{"id":"https://openalex.org/W7203748233","doi":"https://doi.org/10.1016/j.egyai.2026.100870","title":"An empirical benchmark of deep time-series models for smart meter energy forecasting","display_name":"An empirical benchmark of deep time-series models for smart meter energy forecasting","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203748233","doi":"https://doi.org/10.1016/j.egyai.2026.100870"},"language":"en","primary_location":{"id":"doi:10.1016/j.egyai.2026.100870","doi":"https://doi.org/10.1016/j.egyai.2026.100870","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.egyai.2026.100870","pdf_url":null,"source":{"id":"https://openalex.org/S4210241048","display_name":"Energy and AI","issn_l":"2666-5468","issn":["2666-5468"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-20"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Energy and AI","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.egyai.2026.100870","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078871286","display_name":"Behnaz Kavoosighafi","orcid":"https://orcid.org/0000-0002-1951-7515","observed_orcids":["https://orcid.org/0000-0002-1951-7515"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Behnaz Kavoosighafi","raw_affiliation_strings":["Link\u00f6ping University, Department of Science and Technology, Norrk\u00f6ping, 60174, \u00d6sterg\u00f6tland, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-1951-7515","affiliations":[{"raw_affiliation_string":"Link\u00f6ping University, Department of Science and Technology, Norrk\u00f6ping, 60174, \u00d6sterg\u00f6tland, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044685878","display_name":"Maria Eidenskog","orcid":"https://orcid.org/0000-0001-9888-303X","observed_orcids":["https://orcid.org/0000-0001-9888-303X"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Maria Eidenskog","raw_affiliation_strings":["Link\u00f6ping University, Department of Thematic Studies, Link\u00f6ping, 58183, \u00d6sterg\u00f6tland, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-9888-303X","affiliations":[{"raw_affiliation_string":"Link\u00f6ping University, Department of Thematic Studies, Link\u00f6ping, 58183, \u00d6sterg\u00f6tland, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019646511","display_name":"Wiktoria Glad","orcid":"https://orcid.org/0000-0003-3636-081X","observed_orcids":["https://orcid.org/0000-0003-3636-081X"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wiktoria Glad","raw_affiliation_strings":["Link\u00f6ping University, Department of Thematic Studies, Link\u00f6ping, 58183, \u00d6sterg\u00f6tland, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3636-081X","affiliations":[{"raw_affiliation_string":"Link\u00f6ping University, Department of Thematic Studies, Link\u00f6ping, 58183, \u00d6sterg\u00f6tland, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061859149","display_name":"Katerina Vrotsou","orcid":"https://orcid.org/0000-0003-4761-8601","observed_orcids":["https://orcid.org/0000-0003-4761-8601"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Katerina Vrotsou","raw_affiliation_strings":["Link\u00f6ping University, Department of Science and Technology, Norrk\u00f6ping, 60174, \u00d6sterg\u00f6tland, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-4761-8601","affiliations":[{"raw_affiliation_string":"Link\u00f6ping University, Department of Science and Technology, Norrk\u00f6ping, 60174, \u00d6sterg\u00f6tland, Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078871286"],"corresponding_institution_ids":["https://openalex.org/I102134673"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":{"value":3630,"currency":"USD","value_usd":3630},"fwci":1.3169,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73676692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":null,"first_page":"100870","last_page":"100870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.008200000040233135,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/model-benchmarking","display_name":"model benchmarking","score":0.777999997138977},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.8109999895095825},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.906000018119812},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.8069999814033508},{"id":"https://openalex.org/keywords/input-sequence-length","display_name":"input sequence length","score":0.6610000133514404},{"id":"https://openalex.org/keywords/prediction-horizon","display_name":"prediction horizon","score":0.9929999709129333},{"id":"https://openalex.org/keywords/computational-complexity","display_name":"computational complexity","score":0.8190000057220459},{"id":"https://openalex.org/keywords/household-energy-behavior","display_name":"household energy behavior","score":0.7509999871253967},{"id":"https://openalex.org/keywords/attention-models","display_name":"attention-based models","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C2779510800","wikidata":"https://www.wikidata.org/wiki/Q1630602","display_name":"Smart meter","level":3,"score":0.7014999985694885},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6886000037193298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579999923706055},{"id":"https://openalex.org/C10558101","wikidata":"https://www.wikidata.org/wiki/Q689855","display_name":"Smart grid","level":2,"score":0.5873000025749207},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C133199616","wikidata":"https://www.wikidata.org/wiki/Q25386885","display_name":"Empirical modelling","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C206654554","wikidata":"https://www.wikidata.org/wiki/Q5374247","display_name":"Empirical measure","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C67172668","wikidata":"https://www.wikidata.org/wiki/Q622756","display_name":"Electricity meter","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C151011524","wikidata":"https://www.wikidata.org/wiki/Q11573","display_name":"Metre","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.266400009393692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.egyai.2026.100870","doi":"https://doi.org/10.1016/j.egyai.2026.100870","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.egyai.2026.100870","pdf_url":null,"source":{"id":"https://openalex.org/S4210241048","display_name":"Energy and AI","issn_l":"2666-5468","issn":["2666-5468"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-20"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Energy and AI","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2608.18675","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18675","pdf_url":"https://arxiv.org/pdf/2608.18675","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:2bf7257080744ceb9985aa29753d1ac0","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/2bf7257080744ceb9985aa29753d1ac0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Energy and AI, Vol 25, Iss , Pp 100870- (2026)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2608.18675","doi":"https://doi.org/10.48550/arxiv.2608.18675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18675","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.egyai.2026.100870","doi":"https://doi.org/10.1016/j.egyai.2026.100870","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.egyai.2026.100870","pdf_url":null,"source":{"id":"https://openalex.org/S4210241048","display_name":"Energy and AI","issn_l":"2666-5468","issn":["2666-5468"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-20"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Energy and AI","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9090999960899353},{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5351999998092651}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3652627443","display_name":"Exploring the potential of generative AI based data synthesis for the future energy system: data, models, biases and implications","funder_award_id":"P2024-01187","funder_id":"https://openalex.org/F4320322711","funder_display_name":"Energimyndigheten"}],"funders":[{"id":"https://openalex.org/F4320322711","display_name":"Energimyndigheten","ror":"https://ror.org/0359z7n90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203748233.pdf","grobid_xml":"https://content.openalex.org/works/W7203748233.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1975167999","https://openalex.org/W2040395995","https://openalex.org/W2091693228","https://openalex.org/W2110485445","https://openalex.org/W2117829824","https://openalex.org/W2121844625","https://openalex.org/W2295598076","https://openalex.org/W2560599441","https://openalex.org/W2592453717","https://openalex.org/W2792764867","https://openalex.org/W2911964244","https://openalex.org/W2943921667","https://openalex.org/W2952133925","https://openalex.org/W2960560113","https://openalex.org/W2986871121","https://openalex.org/W3022643593","https://openalex.org/W3112325088","https://openalex.org/W3164826854","https://openalex.org/W4239510810","https://openalex.org/W4300980908","https://openalex.org/W4381245607","https://openalex.org/W4382203079","https://openalex.org/W4385270114","https://openalex.org/W4387561305","https://openalex.org/W4388333441","https://openalex.org/W4403565951","https://openalex.org/W4407276595","https://openalex.org/W4409695029","https://openalex.org/W4410950001","https://openalex.org/W4411580379","https://openalex.org/W4416359503","https://openalex.org/W6888947451","https://openalex.org/W7133205715"],"related_works":["https://openalex.org/W4412170571","https://openalex.org/W3092984679","https://openalex.org/W7117777761","https://openalex.org/W3020569291","https://openalex.org/W7043105200","https://openalex.org/W2922950616","https://openalex.org/W7214031181","https://openalex.org/W4318603193","https://openalex.org/W4410356353","https://openalex.org/W4303579011"],"abstract_inverted_index":{"Accurate":[0],"forecasting":[1,105,208,280],"of":[2,11,29,69,109,118,172,262],"energy":[3,20,285],"consumption":[4,32],"is":[5,56,254],"important":[6],"for":[7,17,42,75,231,278],"the":[8,27,107,112,116,125,149,156,166,244,259,263],"efficient":[9],"operation":[10],"power":[12],"systems,":[13],"with":[14,235],"direct":[15],"implications":[16],"operational":[18],"costs,":[19],"management,":[21],"and":[22,44,82,115,161,164,169,210,221,266],"system":[23],"maintenance.":[24],"Due":[25],"to":[26,133,239],"availability":[28],"extensive":[30],"high-resolution":[31],"data":[33,55],"from":[34],"smart":[35,53,93,283],"meters,":[36],"data-driven":[37],"methods":[38],"have":[39],"been":[40],"used":[41],"short-term":[43],"long-term":[45],"forecasting.":[46],"However,":[47],"their":[48],"comparative":[49],"performance":[50,173,194],"on":[51,89,99,211,243],"real-world":[52],"meter":[54,94,284],"still":[57],"not":[58,255,268],"well":[59],"studied.":[60],"In":[61,144],"this":[62,252],"paper,":[63],"we":[64],"present":[65],"an":[66,241],"empirical":[67],"benchmark":[68,274],"nine":[70],"modern":[71],"deep":[72,181],"learning":[73,182],"models":[74,88,183,281],"time-series":[76],"forecasting,":[77],"including":[78],"linear,":[79],"MLP-based,":[80],"convolutional,":[81],"Transformer":[83],"architectures.":[84],"We":[85,121,153],"evaluate":[86],"these":[87],"two":[90],"publicly":[91],"available":[92],"datasets.":[95,214,272],"Our":[96,177],"analysis":[97,218],"focuses":[98],"three":[100],"factors":[101],"that":[102,123,180,225],"strongly":[103],"affect":[104],"performance:":[106],"length":[108],"historical":[110,126],"input,":[111],"prediction":[113,150,159],"horizon,":[114],"choice":[117,227],"model":[119,226],"architecture.":[120],"show":[122,179],"extending":[124],"context":[127],"improves":[128],"accuracy,":[129],"but":[130],"only":[131,203],"up":[132],"a":[134,216],"saturation":[135],"point,":[136],"after":[137],"which":[138],"additional":[139],"input":[140],"provides":[141,275],"limited":[142,229],"benefit.":[143],"contrast,":[145],"accuracy":[146,160],"decreases":[147],"as":[148],"horizon":[151],"increases.":[152],"also":[154],"investigate":[155],"trade-off":[157],"between":[158],"computational":[162,198],"complexity,":[163],"assess":[165],"statistical":[167],"significance":[168],"practical":[170,276],"magnitude":[171],"differences":[174,202],"across":[175,219,271],"models.":[176],"results":[178],"consistently":[184,270],"outperform":[185],"classical":[186],"baselines,":[187],"while":[188],"lightweight":[189],"architectures":[190,237],"achieve":[191],"relatively":[192],"similar":[193],"at":[195,206],"significantly":[196],"lower":[197],"cost.":[199],"Additionally,":[200],"architectural":[201],"become":[204],"meaningful":[205],"longer":[207],"horizons":[209],"more":[212],"heterogeneous":[213],"Finally,":[215],"subgroup":[217],"geodemographic":[220],"household":[222],"categories":[223],"shows":[224],"has":[228],"impact":[230],"most":[232,245],"population":[233],"segments,":[234],"attention-based":[236],"appearing":[238],"offer":[240],"advantage":[242,253],"under-represented":[246],"or":[247],"behaviorally":[248],"irregular":[249],"groups,":[250],"though":[251],"statistically":[256],"robust":[257],"given":[258],"small":[260],"size":[261],"affected":[264],"subgroups":[265],"does":[267],"generalize":[269],"This":[273],"guidance":[277],"selecting":[279],"in":[282],"applications.":[286]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-08-20T00:00:00"}