{"id":"https://openalex.org/W3084903409","doi":"https://doi.org/10.1109/bigdata50022.2020.9377740","title":"Extensible Data Skipping","display_name":"Extensible Data Skipping","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3084903409","doi":"https://doi.org/10.1109/bigdata50022.2020.9377740","mag":"3084903409"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.08150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075862099","display_name":"Paula Ta-Shma","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Paula Ta-Shma","raw_affiliation_strings":["IBM Research","IBM"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016766945","display_name":"Guy Khazma","orcid":"https://orcid.org/0009-0008-1364-5162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guy Khazma","raw_affiliation_strings":["IBM Research","IBM"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007261068","display_name":"Gal Lushi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gal Lushi","raw_affiliation_strings":["IBM Research","IBM"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080554083","display_name":"Oshrit Feder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oshrit Feder","raw_affiliation_strings":["IBM Research","IBM"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075862099"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13799142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"372","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/metadata","display_name":"Metadata","score":0.8701096773147583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8029152750968933},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6002819538116455},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.516079843044281},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5094402432441711},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.47451964020729065},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4540853798389435},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.38634824752807617},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2852455973625183},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2759956121444702},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1876235008239746}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8701096773147583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029152750968933},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6002819538116455},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.516079843044281},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5094402432441711},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.47451964020729065},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4540853798389435},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.38634824752807617},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2852455973625183},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2759956121444702},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1876235008239746}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.08150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.08150","pdf_url":"https://arxiv.org/pdf/2009.08150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"mag:3084903409","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2009.08150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2009.08150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.08150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.08150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.08150","pdf_url":"https://arxiv.org/pdf/2009.08150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[{"score":0.5299999713897705,"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":33,"referenced_works":["https://openalex.org/W125925666","https://openalex.org/W1494049834","https://openalex.org/W1967601791","https://openalex.org/W1981988185","https://openalex.org/W2028226582","https://openalex.org/W2038412523","https://openalex.org/W2098431345","https://openalex.org/W2106867122","https://openalex.org/W2109966155","https://openalex.org/W2123845384","https://openalex.org/W2146534064","https://openalex.org/W2157092487","https://openalex.org/W2168456130","https://openalex.org/W2280230190","https://openalex.org/W2368326835","https://openalex.org/W2591324491","https://openalex.org/W2612529667","https://openalex.org/W2750787376","https://openalex.org/W2756982556","https://openalex.org/W2778067733","https://openalex.org/W2798891709","https://openalex.org/W2799221749","https://openalex.org/W2805382875","https://openalex.org/W2889201433","https://openalex.org/W2992496917","https://openalex.org/W3137018880","https://openalex.org/W6605063754","https://openalex.org/W6606829079","https://openalex.org/W6629716282","https://openalex.org/W6674704250","https://openalex.org/W6681398051","https://openalex.org/W6682969285","https://openalex.org/W6746780038"],"related_works":["https://openalex.org/W3137018880","https://openalex.org/W1607887266","https://openalex.org/W2740841986","https://openalex.org/W2101293592","https://openalex.org/W3194200534","https://openalex.org/W2002779106","https://openalex.org/W3020268658","https://openalex.org/W2232216393","https://openalex.org/W2521416656","https://openalex.org/W2098431345","https://openalex.org/W2760685924","https://openalex.org/W2038783780","https://openalex.org/W121967257","https://openalex.org/W2765342551","https://openalex.org/W2528775446","https://openalex.org/W2108290652","https://openalex.org/W2112485457","https://openalex.org/W2888971921","https://openalex.org/W1966558147","https://openalex.org/W2184446796"],"abstract_inverted_index":{"Data":[0],"skipping":[1,8,52,90,115,159],"reduces":[2],"I/O":[3],"for":[4,53,116],"SQL":[5],"queries":[6,61,145],"by":[7,22],"over":[9],"irrelevant":[10],"data":[11,29,51,55,89,114,158],"objects":[12],"(files)":[13],"based":[14],"on":[15],"their":[16,27],"metadata.":[17,153],"We":[18,68,85,154],"extend":[19],"this":[20],"notion":[21],"allowing":[23],"developers":[24],"to":[25,48,144,149,162],"define":[26],"own":[28],"s":[30,44],"kipping":[31],"metadata":[32,98,134],"types":[33,56],"and":[34,60,75,95,124,174],"indexes":[35,170],"using":[36],"a":[37,117,137],"flexible":[38],"A":[39],"PI.":[40],"Our":[41,132],"framework":[42,71],"i":[43],"t":[45],"he":[46],"first":[47],"natively":[49],"support":[50],"arbitrary":[54],"(e.g.":[57],"geospatial,":[58],"logs)":[59],"with":[62,72,121,177],"User":[63],"Defined":[64],"Functions":[65],"(":[66],"UDFs).":[67],"integrated":[69],"our":[70,87],"Apache":[73],"Spark":[74],"it":[76],"is":[77,160],"now":[78],"deployed":[79],"across":[80],"multiple":[81],"products/services":[82],"at":[83],"IBM.":[84],"present":[86],"extensible":[88,157],"APIs,":[91],"discuss":[92],"index":[93],"design,":[94],"implement":[96,113],"various":[97],"indexes,":[99],"requiring":[100],"only":[101],"around":[102],"30":[103],"lines":[104],"of":[105,127,130,165],"additional":[106],"code":[107],"per":[108],"index.":[109],"In":[110],"particular":[111],"we":[112],"third":[118],"party":[119],"library":[120],"geospatial":[122],"UDFs":[123],"demonstrate":[125,155],"speedups":[126,173],"two":[128],"orders":[129],"magnitude.":[131],"centralized":[133],"approach":[135],"provides":[136],"x3.6":[138],"speed":[139],"up":[140],"even":[141],"when":[142],"compared":[143],"which":[146],"are":[147],"rewritten":[148],"exploit":[150],"Parquet":[151],"min/max":[152],"that":[156],"applicable":[161],"broad":[163],"class":[164],"applications,":[166],"where":[167],"user":[168],"defined":[169],"achieve":[171],"significant":[172],"cost":[175],"savings":[176],"very":[178],"low":[179],"development":[180],"cost.":[181]},"counts_by_year":[],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-10-10T00:00:00"}