openalex.org/W2030433745","https://openalex.org/W2072269087","https://openalex.org/W2073074467","https://openalex.org/W2082171780","https://openalex.org/W2095617559","https://openalex.org/W2100153179","https://openalex.org/W2112582917","https://openalex.org/W2119325664","https://openalex.org/W2133986470","https://openalex.org/W2136575791","https://openalex.org/W2137567142","https://openalex.org/W2144622944","https://openalex.org/W2155882070","https://openalex.org/W2165766811","https://openalex.org/W2167541073","https://openalex.org/W2171467255","https://openalex.org/W2215524946","https://openalex.org/W2263923344","https://openalex.org/W2288788587","https://openalex.org/W2293299776","https://openalex.org/W2294556882","https://openalex.org/W2295651644","https://openalex.org/W2400796894","https://openalex.org/W2404369708","https://openalex.org/W3098257205","https://openalex.org/W4365786623"],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W2783505431","https://openalex.org/W1518535918","https://openalex.org/W2521947294","https://openalex.org/W2070353846","https://openalex.org/W4236419692"],"abstract_inverted_index":{"We":[0,132,146,206],"report":[1],"on":[2,90,136,214],"the":[3,14,61,65,69,85,91,115,179,199,202,242],"design":[4],"and":[5,54,162,185,193,217],"implementation":[6,176],"of":[7,16,68,73,87,94,153,158,182,201,227,237],"a":[8,30,95,104,122,140,148,188],"general":[9,105],"framework":[10],"for":[11,107,124],"interactively":[12],"explaining":[13],"outputs":[15],"modern":[17,141],"data-parallel":[18,160],"computations,":[19],"including":[20],"iterative":[21,99],"data":[22],"analytics.":[23],"To":[24],"produce":[25],"explanations,":[26],"existing":[27],"works":[28],"adopt":[29],"naive":[31,40],"backward":[32,41],"tracing":[33,42],"approach":[34,135],"which":[35,63,125],"runs":[36],"into":[37],"known":[38],"issues;":[39],"may":[43],"identify:":[44],"(i)":[45],"too":[46],"much":[47],"information":[48,58],"that":[49,110,190,220,245],"is":[50,76],"difficult":[51],"to":[52,59,82,113,155,177,234],"process,":[53],"(ii)":[55],"not":[56,247],"enough":[57],"reproduce":[60,114],"output,":[62],"hinders":[64],"logical":[66],"debugging":[67],"program.":[70],"The":[71],"contribution":[72],"this":[74],"work":[75],"twofold.":[77],"First,":[78],"we":[79,102,163,218],"provide":[80,103],"methods":[81],"effectively":[83],"reduce":[84],"size":[86],"explanations":[88,109,224],"based":[89],"first":[92],"occurrence":[93],"record":[96],"in":[97,118,187,225],"an":[98],"computation.":[100],"Second,":[101],"method":[106],"identifying":[108],"are":[111],"sufficient":[112],"target":[116],"output":[117],"arbitrary":[119],"computations":[120],"--":[121,232,239],"problem":[123],"no":[126],"viable":[127],"solution":[128],"existed":[129],"until":[130],"now.":[131],"implement":[133,164],"our":[134,175,208],"differential":[137,168,183],"dataflow":[138,144,169],",":[139],"high-throughput,":[142],"low-latency":[143],"platform.":[145],"add":[147],"small":[149],"(but":[150],"extensible)":[151],"set":[152],"rules":[154,166],"explain":[156],"each":[157],"its":[159],"operators,":[161],"these":[165],"as":[167,198],"operators":[170],"themselves.":[171],"This":[172],"choice":[173],"allows":[174],"inherit":[178],"performance":[180],"characteristics":[181],"dataflow,":[184],"results":[186],"system":[189,209],"efficiently":[191],"computes":[192],"updates":[194],"explanatory":[195],"inputs":[196,200],"even":[197,241],"reference":[203],"computation":[204],"change.":[205],"evaluate":[207],"with":[210],"various":[211],"analytic":[212],"tasks":[213],"real":[215],"datasets,":[216],"show":[219],"it":[221],"produces":[222],"concise":[223],"tens":[226],"milliseconds,":[228],"while":[229],"remaining":[230],"faster":[231],"up":[233],"two":[235],"orders":[236],"magnitude":[238],"than":[240],"best":[243],"implementations":[244],"do":[246],"support":[248],"explanations.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
