{"id":"https://openalex.org/W4280537071","doi":"https://doi.org/10.1145/3530050.3532923","title":"Ameliorating data compression and query performance through cracked Parquet","display_name":"Ameliorating data compression and query performance through cracked Parquet","publication_year":2022,"publication_date":"2022-05-12","ids":{"openalex":"https://openalex.org/W4280537071","doi":"https://doi.org/10.1145/3530050.3532923"},"language":"en","primary_location":{"id":"doi:10.1145/3530050.3532923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3530050.3532923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Big Data in Emergent Distributed Environments","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/A5039935651","display_name":"Patrick Hansert","orcid":"https://orcid.org/0000-0002-7592-3542"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Patrick Hansert","raw_affiliation_strings":["TU Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043223305","display_name":"Sebastian Michel","orcid":"https://orcid.org/0000-0001-6636-2694"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Michel","raw_affiliation_strings":["TU Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039935651"],"corresponding_institution_ids":["https://openalex.org/I153267046"],"apc_list":null,"apc_paid":null,"fwci":0.6907,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70024211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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":0.9987000226974487,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9986000061035156,"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":0.9976999759674072,"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/spark","display_name":"SPARK (programming language)","score":0.8898228406906128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7595947980880737},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7414290904998779},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6722949147224426},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6378239989280701},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5767156481742859},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.528344988822937},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.49297308921813965},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.43203532695770264},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3477821946144104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3462161421775818},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3355928063392639},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2044326364994049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14852285385131836},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11056950688362122}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8898228406906128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595947980880737},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7414290904998779},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6722949147224426},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6378239989280701},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5767156481742859},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.528344988822937},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.49297308921813965},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.43203532695770264},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3477821946144104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3462161421775818},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3355928063392639},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2044326364994049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14852285385131836},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11056950688362122},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3530050.3532923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3530050.3532923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Big Data in Emergent Distributed Environments","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.550000011920929,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2074935284","https://openalex.org/W2123686039","https://openalex.org/W2139000699","https://openalex.org/W2574861468","https://openalex.org/W2612636236","https://openalex.org/W2756982556","https://openalex.org/W2788260429","https://openalex.org/W3032251503","https://openalex.org/W3085477028","https://openalex.org/W3085940077","https://openalex.org/W3158312191","https://openalex.org/W3173993340","https://openalex.org/W3175055685"],"related_works":["https://openalex.org/W4383723869","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974","https://openalex.org/W3007688875","https://openalex.org/W2766695209","https://openalex.org/W3123970444","https://openalex.org/W2110517301"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,75],"propose":[4],"to":[5],"exploit":[6],"synergy":[7],"effects":[8,94],"between":[9],"partitioning":[10],"and":[11,54],"compression":[12,98],"for":[13,22,90],"Dremel-encoded":[14],"nested":[15],"data":[16,20,91],"serving":[17],"as":[18],"the":[19,36,62,78,84,88,105],"storage":[21,52],"Spark-style":[23],"processing":[24,55],"jobs.":[25],"The":[26],"encoding":[27],"proposed":[28],"with":[29,48],"Dremel":[30],"has":[31],"found":[32],"widespread":[33],"use":[34],"in":[35,66,113],"form":[37],"of":[38,51,64,80,100,111],"open":[39],"approaches":[40],"like":[41,57],"Apache":[42,58],"Parquet,":[43],"which":[44],"can":[45,76,95],"be":[46],"used":[47],"a":[49,97,109],"multitude":[50],"engines":[53],"frameworks,":[56],"Spark.":[59],"It":[60],"stores":[61],"presence":[63],"objects":[65],"additional":[67],"columns":[68],"compressed":[69],"using":[70,87],"run-length":[71],"encoding.":[72],"Using":[73],"partitioning,":[74],"decrease":[77],"number":[79],"runs":[81],"while":[82,102],"at":[83],"same":[85],"time":[86],"partitions":[89],"skipping.":[92],"These":[93],"achieve":[96],"ratio":[99],"1.37":[101],"also":[103],"reducing":[104],"query":[106],"runtime":[107],"by":[108],"factor":[110],"1.22":[112],"our":[114],"test":[115],"setup.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}