{"id":"https://openalex.org/W2044547639","doi":"https://doi.org/10.1109/icde.2013.6544881","title":"SubZero: A fine-grained lineage system for scientific databases","display_name":"SubZero: A fine-grained lineage system for scientific databases","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2044547639","doi":"https://doi.org/10.1109/icde.2013.6544881","mag":"2044547639"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2013.6544881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2013.6544881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 29th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/90854","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Wu","raw_affiliation_strings":["CSAIL, MIT, Cambridge, MA, USA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Madden","raw_affiliation_strings":["CSAIL, MIT, Cambridge, MA, USA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Stonebraker","raw_affiliation_strings":["CSAIL, MIT, Cambridge, MA, USA","CSAIL - MIT, Cambridge, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"CSAIL - MIT, Cambridge, MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"865","last_page":"876"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9954000115394592,"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/lineage","display_name":"Lineage (genetic)","score":0.8212810754776001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7938457727432251},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7218316793441772},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6320441961288452},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.560738742351532},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4441588222980499},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4396378695964813},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43942970037460327},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4347216486930847},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14627650380134583},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12390550971031189}],"concepts":[{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.8212810754776001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938457727432251},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7218316793441772},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6320441961288452},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.560738742351532},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4441588222980499},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4396378695964813},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43942970037460327},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4347216486930847},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14627650380134583},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12390550971031189},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icde.2013.6544881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2013.6544881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 29th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.7094","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.7094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://db.csail.mit.edu/pubs/subzero.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.306.4980","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.306.4980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mit.edu/~eugenewu/files/papers/subzero-icde13.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/90854","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/90854","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/90854","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/90854","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W22495568","https://openalex.org/W56918557","https://openalex.org/W135267584","https://openalex.org/W1486776102","https://openalex.org/W1559528097","https://openalex.org/W1620997626","https://openalex.org/W1677767588","https://openalex.org/W1972743486","https://openalex.org/W1983178058","https://openalex.org/W2019379313","https://openalex.org/W2035168235","https://openalex.org/W2098935637","https://openalex.org/W2112525062","https://openalex.org/W2123663722","https://openalex.org/W2133986470","https://openalex.org/W2136482257","https://openalex.org/W2140855509","https://openalex.org/W2167541073","https://openalex.org/W2172143128","https://openalex.org/W2200883250","https://openalex.org/W3104062568","https://openalex.org/W4252427272","https://openalex.org/W4299639459","https://openalex.org/W6602324189","https://openalex.org/W6605500462","https://openalex.org/W6637354909","https://openalex.org/W6646101001","https://openalex.org/W6763976586"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W1556451512","https://openalex.org/W2964988449","https://openalex.org/W1555349535","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W188202134","https://openalex.org/W4255934811"],"abstract_inverted_index":{"Data":[0],"lineage":[1,25,91,101,114,137],"is":[2,40],"a":[3,71,104],"key":[4],"component":[5],"of":[6,46,73,106],"provenance":[7],"that":[8,76,93,132],"helps":[9],"scientists":[10,65],"track":[11],"and":[12,17,52,56,103,128,130,152],"query":[13,138],"relationships":[14,26],"between":[15],"input":[16],"output":[18],"data.":[19],"While":[20],"current":[21],"systems":[22],"readily":[23],"support":[24,35,47],"at":[27,36],"the":[28,44,53,87,100],"file":[29],"or":[30],"data":[31],"array":[32],"level,":[33],"finer-grained":[34],"an":[37],"array-cell":[38],"level":[39],"impractical":[41],"due":[42],"to":[43,59,69,80,89,142],"lack":[45],"for":[48],"user":[49,117],"defined":[50,118],"operators":[51],"high":[54],"runtime":[55,151],"storage":[57],"overhead":[58],"store":[60,82],"such":[61],"lineage.":[62,84],"We":[63,85],"interviewed":[64],"in":[66,99],"several":[67],"domains":[68],"identify":[70],"set":[72,105],"common":[74,96],"semantics":[75],"can":[77,111,135],"be":[78],"leveraged":[79],"efficiently":[81,94],"fine-grained":[83],"use":[86],"insights":[88],"define":[90],"representations":[92],"capture":[95],"locality":[97],"properties":[98],"data,":[102],"APIs":[107],"so":[108],"operator":[109],"developers":[110],"easily":[112],"export":[113],"information":[115],"from":[116,126],"operators.":[119],"Finally,":[120],"we":[121],"introduce":[122],"two":[123],"benchmarks":[124],"derived":[125],"astronomy":[127],"genomics,":[129],"show":[131],"our":[133],"techniques":[134],"reduce":[136],"costs":[139],"by":[140],"up":[141],"10\u00d7":[143],"while":[144],"incuring":[145],"substantially":[146],"less":[147],"impact":[148],"on":[149],"workflow":[150],"storage.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
