{"id":"https://openalex.org/W7160963815","doi":"https://doi.org/10.48550/arxiv.2605.08217","title":"Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting","display_name":"Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160963815","doi":"https://doi.org/10.48550/arxiv.2605.08217"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08217","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08217","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.08217","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135980819","display_name":"Rishi Ahuja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahuja, Rishi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135928616","display_name":"Kumar Prateek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prateek, Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135989717","display_name":"Simranjit Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Simranjit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135945632","display_name":"Vijay Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Vijay","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":null,"has_fulltext":false,"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":0.39500001072883606,"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":0.39500001072883606,"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":0.2644999921321869,"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":0.19449999928474426,"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/premise","display_name":"Premise","score":0.7103000283241272},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6302000284194946},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.46230000257492065},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.42989999055862427},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3779999911785126},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.36640000343322754}],"concepts":[{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.7103000283241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450999975204468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08217","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08217","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.08217","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08217","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,"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"},"sustainable_development_goals":[{"score":0.5194844603538513,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time":[0],"Series":[1],"Foundation":[2],"Models":[3],"(TSFMs)":[4],"have":[5],"borrowed":[6],"the":[7,16,23,42,59,66,146,151,162],"long":[8],"context":[9,54,80],"paradigm":[10],"from":[11,174],"natural":[12],"language":[13],"processing":[14],"under":[15],"premise":[17,48],"that":[18,94],"feeding":[19],"more":[20],"history":[21,33],"into":[22],"model":[24,163],"improves":[25],"forecast":[26],"quality.":[27],"But":[28],"in":[29],"stochastic":[30],"domains,":[31],"distant":[32],"is":[34,107],"often":[35],"just":[36],"high-frequency":[37],"noise,":[38],"not":[39],"signal.":[40],"Hence,":[41],"proposed":[43],"work":[44],"tests":[45],"whether":[46],"this":[47],"actually":[49],"holds":[50],"by":[51,90],"running":[52],"continuous":[53],"architectures":[55],"(PatchTST":[56],"included)":[57],"through":[58],"ETTh1":[60],"benchmark.":[61],"The":[62],"obtained":[63],"results":[64],"contradict":[65],"premise:":[67],"an":[68,110],"inverse":[69],"scaling":[70],"law":[71],"shows":[72],"up":[73],"clearly,":[74],"with":[75,121],"forecasting":[76],"error":[77,117],"rising":[78],"as":[79,109,156],"gets":[81],"longer.":[82],"A":[83],"3,000-step":[84],"window":[85,125],"causes":[86],"performance":[87],"to":[88,183],"drop":[89],"over":[91],"68%,":[92],"evidence":[93],"attention":[95],"mechanisms":[96],"are":[97],"poor":[98],"at":[99],"ignoring":[100],"irrelevant":[101],"historical":[102,154],"volatility.":[103],"Retrieval-Augmented":[104],"Forecasting":[105],"(RAFT)":[106],"evaluated":[108],"alternative.":[111],"RAFT":[112],"achieves":[113],"a":[114,122,164],"mean":[115],"squared":[116],"(MSE)":[118],"of":[119],"0.379":[120],"fixed":[123],"720-step":[124],"and":[126,133],"selective":[127,187],"retrieval,":[128],"outperforming":[129],"both":[130],"long-context":[131],"configurations":[132],"zero-shot":[134],"foundation":[135,178],"models":[136,179],"(Chronos,":[137],"Moirai)":[138],"despite":[139],"requiring":[140],"far":[141],"less":[142],"computation.":[143],"In":[144],"addition,":[145],"retrieval":[147],"step":[148],"injects":[149],"only":[150],"most":[152],"relevant":[153],"segments":[155],"dynamic":[157],"exogenous":[158],"variables,":[159],"which":[160],"gives":[161],"context-informed":[165],"inductive":[166],"bias":[167],"it":[168],"cannot":[169],"build":[170],"on":[171],"its":[172],"own":[173],"raw":[175],"sequences.":[176],"Therefore,":[177],"going":[180],"forward":[181],"need":[182],"shift":[184],"architecturally":[185],"toward":[186],"retrieval.":[188]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}