{"id":"https://openalex.org/W7214924586","doi":"https://doi.org/10.48550/arxiv.2609.36281","title":"GNA: Granular Neighbor Assembly for Retrieval-Augmented Multivariate Time-Series Forecasting","display_name":"GNA: Granular Neighbor Assembly for Retrieval-Augmented Multivariate Time-Series Forecasting","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214924586","doi":"https://doi.org/10.48550/arxiv.2609.36281"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36281","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36281","pdf_url":"https://arxiv.org/pdf/2609.36281","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36281","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153568240","display_name":"Vincent Uhse","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Uhse, Vincent","raw_affiliation_strings":["CERN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN","institution_ids":["https://openalex.org/I67311998"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5153568240"],"corresponding_institution_ids":["https://openalex.org/I67311998"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9945999979972839,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9945999979972839,"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/T11918","display_name":"Forecasting Techniques and Applications","score":0.0031999999191612005,"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"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.000699999975040555,"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/multivariate-time-series-forecasting","display_name":"multivariate time series forecasting","score":0.9359999895095825},{"id":"https://openalex.org/keywords/persistence-forecast","display_name":"persistence forecast","score":0.5920000076293945},{"id":"https://openalex.org/keywords/embedding-based-retrieval","display_name":"embedding-based retrieval","score":0.4950000047683716},{"id":"https://openalex.org/keywords/nonstationary-time-series","display_name":"non-stationary time series","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C141547133","wikidata":"https://www.wikidata.org/wiki/Q7291996","display_name":"Random variate","level":3,"score":0.5778999924659729},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5478000044822693},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5314000248908997},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.38109999895095825},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3176000118255615},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2776085556","wikidata":"https://www.wikidata.org/wiki/Q183361","display_name":"Chen","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36281","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36281","pdf_url":"https://arxiv.org/pdf/2609.36281","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.36281","doi":"https://doi.org/10.48550/arxiv.2609.36281","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36281","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":"pmh:oai:arXiv.org:2609.36281","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36281","pdf_url":"https://arxiv.org/pdf/2609.36281","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214924586.pdf","grobid_xml":"https://content.openalex.org/works/W7214924586.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1569592761","https://openalex.org/W2067562626","https://openalex.org/W2113405802","https://openalex.org/W2604847698","https://openalex.org/W3177318507","https://openalex.org/W4382203079","https://openalex.org/W4399034646","https://openalex.org/W4404407089","https://openalex.org/W4405386924","https://openalex.org/W4405900349","https://openalex.org/W4409363871","https://openalex.org/W4409366081","https://openalex.org/W4411232126","https://openalex.org/W7160375093"],"related_works":["https://openalex.org/W7204174706","https://openalex.org/W7162416775","https://openalex.org/W7208708326","https://openalex.org/W7220973571","https://openalex.org/W4412944150","https://openalex.org/W7201833294","https://openalex.org/W4414029295","https://openalex.org/W7172331733","https://openalex.org/W7223552851","https://openalex.org/W7152934175"],"abstract_inverted_index":{"Deep":[0],"forecasters":[1],"predict":[2,130],"from":[3,53,93,125],"a":[4,15,30,63,114,139,243],"fixed-length":[5],"lookback":[6,154,216],"window,":[7],"and":[8,83,105,134,158,187,202],"lengthening":[9],"it":[10,229],"gives":[11,34,177],"diminishing":[12],"returns":[13],"at":[14,72,235],"growing":[16],"cost.":[17],"Retrieval":[18,211],"augmentation":[19],"instead":[20],"shows":[21],"the":[22,37,40,48,80,119,152,159,178,215,219,238,247],"model":[23,157],"how":[24,107],"similar":[25],"past":[26,32,42,50,76,140],"situations":[27],"continued.":[28],"Retrieving":[29],"whole":[31,75],"window":[33,141],"every":[35,156,192],"variate":[36,54,89],"continuation":[38],"of":[39,173,183,196,204,246],"same":[41,153,160],"moment.":[43],"In":[44],"multivariate":[45],"series,":[46],"however,":[47],"best":[49],"match":[51],"differs":[52],"to":[55,109,118,129,223],"variate.":[56],"We":[57],"present":[58],"GNA":[59,166],"(Granular":[60],"Neighbor":[61],"Assembly),":[62],"retrieval":[64,135,161],"layer":[65],"for":[66,155,163],"forecasting":[67],"backbones":[68,170],"that":[69],"assembles":[70],"neighbors":[71,203],"two":[73,168],"granularities:":[74],"windows,":[77],"which":[78,87],"keep":[79],"variates":[81],"coherent,":[82],"per-variate":[84],"neighbors,":[85],"in":[86,171,191],"each":[88,131],"takes":[90],"its":[91,94,146,189],"future":[92,147],"own":[95,121],"best-matching":[96],"past.":[97],"A":[98],"learned":[99],"gate":[100,220],"decides,":[101],"per":[102],"forecast":[103],"step":[104],"variate,":[106],"much":[108],"trust":[110,222],"these":[111],"futures":[112,225],"against":[113],"persistence":[115],"forecast,":[116],"next":[117],"backbone's":[120],"forecast.":[122],"Candidates":[123],"come":[124],"an":[126],"embedding":[127],"trained":[128],"window's":[132],"future,":[133],"is":[136,142,240],"strictly":[137],"causal:":[138],"used":[143],"only":[144],"once":[145],"has":[148],"been":[149],"observed.":[150],"With":[151],"constants":[162],"all":[164],"datasets,":[165],"improves":[167],"Transformer":[169],"85":[172],"96":[174],"dataset-horizon":[175],"settings,":[176],"lowest":[179],"MSE":[180],"on":[181,194,231],"8":[182],"12":[184],"standard":[185],"benchmarks":[186],"beats":[188],"backbone":[190],"seed":[193],"10":[195],"them.":[197],"Both":[198],"granularities":[199],"are":[200,207],"needed,":[201],"mismatched":[205],"queries":[206],"worse":[208],"than":[209],"none.":[210],"helps":[212],"most":[213],"where":[214],"says":[217],"least:":[218],"shifts":[221],"retrieved":[224,248],"further":[226],"ahead.":[227],"Where":[228],"fails,":[230],"hourly":[232],"non-stationary":[233],"series":[234],"long":[236],"horizons,":[237],"loss":[239],"consistent":[241],"with":[242],"drifting":[244],"level":[245],"futures.":[249]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}