{"id":"https://openalex.org/W3175356203","doi":"https://doi.org/10.1145/3448016.3457283","title":"Good to the Last Bit: Data-Driven Encoding with CodecDB","display_name":"Good to the Last Bit: Data-Driven Encoding with CodecDB","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3175356203","doi":"https://doi.org/10.1145/3448016.3457283","mag":"3175356203"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","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/A5082485594","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0003-3627-8672"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508204","display_name":"Chunwei Liu","orcid":"https://orcid.org/0000-0003-1481-2678"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunwei Liu","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091139670","display_name":"John Paparrizos","orcid":"https://orcid.org/0000-0002-7592-748X"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Paparrizos","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085538238","display_name":"Andrew A. Chien","orcid":"https://orcid.org/0000-0002-1204-206X"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew A. Chien","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029136335","display_name":"Jihong Ma","orcid":"https://orcid.org/0000-0001-9142-8528"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihong Ma","raw_affiliation_strings":["Alibaba Group, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Chicago, IL, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041264166","display_name":"Aaron J. Elmore","orcid":"https://orcid.org/0000-0002-4062-8826"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron J. Elmore","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082485594"],"corresponding_institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":3.9818,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9379819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"843","last_page":"856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T11181","display_name":"Advanced Data Storage Technologies","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/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8419610261917114},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.8348214626312256},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6719765663146973},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48555800318717957},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.46153295040130615},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.46038082242012024},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44928857684135437},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3865682780742645},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3463212847709656},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2709013819694519},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.26422804594039917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15643423795700073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419610261917114},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.8348214626312256},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6719765663146973},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48555800318717957},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46153295040130615},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.46038082242012024},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44928857684135437},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3865682780742645},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3463212847709656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2709013819694519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26422804594039917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15643423795700073},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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":[{"id":"doi:10.1145/3448016.3457283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448016.3457283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W21419474","https://openalex.org/W95608104","https://openalex.org/W1521148341","https://openalex.org/W1522301498","https://openalex.org/W1600355623","https://openalex.org/W1762161369","https://openalex.org/W1946402190","https://openalex.org/W1971568552","https://openalex.org/W1972418517","https://openalex.org/W1974671283","https://openalex.org/W1981420413","https://openalex.org/W1982013147","https://openalex.org/W1985136582","https://openalex.org/W1985514943","https://openalex.org/W1992977903","https://openalex.org/W1993892970","https://openalex.org/W2008365755","https://openalex.org/W2032866865","https://openalex.org/W2047662881","https://openalex.org/W2055774867","https://openalex.org/W2086529872","https://openalex.org/W2096496252","https://openalex.org/W2098935637","https://openalex.org/W2103670492","https://openalex.org/W2104626092","https://openalex.org/W2105326258","https://openalex.org/W2107745473","https://openalex.org/W2108862644","https://openalex.org/W2117546628","https://openalex.org/W2123686039","https://openalex.org/W2140453381","https://openalex.org/W2143331230","https://openalex.org/W2151131744","https://openalex.org/W2189465200","https://openalex.org/W2295448598","https://openalex.org/W2515174656","https://openalex.org/W2592738632","https://openalex.org/W2611538725","https://openalex.org/W2612457169","https://openalex.org/W2732024933","https://openalex.org/W2741497758","https://openalex.org/W2761621268","https://openalex.org/W2799873835","https://openalex.org/W2805363034","https://openalex.org/W2964121744","https://openalex.org/W3010666283","https://openalex.org/W3030666455","https://openalex.org/W3031206277","https://openalex.org/W3044054734","https://openalex.org/W3081593267","https://openalex.org/W3084651990","https://openalex.org/W3102704970","https://openalex.org/W3147010956","https://openalex.org/W6640789038","https://openalex.org/W6646664084","https://openalex.org/W6687322159","https://openalex.org/W6712120708"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Columnar":[0],"databases":[1,23,171],"rely":[2,32],"on":[3,33,116,129,157,172,177,186],"specialized":[4],"encoding":[5,49,97,108,137,151],"schemes":[6],"to":[7,44,55,75,85,120,123,145,148],"reduce":[8],"storage":[9],"requirements.":[10],"These":[11],"encodings":[12],"also":[13],"enable":[14],"efficient":[15,107],"in-situ":[16],"data":[17,42,66,96,112],"processing.":[18],"Nevertheless,":[19],"many":[20],"existing":[21],"columnar":[22,83,170],"are":[24],"encoding-oblivious.":[25],"When":[26],"storing":[27],"the":[28,38,41,62,70,87,91,95,105,135,140,149,165,173,187],"data,":[29],"these":[30],"systems":[31,63],"a":[34,102,110,182],"global":[35],"understanding":[36],"of":[37,72,89,161],"dataset":[39],"or":[40],"types":[43],"derive":[45],"simple":[46],"rules":[47],"for":[48,109,133],"selection.":[50],"Such":[51],"rule-based":[52],"selection":[53,152],"leads":[54],"unsatisfactory":[56],"performance.":[57],"Specifically,":[58],"when":[59],"performing":[60],"queries,":[61],"always":[64],"decode":[65],"into":[67],"memory,":[68],"ignoring":[69],"possibility":[71],"optimizing":[73],"access":[74,122],"encoded":[76,124],"data.":[77,125],"We":[78],"develop":[79],"CodecDB,":[80],"an":[81],"encoding-aware":[82,117],"database,":[84],"demonstrate":[86],"benefit":[88],"tightly-coupling":[90],"database":[92],"design":[93],"with":[94],"schemes.":[98],"CodecDB":[99,127,155],"chooses":[100],"in":[101],"principled":[103],"manner":[104],"most":[106],"given":[111],"column":[113],"and":[114,138,168,176],"relies":[115],"query":[118],"operators":[119],"optimize":[121],"Storage-wise,":[126],"achieves":[128],"average":[130,158,178],"90%":[131],"accuracy":[132],"selecting":[134],"best":[136],"improves":[139],"compression":[141],"ratio":[142],"by":[143],"up":[144],"40%":[146],"compared":[147],"state-of-the-art":[150],"solution.":[153],"Query-wise,":[154],"is":[156],"one":[159],"order":[160],"magnitude":[162],"faster":[163,180],"than":[164,181],"latest":[166],"open-source":[167],"commercial":[169],"TPC-H":[174],"benchmark,":[175],"3x":[179],"recent":[183],"research":[184],"project":[185],"Star-Schema":[188],"Benchmark":[189],"(SSB).":[190]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}