{"id":"https://openalex.org/W2594526919","doi":"https://doi.org/10.1109/escience.2016.7870919","title":"Crossing analytics systems: A case for integrated provenance in data lakes","display_name":"Crossing analytics systems: A case for integrated provenance in data lakes","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2594526919","doi":"https://doi.org/10.1109/escience.2016.7870919","mag":"2594526919"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2016.7870919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2016.7870919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 12th International Conference on e-Science (e-Science)","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/A5039777765","display_name":"Isuru Suriarachchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Isuru Suriarachchi","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060672408","display_name":"Beth Plale","orcid":"https://orcid.org/0000-0003-2164-8132"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beth Plale","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039777765"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":9.7487,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97588105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"354"},"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/T11937","display_name":"Research Data Management Practices","score":0.9973000288009644,"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/T11719","display_name":"Data Quality and Management","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7427893877029419},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.695023775100708},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6495493054389954},{"id":"https://openalex.org/keywords/traceability","display_name":"Traceability","score":0.6199115514755249},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6193705797195435},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5349264144897461},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.5104221701622009},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5101032853126526},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.506702721118927},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4967978298664093},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.4522833824157715},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4501773715019226},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4488089084625244},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4170375168323517},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2521994709968567},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.22860625386238098},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.2036859095096588},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.19935911893844604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427893877029419},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.695023775100708},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6495493054389954},{"id":"https://openalex.org/C153876917","wikidata":"https://www.wikidata.org/wiki/Q899704","display_name":"Traceability","level":2,"score":0.6199115514755249},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6193705797195435},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5349264144897461},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5104221701622009},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5101032853126526},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.506702721118927},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4967978298664093},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.4522833824157715},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4501773715019226},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4488089084625244},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4170375168323517},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2521994709968567},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.22860625386238098},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2036859095096588},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.19935911893844604},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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":1,"locations":[{"id":"doi:10.1109/escience.2016.7870919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2016.7870919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 12th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W89955767","https://openalex.org/W180519810","https://openalex.org/W234481681","https://openalex.org/W1582664144","https://openalex.org/W1971290995","https://openalex.org/W1975268024","https://openalex.org/W2016488143","https://openalex.org/W2019371364","https://openalex.org/W2022280610","https://openalex.org/W2037712729","https://openalex.org/W2128226234","https://openalex.org/W2168544140","https://openalex.org/W2186090720","https://openalex.org/W2200241032","https://openalex.org/W2294556882","https://openalex.org/W2479639269","https://openalex.org/W4252427272","https://openalex.org/W4365786623","https://openalex.org/W6603679206","https://openalex.org/W6609074211"],"related_works":["https://openalex.org/W2384379346","https://openalex.org/W2369660510","https://openalex.org/W2364093074","https://openalex.org/W2284149529","https://openalex.org/W4216703","https://openalex.org/W2949279097","https://openalex.org/W3198250195","https://openalex.org/W2020045149","https://openalex.org/W167181451","https://openalex.org/W2479844588"],"abstract_inverted_index":{"The":[0,20,46],"volumes":[1],"of":[2,43,58,105,113],"data":[3,18,21,28,57,76,95,125],"in":[4,90,138,141],"Big":[5,44,106],"Data,":[6],"their":[7],"variety":[8,42],"and":[9,62,75,127,145],"unstructured":[10],"nature,":[11],"have":[12],"had":[13],"researchers":[14],"looking":[15],"beyond":[16],"the":[17,40,68,84,136,152],"warehouse.":[19],"warehouse,":[22],"among":[23],"other":[24],"features,":[25],"requires":[26],"mapping":[27],"to":[29,80,111,123,150],"a":[30,72,91,94,130,142,147,159],"schema":[31],"upon":[32],"ingest,":[33],"an":[34,52],"approach":[35],"seen":[36],"as":[37,51],"inflexible":[38],"for":[39,55,65],"massive":[41],"Data.":[45],"Data":[47,69,85,92,107,131,143],"Lake":[48,70,132,144],"is":[49],"emerging":[50],"alternate":[53],"solution":[54],"storing":[56],"widely":[59],"divergent":[60],"types":[61],"scales.":[63],"Designed":[64],"high":[66],"flexibility,":[67],"follows":[71],"schema-on-read":[73],"philosophy":[74],"transformations":[77,100],"are":[78],"assumed":[79],"be":[81],"performed":[82,101],"within":[83,129],"Lake.":[86],"During":[87],"its":[88],"lifecycle":[89],"Lake,":[93],"product":[96],"may":[97],"undergo":[98],"numerous":[99],"by":[102],"any":[103],"number":[104],"processing":[108],"engines":[109],"leading":[110],"questions":[112],"traceability.":[114],"In":[115],"this":[116],"paper":[117],"we":[118],"argue":[119],"that":[120],"provenance":[121,139,166],"contributes":[122],"easier":[124],"management":[126],"traceability":[128],"infrastructure.":[133],"We":[134,154],"discuss":[135],"challenges":[137],"integration":[140],"propose":[146],"reference":[148],"architecture":[149,157],"overcome":[151],"challenges.":[153],"evaluate":[155],"our":[156,164],"through":[158],"prototype":[160],"implementation":[161],"built":[162],"using":[163],"distributed":[165],"collection":[167],"tools.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}