{"id":"https://openalex.org/W1996057387","doi":"https://doi.org/10.1109/services.2013.32","title":"Storing, Indexing and Querying Large Provenance Data Sets as RDF Graphs in Apache HBase","display_name":"Storing, Indexing and Querying Large Provenance Data Sets as RDF Graphs in Apache HBase","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W1996057387","doi":"https://doi.org/10.1109/services.2013.32","mag":"1996057387"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/services.2013.32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5044196026","display_name":"Artem Chebotko","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Artem Chebotko","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. of Texas - Pan American, Edinbug, TX, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Texas - Pan American, Edinbug, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009861962","display_name":"John Abraham","orcid":"https://orcid.org/0000-0002-3818-8681"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Abraham","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. of Texas - Pan American, Edinbug, TX, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Texas - Pan American, Edinbug, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019591981","display_name":"Pearl Brazier","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pearl Brazier","raw_affiliation_strings":["Dept. of Comput. Sci., Univ. of Texas - Pan American, Edinbug, TX, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Univ. of Texas - Pan American, Edinbug, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760558","display_name":"Anthony Piazza","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Piazza","raw_affiliation_strings":["Piazza Software Consulting Corpus, Christi, TX, USA"],"affiliations":[{"raw_affiliation_string":"Piazza Software Consulting Corpus, Christi, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007412180","display_name":"Andrey Kashlev","orcid":null},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrey Kashlev","raw_affiliation_strings":["Department of Computer Science, Wayne State University, Detroit, MI USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wayne State University, Detroit, MI USA#TAB#","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044023807","display_name":"Shiyong Lu","orcid":"https://orcid.org/0000-0002-7864-1815"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyong Lu","raw_affiliation_strings":["Department of Computer Science, Wayne State University, Detroit, MI USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wayne State University, Detroit, MI USA#TAB#","institution_ids":["https://openalex.org/I185443292"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.457,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":22,"citation_normalized_percentile":{"value":0.91887,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9999,"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":0.9999,"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":0.9945,"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":0.9935,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6120518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83137584},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.7634169},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.71599644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6955998},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6826601},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.61805284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6120518},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5136656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4950792},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47980908},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.14768419},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/services.2013.32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":25,"referenced_works":["https://openalex.org/W1980280904","https://openalex.org/W1981420413","https://openalex.org/W1983833794","https://openalex.org/W1988545508","https://openalex.org/W1994326726","https://openalex.org/W2003500287","https://openalex.org/W2027172230","https://openalex.org/W2031194666","https://openalex.org/W2039589115","https://openalex.org/W2062069258","https://openalex.org/W2081186283","https://openalex.org/W2099052309","https://openalex.org/W2114330123","https://openalex.org/W2128226234","https://openalex.org/W2145007750","https://openalex.org/W2146917903","https://openalex.org/W2158190501","https://openalex.org/W2161584750","https://openalex.org/W2169411125","https://openalex.org/W2172143128","https://openalex.org/W22495568","https://openalex.org/W2293919922","https://openalex.org/W3103545209","https://openalex.org/W4211265092","https://openalex.org/W4254560685"],"related_works":["https://openalex.org/W4241483715","https://openalex.org/W4206665951","https://openalex.org/W3139465322","https://openalex.org/W2904139343","https://openalex.org/W2768092701","https://openalex.org/W2615202182","https://openalex.org/W2604011835","https://openalex.org/W2529794967","https://openalex.org/W2528203718","https://openalex.org/W2484233589"],"abstract_inverted_index":{"Provenance,":[0],"which":[1,41],"records":[2],"the":[3,55,137,158],"history":[4],"of":[5,34,40,57,64,67,124,149,157,160],"an":[6,13,75],"in-silico":[7],"experiment,":[8],"has":[9],"been":[10],"identified":[11],"as":[12,71],"important":[14],"requirement":[15],"for":[16,88,97,139],"scientific":[17,21],"workflows":[18],"to":[19,43,117],"support":[20],"discovery":[22],"reproducibility,":[23],"result":[24],"interpretation,":[25],"and":[26,53,59,62,85,105,135,155,170],"problem":[27],"diagnosis.":[28],"Large":[29],"provenance":[30,37,68,98,153],"datasets":[31,99,154],"are":[32,94],"composed":[33],"many":[35],"smaller":[36],"graphs,":[38],"each":[39],"corresponds":[42],"a":[44,144],"single":[45],"workflow":[46],"execution.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,80],"explore":[52],"address":[54],"challenge":[56],"efficient":[58,169],"scalable":[60],"storage":[61,84],"querying":[63],"large":[65],"collections":[66],"graphs":[69,73,104],"serialized":[70],"RDF":[72,89,103],"in":[74,91],"Apache":[76],"HBase":[77,92],"database.":[78],"Specifically,":[79],"propose:":[81],"(i)":[82],"novel":[83,107],"indexing":[86],"techniques":[87],"data":[90,141],"that":[93,112,127,165],"better":[95],"suited":[96],"rather":[100,131],"than":[101,132],"generic":[102],"(ii)":[106],"SPARQL":[108],"query":[109],"evaluation":[110,148],"algorithms":[111,151],"solely":[113],"rely":[114],"on":[115],"indices":[116],"compute":[118],"expensive":[119],"join":[120],"operations,":[121],"make":[122],"use":[123],"numeric":[125],"values":[126],"represent":[128],"triple":[129],"positions":[130],"actual":[133],"triples,":[134],"eliminate":[136],"need":[138],"intermediate":[140],"transfers":[142],"over":[143],"network.":[145],"The":[146],"empirical":[147],"our":[150,166],"using":[152],"queries":[156],"University":[159],"Texas":[161],"Provenance":[162],"Benchmark":[163],"confirms":[164],"approach":[167],"is":[168],"scalable.":[171]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1996057387","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2024-12-12T20:00:17.457469","created_date":"2016-06-24"}