{"id":"https://openalex.org/W7127064680","doi":"https://doi.org/10.1051/epjconf/202533701269/pdf","title":"On-Demand Column Joining for High Energy Physics","display_name":"On-Demand Column Joining for High Energy Physics","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W7127064680","doi":"https://doi.org/10.1051/epjconf/202533701269/pdf"},"language":"en","primary_location":{"id":"pmh:oai:edpsciences.org:dkey/10.1051/epjconf/202533701269","doi":"https://doi.org/10.1051/epjconf/202533701269/pdf","is_oa":false,"landing_page_url":"https://www.epj-conferences.org/10.1051/epjconf/202533701269/pdf","pdf_url":"https://www.epj-conferences.org/10.1051/epjconf/202533701269/pdf","source":{"id":"https://openalex.org/S4306400744","display_name":"Springer Link (Chiba Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I8488066","host_organization_name":"Chiba Institute of Technology","host_organization_lineage":["https://openalex.org/I8488066"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1051/epjconf/202533701269","raw_type":"Text"},"volume":null,"type":"article","indexed_in":[],"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/A5089574904","display_name":"N. Manganelli","orcid":"https://orcid.org/0000-0002-3398-4531","observed_orcids":["https://orcid.org/0000-0002-3398-4531"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Manganelli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033706838","display_name":"Ben Galewsky","orcid":"https://orcid.org/0000-0003-3811-5949","observed_orcids":["https://orcid.org/0000-0003-3811-5949"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Galewsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012408300","display_name":"Burt Holzman","orcid":"https://orcid.org/0000-0001-5235-6314","observed_orcids":["https://orcid.org/0000-0001-5235-6314"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Burt Holzman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60616781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.453900009393692,"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":0.453900009393692,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.3337000012397766,"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/T10048","display_name":"Particle physics theoretical and experimental studies","score":0.07090000063180923,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cms-experiment","display_name":"CMS experiment","score":0.5059999823570251},{"id":"https://openalex.org/keywords/high-luminosity-lhc","display_name":"High-Luminosity LHC","score":0.8640000224113464},{"id":"https://openalex.org/keywords/data-duplication","display_name":"data duplication","score":0.671999990940094},{"id":"https://openalex.org/keywords/data-storage-efficiency","display_name":"data storage efficiency","score":0.7110000252723694},{"id":"https://openalex.org/keywords/trino","display_name":"Trino","score":0.9300000071525574},{"id":"https://openalex.org/keywords/scikit-hep","display_name":"scikit-hep","score":0.8709999918937683},{"id":"https://openalex.org/keywords/coffea","display_name":"Coffea","score":0.9819999933242798},{"id":"https://openalex.org/keywords/object-storage","display_name":"object storage","score":0.7369999885559082}],"concepts":[{"id":"https://openalex.org/C87668248","wikidata":"https://www.wikidata.org/wiki/Q40605","display_name":"Large Hadron Collider","level":2,"score":0.6636999845504761},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6273000240325928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616999864578247},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C529754248","wikidata":"https://www.wikidata.org/wiki/Q1054772","display_name":"Data recovery","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C125611927","wikidata":"https://www.wikidata.org/wiki/Q17008131","display_name":"Criticality","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C152290109","wikidata":"https://www.wikidata.org/wiki/Q2033879","display_name":"Collider","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C3102742","wikidata":"https://www.wikidata.org/wiki/Q6031177","display_name":"Information repository","level":3,"score":0.25220000743865967},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:edpsciences.org:dkey/10.1051/epjconf/202533701269","doi":"https://doi.org/10.1051/epjconf/202533701269/pdf","is_oa":false,"landing_page_url":"https://www.epj-conferences.org/10.1051/epjconf/202533701269/pdf","pdf_url":"https://www.epj-conferences.org/10.1051/epjconf/202533701269/pdf","source":{"id":"https://openalex.org/S4306400744","display_name":"Springer Link (Chiba Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I8488066","host_organization_name":"Chiba Institute of Technology","host_organization_lineage":["https://openalex.org/I8488066"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1051/epjconf/202533701269","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,8,13,50,78,117,134,138,146,170],"Large":[2],"Hadron":[3],"Collider":[4],"(LHC)":[5],"transitions":[6],"into":[7],"High-Luminosity":[9],"LHC":[10],"(HL-LHC)":[11],"era,":[12],"volume":[14],"of":[15,42,52,81,119,172],"data":[16,31,53,74,83,89,110,151,166],"to":[17,22,72,105],"be":[18],"processed":[19],"is":[20,142],"expected":[21],"increase":[23],"significantly.":[24],"The":[25,94],"CMS":[26,114],"Experiment":[27],"currently":[28],"utilizes":[29],"various":[30],"formats,":[32],"including":[33],"AOD,":[34],"MiniAOD,":[35],"and":[36,44,55,108,137,153,156,168],"NanoAOD,":[37],"each":[38],"with":[39,84,129,133],"different":[40],"levels":[41],"detail":[43],"storage":[45,56,175],"requirements.":[46],"This":[47,69],"paper":[48],"addresses":[49],"challenges":[51],"duplication":[54,75],"inefficiencies":[57],"in":[58],"high-energy":[59],"physics":[60],"(HEP)":[61],"analyses":[62],"by":[63,76],"proposing":[64],"an":[65],"on-demand":[66],"column-joining":[67],"solution.":[68],"approach":[70],"aims":[71],"reduce":[73],"enabling":[77],"dynamic":[79],"combination":[80],"NanoAOD":[82],"auxiliary":[85],"information":[86],"from":[87],"larger":[88],"tiers,":[90],"such":[91],"as":[92],"MiniAOD.":[93],"proposed":[95],"solution":[96],"leverages":[97],"Trino,":[98],"a":[99],"high-performance":[100],"distributed":[101],"SQL":[102],"query":[103],"engine,":[104],"perform":[106],"efficient":[107],"scalable":[109],"joins.":[111],"Benchmarks":[112],"using":[113],"OpenData":[115],"demonstrate":[116],"feasibility":[118],"this":[120],"approach,":[121],"showing":[122],"that":[123],"it":[124],"can":[125],"handle":[126],"large":[127],"datasets":[128],"low":[130],"latency.":[131],"Integration":[132],"scikit-hep":[135],"ecosystem":[136],"coffea":[139],"analysis":[140],"framework":[141],"also":[143],"discussed,":[144],"highlighting":[145],"potential":[147],"for":[148,165],"seamless":[149],"end-to-end":[150],"processing":[152],"analysis.":[154],"Ongoing":[155],"future":[157],"work":[158],"focuses":[159],"on":[160],"expanding":[161],"benchmarks,":[162],"integrating":[163],"ServiceX":[164],"transformation,":[167],"exploring":[169],"use":[171],"native":[173],"object":[174],"solutions.":[176]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-02-03T00:00:00"}
