{"id":"https://openalex.org/W2260378577","doi":"https://doi.org/10.14778/2824032.2824100","title":"Collaborative data analytics with DataHub","display_name":"Collaborative data analytics with DataHub","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2260378577","doi":"https://doi.org/10.14778/2824032.2824100","mag":"2260378577","pmid":"https://pubmed.ncbi.nlm.nih.gov/26844007"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824100","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824100","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/100937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048422887","display_name":"Anant Bhardwaj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Anant Bhardwaj","raw_affiliation_strings":["MIT","Chicago","U. Maryland","U. Illinois (UIUC"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"Chicago","institution_ids":[]},{"raw_affiliation_string":"U. Maryland","institution_ids":[]},{"raw_affiliation_string":"U. Illinois (UIUC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113637223","display_name":"Amol Deshpande","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122018","display_name":"University of Maryland Extension","ror":"https://ror.org/03r8q5f36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210122018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amol Deshpande","raw_affiliation_strings":["U. Maryland (UMD)"],"affiliations":[{"raw_affiliation_string":"U. Maryland (UMD)","institution_ids":["https://openalex.org/I4210122018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041264166","display_name":"Aaron J. Elmore","orcid":"https://orcid.org/0000-0002-4062-8826"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron J. Elmore","raw_affiliation_strings":["U. Chicago"],"affiliations":[{"raw_affiliation_string":"U. Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028448267","display_name":"David R. Karger","orcid":"https://orcid.org/0000-0002-0024-5847"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"David Karger","raw_affiliation_strings":["MIT","U. Illinois (UIUC","U. Maryland","Chicago"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"U. Illinois (UIUC","institution_ids":[]},{"raw_affiliation_string":"U. Maryland","institution_ids":[]},{"raw_affiliation_string":"Chicago","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sam Madden","raw_affiliation_strings":["MIT","U. Illinois (UIUC","U. Maryland","Chicago"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"U. Illinois (UIUC","institution_ids":[]},{"raw_affiliation_string":"U. Maryland","institution_ids":[]},{"raw_affiliation_string":"Chicago","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013608601","display_name":"Aditya Parameswaran","orcid":"https://orcid.org/0000-0002-4538-4752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Parameswaran","raw_affiliation_strings":["U. Illinois (UIUC)"],"affiliations":[{"raw_affiliation_string":"U. Illinois (UIUC)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048500159","display_name":"Harihar Subramanyam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Harihar Subramanyam","raw_affiliation_strings":["MIT","U. Illinois (UIUC","Chicago","U. Maryland"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"U. Illinois (UIUC","institution_ids":[]},{"raw_affiliation_string":"Chicago","institution_ids":[]},{"raw_affiliation_string":"U. Maryland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia"],"affiliations":[{"raw_affiliation_string":"Columbia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114357284","display_name":"Rebecca Zhang","orcid":"https://orcid.org/0000-0001-7325-283X"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Rebecca Zhang","raw_affiliation_strings":["MIT","U. Illinois (UIUC","Chicago","U. Maryland"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]},{"raw_affiliation_string":"U. Illinois (UIUC","institution_ids":[]},{"raw_affiliation_string":"Chicago","institution_ids":[]},{"raw_affiliation_string":"U. Maryland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5048422887"],"corresponding_institution_ids":["https://openalex.org/I4210109586"],"apc_list":null,"apc_paid":null,"fwci":17.4314,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98795326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"12","first_page":"1916","last_page":"1919"},"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":0.9959999918937683,"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":0.9835000038146973,"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/computer-science","display_name":"Computer science","score":0.8577093482017517},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.7543690204620361},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7448495626449585},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.7058440446853638},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5395898222923279},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4842826724052429},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4594787657260895},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3708266317844391},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34940287470817566},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34285983443260193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3290899395942688},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20930612087249756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577093482017517},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.7543690204620361},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7448495626449585},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.7058440446853638},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5395898222923279},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4842826724052429},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4594787657260895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3708266317844391},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34940287470817566},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34285983443260193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3290899395942688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20930612087249756}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.14778/2824032.2824100","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824100","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":"pmid:26844007","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26844007","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.695.3515","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.695.3515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-cs-students.stanford.edu/%7Eadityagp/papers/datahubdemo.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/100937","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/100937","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt1mj8x6h0","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/1mj8x6h0","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"chapter"},{"id":"pmh:oai:pubmedcentral.nih.gov:4734646","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4734646","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4734646","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings VLDB Endowment","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/100937","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/100937","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W297231882","https://openalex.org/W641186890","https://openalex.org/W2023758372","https://openalex.org/W2064766209","https://openalex.org/W2093189534","https://openalex.org/W2098961002","https://openalex.org/W2130204178","https://openalex.org/W2141517858","https://openalex.org/W2146105230","https://openalex.org/W2147931936","https://openalex.org/W2167541073","https://openalex.org/W2950879962","https://openalex.org/W2951968982","https://openalex.org/W7065927269"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W2782165897","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W2188981919","https://openalex.org/W3084909426","https://openalex.org/W3213706029","https://openalex.org/W2236574726"],"abstract_inverted_index":{"While":[0],"there":[1],"have":[2,19],"been":[3],"many":[4,29],"solutions":[5,18],"proposed":[6],"for":[7,22,48,126,206],"storing":[8,210],"and":[9,31,37,51,81,99,111,116,139,177,182,209],"analyzing":[10,207],"large":[11],"volumes":[12],"of":[13,16,43,90,156,213],"data,":[14],"all":[15],"these":[17],"limited":[20],"support":[21],"<i>collaborative":[23],"data":[24,49,96,141,148,151,164,208,214],"analytics</i>,":[25],"especially":[26],"given":[27],"the":[28,67,87,91,109,113,162,180,183,199,211],"individuals":[30],"teams":[32],"are":[33,185],"simultaneously":[34],"analyzing,":[35],"modifying":[36],"exchanging":[38],"datasets,":[39],"employing":[40],"a":[41,63],"number":[42],"heterogeneous":[44],"tools":[45],"or":[46,57],"languages":[47],"analysis,":[50],"writing":[52],"scripts":[53],"to":[54,69,135,171,197],"clean,":[55],"preprocess,":[56],"query":[58],"data.":[59],"We":[60,84],"demonstrate":[61,86],"DataHub,":[62],"unified":[64],"platform":[65],"with":[66,78],"ability":[68],"load,":[70],"store,":[71],"query,":[72,138],"collaboratively":[73],"analyze,":[74],"interactively":[75],"visualize,":[76],"interface":[77],"external":[79],"applications,":[80],"share":[82],"datasets.":[83],"will":[85,132,168,194],"following":[88],"aspects":[89],"DataHub":[92,160],"platform:":[93],"(a)":[94],"<i>flexible":[95],"storage,":[97],"sharing,":[98],"native":[100],"versioning":[101],"capabilities</i>:":[102],"multiple":[103],"conference":[104,130,166,192],"attendees":[105,131,167,193],"can":[106],"concurrently":[107],"update":[108],"database":[110],"browse":[112],"different":[114],"versions":[115],"inspect":[117],"conflicts;":[118],"(b)":[119],"<i>an":[120],"app":[121],"ecosystem":[122],"that":[123],"hosts":[124],"apps":[125],"various":[127],"data-processing":[128],"activities</i>:":[129],"be":[133,169,195],"able":[134,170,196],"effortlessly":[136],"ingest,":[137],"visualize":[140],"using":[142],"our":[143],"existing":[144],"apps;":[145],"(c)":[146],"<i>thrift-based":[147],"serialization":[149],"permits":[150],"analysis":[152],"in":[153,174,188],"any":[154],"combination":[155],"20+":[157],"languages</i>,":[158],"<i>with":[159],"as":[161],"common":[163],"store</i>:":[165],"analyze":[172],"datasets":[173],"R,":[175],"Python,":[176],"Matlab,":[178],"while":[179],"inputs":[181],"results":[184,212],"still":[186],"stored":[187],"DataHub.":[189],"In":[190],"particular,":[191],"use":[198],"<i>DataHub":[200],"notebook</i>":[201],"-":[202],"an":[203],"IPython-based":[204],"notebook":[205],"analysis.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
