{"id":"https://openalex.org/W7133513783","doi":"https://doi.org/10.48550/arxiv.2603.02840","title":"Adapting Time Series Foundation Models through Data Mixtures","display_name":"Adapting Time Series Foundation Models through Data Mixtures","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133513783","doi":"https://doi.org/10.48550/arxiv.2603.02840"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128070785","display_name":"Thomas L. Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Thomas L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128089100","display_name":"Edoardo M. Ponti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ponti, Edoardo M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023731605","display_name":"AMOS J. STORKEY","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Storkey, Amos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T11918","display_name":"Forecasting Techniques and Applications","score":0.649399995803833,"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"}},"topics":[{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.649399995803833,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.16910000145435333,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.053300000727176666,"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/series","display_name":"Series (stratigraphy)","score":0.6625000238418579},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6402000188827515},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5723000168800354},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5504999756813049},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4952000081539154},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47290000319480896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303000092506409},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.6625000238418579},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6212000250816345},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.2825999855995178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02840","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02840","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time":[0],"series":[1,17,112,128],"foundation":[2],"models":[3],"(TSFMs)":[4],"have":[5],"become":[6],"increasingly":[7],"popular":[8],"for":[9,13,90,109,152],"zero-shot":[10,58,246],"forecasting.":[11,247],"However,":[12,114],"a":[14,31,35,42,54,71,83,126,222],"new":[15,36],"time":[16,111,127,157],"domain":[18,37],"not":[19,122],"fully":[20],"covered":[21],"by":[22,102,232],"the":[23,47,91,94,145,156,165,175,179,192,227,234],"pretraining":[24],"set,":[25],"performance":[26],"can":[27,130,141,240],"suffer.":[28],"Therefore,":[29],"when":[30,220],"practitioner":[32],"cares":[33],"about":[34],"and":[38,181,219],"has":[39],"access":[40],"to":[41,52,56,63,69,96,144,202,236,244],"set":[43,197],"of":[44,66,93,99,106,136,155,186,191],"related":[45],"datasets,":[46],"question":[48],"arises:":[49],"how":[50],"best":[51,173],"fine-tune":[53,70],"TSFM":[55,95],"improve":[57,245],"forecasting?":[59],"A":[60],"typical":[61],"approach":[62],"this":[64],"type":[65],"problem":[67],"is":[68,198],"LoRA":[72],"module":[73,85,224],"on":[74,79,86,184,206,225],"all":[75,226],"datasets":[76],"or":[77,148],"separately":[78,183],"each":[80,87,185,196],"dataset.":[81],"Tuning":[82],"separate":[84],"dataset":[88,129],"allows":[89],"specialisation":[92],"different":[97,110,153],"types":[98,135],"data":[100,132,166,193,235],"distribution,":[101],"selecting":[103],"differing":[104,150],"combinations":[105],"per-dataset":[107,119,217],"modules":[108,120,204],"contexts.":[113],"we":[115,160,239],"find":[116],"that,":[117],"using":[118,167],"might":[121],"be":[123,142],"optimal,":[124],"since":[125],"contain":[131],"from":[133],"several":[134],"distributions,":[137],"i.e.":[138],"sub-domains.":[139,208],"This":[140,189,229],"due":[143],"distribution":[146],"shifting":[147],"having":[149],"distributions":[151],"dimensions":[154],"series.":[158],"Hence,":[159],"propose":[161],"MixFT":[162,213],"which":[163],"re-divides":[164],"Bayesian":[168],"mixtures":[169],"into":[170],"sets":[171],"that":[172,195,212,231],"represent":[174,237],"sub-domains":[176,238],"present":[177],"in":[178],"data,":[180],"fine-tunes":[182],"these":[187],"sets.":[188],"re-division":[190],"ensures":[194],"more":[199],"homogeneous,":[200],"leading":[201],"fine-tuned":[203],"focused":[205],"specific":[207],"Our":[209],"experiments":[210],"show":[211],"performs":[214],"better":[215,241],"than":[216],"methods":[218],"fine-tuning":[221],"single":[223],"data.":[228],"suggests":[230],"re-partitioning":[233],"specialise":[242],"TSFMs":[243]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-05T00:00:00"}