{"id":"https://openalex.org/W2403222772","doi":"https://doi.org/10.1145/2896825.2896830","title":"DataLab","display_name":"DataLab","publication_year":2016,"publication_date":"2016-05-14","ids":{"openalex":"https://openalex.org/W2403222772","doi":"https://doi.org/10.1145/2896825.2896830","mag":"2403222772"},"language":"en","primary_location":{"id":"doi:10.1145/2896825.2896830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2896825.2896830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on BIG Data Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100354773","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0003-1684-6273"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067912085","display_name":"Fangzhou Xu","orcid":"https://orcid.org/0009-0001-5174-8882"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangzhou Xu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005279299","display_name":"Erwin Frise","orcid":"https://orcid.org/0000-0002-9281-4567"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erwin Frise","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081351055","display_name":"Siqi Wu","orcid":"https://orcid.org/0000-0002-5051-2923"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Wu","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015318204","display_name":"Bin Yu","orcid":"https://orcid.org/0000-0002-7461-625X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Yu","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007217781","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-1287-4552"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"18"},"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":0.9822999835014343,"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":0.9804999828338623,"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":0.8750003576278687},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6961308121681213},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6385859251022339},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6258136034011841},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5277895331382751},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.512638509273529},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.46073171496391296},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44340670108795166},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.31552690267562866},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2785003185272217},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23584339022636414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8750003576278687},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6961308121681213},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6385859251022339},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6258136034011841},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5277895331382751},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.512638509273529},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.46073171496391296},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44340670108795166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31552690267562866},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2785003185272217},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23584339022636414},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2896825.2896830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2896825.2896830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on BIG Data Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W641258496","https://openalex.org/W1598064945","https://openalex.org/W2078210269","https://openalex.org/W2100830825","https://openalex.org/W2103465290","https://openalex.org/W2104125540","https://openalex.org/W2107571548","https://openalex.org/W2108598243","https://openalex.org/W2111144331","https://openalex.org/W2112447569","https://openalex.org/W2116015974","https://openalex.org/W2119738171","https://openalex.org/W2119984902","https://openalex.org/W2129666400","https://openalex.org/W2130204178","https://openalex.org/W2131975293","https://openalex.org/W2144019624","https://openalex.org/W2145154883","https://openalex.org/W2189465200","https://openalex.org/W2260378577","https://openalex.org/W2296335794","https://openalex.org/W2315452447","https://openalex.org/W2396068768","https://openalex.org/W2912516925","https://openalex.org/W2996852294","https://openalex.org/W4239429564","https://openalex.org/W6676297131","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2019038080"],"abstract_inverted_index":{"One":[0],"challenge":[1],"in":[2,22,57,71,96,174],"big":[3,48,53],"data":[4,18,49,54,70,93,98,134,139],"analytics":[5,94],"is":[6,103],"the":[7,13,23,47,64,92,107,123],"lack":[8],"of":[9,66,90,125,162,169],"tools":[10],"to":[11,45,82,105,120,137],"manage":[12,46],"complex":[14],"interactions":[15],"among":[16],"code,":[17],"and":[19,69,75,102,147],"parameters,":[20],"especially":[21],"common":[24,152],"situation":[25],"where":[26],"all":[27,91],"these":[28],"factors":[29],"can":[30,156],"change":[31],"a":[32,41,72,77,97,151,171,175],"lot.":[33],"We":[34,164],"present":[35,166],"our":[36,167],"preliminary":[37],"experience":[38,168],"with":[39],"DataLab,":[40],"system":[42,136],"we":[43],"build":[44,157],"workflow.":[50],"DataLab":[51,62,87,130,149,172],"improves":[52],"analytical":[55],"workflow":[56],"several":[58],"novel":[59],"ways.":[60],"1)":[61],"manages":[63],"revision":[65],"both":[67],"code":[68,79,108,127],"coherent":[73],"system,":[74],"includes":[76],"distributed":[78],"execution":[80],"engine":[81],"run":[83],"users'":[84],"code;":[85],"2)":[86],"keeps":[88],"track":[89],"results":[95,110,124],"work":[99],"flow":[100],"graph,":[101],"able":[104],"compare":[106],"/":[109],"between":[111],"any":[112],"two":[113],"versions,":[114],"making":[115],"it":[116],"easier":[117],"for":[118],"users":[119],"intuitively":[121],"see":[122],"their":[126,141],"change;":[128],"3)":[129],"provides":[131,150],"an":[132],"efficient":[133,144],"management":[135],"separate":[138],"from":[140],"metadata,":[142],"allowing":[143],"preprocessing":[145],"filters;":[146],"4)":[148],"API":[153],"so":[154],"people":[155],"different":[158],"applications":[159],"on":[160],"top":[161],"it.":[163],"also":[165],"applying":[170],"prototype":[173],"real":[176],"bioinformatics":[177],"application.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}