{"id":"https://openalex.org/W7166092050","doi":"https://doi.org/10.1145/3810991.3811633","title":"Benchmarking Column Statistics for Analytical Query Pruning","display_name":"Benchmarking Column Statistics for Analytical Query Pruning","publication_year":2026,"publication_date":"2026-05-31","ids":{"openalex":"https://openalex.org/W7166092050","doi":"https://doi.org/10.1145/3810991.3811633"},"language":null,"primary_location":{"id":"doi:10.1145/3810991.3811633","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810991.3811633","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 11th International Workshop on Testing Database Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3810991.3811633","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139450026","display_name":"Alexander Bilde Pedersen","orcid":"https://orcid.org/0009-0003-9138-1135"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Alexander Bilde Pedersen","raw_affiliation_strings":["DSAR, IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0009-0003-9138-1135","affiliations":[{"raw_affiliation_string":"DSAR, IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046504176","display_name":"Ehsan Yousefzadeh-Asl-Miandoab","orcid":"https://orcid.org/0000-0003-0156-1435"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ehsan Yousefzadeh-Asl-Miandoab","raw_affiliation_strings":["DSAR, IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0156-1435","affiliations":[{"raw_affiliation_string":"DSAR, IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033453497","display_name":"Ismail Oukid","orcid":"https://orcid.org/0000-0002-4253-4989"},"institutions":[{"id":"https://openalex.org/I4210124099","display_name":"Total (Germany)","ror":"https://ror.org/0344nnn17","country_code":"DE","type":"company","lineage":["https://openalex.org/I103084370","https://openalex.org/I4210124099"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ismail Oukid","raw_affiliation_strings":["Engeneering Department, Snowflake, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4253-4989","affiliations":[{"raw_affiliation_string":"Engeneering Department, Snowflake, Berlin, Germany","institution_ids":["https://openalex.org/I4210124099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027200254","display_name":"Martin Hentschel","orcid":"https://orcid.org/0009-0004-8528-4168"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Martin Hentschel","raw_affiliation_strings":["DSAR, IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0009-0004-8528-4168","affiliations":[{"raw_affiliation_string":"DSAR, IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.5821999907493591,"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":0.5821999907493591,"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":0.06859999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.03440000116825104,"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/column","display_name":"Column (typography)","score":0.5612999796867371},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5339999794960022},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5217999815940857},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.3043000102043152},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29190000891685486},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.29109999537467957}],"concepts":[{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5612999796867371},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.527400016784668},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44369998574256897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3752000033855438},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3810991.3811633","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810991.3811633","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 11th International Workshop on Testing Database Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3810991.3811633","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810991.3811633","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 11th International Workshop on Testing Database Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5507431245","display_name":null,"funder_award_id":"NNF24OC0091339","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"}],"funders":[{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1585029481","https://openalex.org/W1967373117","https://openalex.org/W2430301697","https://openalex.org/W2949054050","https://openalex.org/W2994941531","https://openalex.org/W4411374391"],"related_works":[],"abstract_inverted_index":{"Min/max":[0],"indexes":[1,32],"are":[2],"the":[3,44,86],"most":[4],"widely":[5],"used":[6],"statistics":[7,65,97,116],"for":[8,62,66,100,113],"partition":[9,67],"pruning":[10,17,41,74],"in":[11,70],"analytical":[12],"systems,":[13],"but":[14],"they":[15],"miss":[16],"opportunities":[18],"when":[19,53],"partitions":[20],"contain":[21],"outliers":[22],"or":[23],"wide":[24],"value":[25],"ranges.":[26],"Richer":[27],"statistics,":[28],"including":[29],"multiple":[30],"min/max":[31,90],"per":[33],"partition,":[34],"Bloom":[35],"filters,":[36],"and":[37,72,76,106],"dictionaries,":[38],"can":[39],"improve":[40],"effectiveness":[42,75],"at":[43,121],"cost":[45],"of":[46,82,88],"additional":[47],"metadata,":[48],"yet":[49],"no":[50],"study":[51],"quantifies":[52],"this":[54],"overhead":[55],"is":[56],"justified.":[57],"We":[58,109],"present":[59],"a":[60],"benchmark":[61],"evaluating":[63],"column":[64,115],"pruning,":[68],"implemented":[69],"DuckDB,":[71],"assess":[73],"query":[77],"runtimes":[78],"across":[79],"metadata":[80],"budgets":[81],"10\u00d7":[83],"to":[84],"1000\u00d7":[85],"size":[87],"standard":[89],"indexes.":[91],"Our":[92],"results":[93],"show":[94],"that":[95],"richer":[96],"yield":[98],"gains":[99],"unsorted":[101],"data,":[102],"data":[103,119],"with":[104],"outliers,":[105],"low-cardinality":[107],"columns.":[108],"derive":[110],"initial":[111],"guidelines":[112],"selecting":[114],"based":[117],"on":[118],"characteristics":[120],"load":[122],"time.":[123]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-27T00:00:00"}