{"id":"https://openalex.org/W7127899703","doi":"https://doi.org/10.48550/arxiv.2602.04596","title":"Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference","display_name":"Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7127899703","doi":"https://doi.org/10.48550/arxiv.2602.04596"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.04596","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056084258","display_name":"Sandra Fortini","orcid":"https://orcid.org/0000-0003-0688-6538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fortini, Sandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125224202","display_name":"Kenyon Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, Kenyon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060041011","display_name":"Sonia Petrone","orcid":"https://orcid.org/0000-0003-2844-5100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petrone, Sonia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125144439","display_name":"Judith Rousseau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rousseau, Judith","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125205355","display_name":"Susan Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Susan","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":0.13536171,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3813999891281128,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3813999891281128,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1808999925851822,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05559999868273735,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.7541999816894531},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6047999858856201},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5375000238418579},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.4966999888420105},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.426800012588501},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.41830000281333923},{"id":"https://openalex.org/keywords/bayesian-statistics","display_name":"Bayesian statistics","score":0.3847000002861023},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3734999895095825},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3637999892234802}],"concepts":[{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.7541999816894531},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48010000586509705},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.41830000281333923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3950999975204468},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3847000002861023},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3560999929904938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35600000619888306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.34360000491142273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.323199987411499},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C149569020","wikidata":"https://www.wikidata.org/wiki/Q25098598","display_name":"Bayesian average","level":5,"score":0.27070000767707825},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C130648207","wikidata":"https://www.wikidata.org/wiki/Q6007562","display_name":"Imprecise probability","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C142291917","wikidata":"https://www.wikidata.org/wiki/Q4165283","display_name":"Bayes factor","level":4,"score":0.2639000117778778},{"id":"https://openalex.org/C91602232","wikidata":"https://www.wikidata.org/wiki/Q756115","display_name":"Volatility (finance)","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.04596","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.04596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.04596","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.04596","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":{"Bayes-filtered":[0,116],"transformers":[1,3],"are":[2,75],"meta-learned":[4],"on":[5],"sequences":[6],"from":[7,43],"a":[8,25,33,63,115,120],"prior":[9],"predictive":[10,17,22,56,64,92],"distribution":[11,93],"to":[12,40,113],"approximate":[13],"the":[14,37,52,77,81,87,90,101,111,140,160,163],"corresponding":[15],"posterior":[16,34,88],"distribution.":[18],"They":[19],"output":[20],"total":[21],"uncertainty":[23,45,147,168],"in":[24,80,155],"single":[26],"forward":[27],"pass":[28],"but":[29],"never":[30],"explicitly":[31],"represent":[32],"distribution,":[35],"making":[36],"standard":[38,144],"route":[39],"separating":[41],"aleatoric":[42,167],"epistemic":[44,107,146],"unavailable.":[46],"We":[47,109],"address":[48],"this":[49,104],"challenge":[50],"through":[51],"lens":[53],"of":[54,89,103,162],"Bayesian":[55],"inference":[57],"(BPI).":[58],"Our":[59],"main":[60],"result":[61],"is":[62,119,153],"Central":[65],"Limit":[66],"Theorem":[67],"(CLT)":[68],"for":[69,124],"supervised":[70],"settings":[71],"under":[72],"conditions":[73],"that":[74,118],"among":[76],"weakest":[78],"known":[79],"BPI":[82],"literature.":[83],"The":[84,127],"CLT":[85],"characterises":[86],"limiting":[91],"given":[94],"an":[95],"observed":[96,157],"context":[97,136,150,164],"as":[98,135],"asymptotically":[99],"Gaussian;":[100],"variance":[102],"Gaussian":[105],"quantifies":[106],"uncertainty.":[108],"apply":[110],"framework":[112],"TabPFN,":[114],"transformer":[117],"state-of-the-art":[121],"foundation":[122],"model":[123],"tabular":[125],"prediction.":[126],"resulting":[128],"credible":[129],"bands":[130],"achieve":[131],"near-nominal":[132],"frequentist":[133],"coverage":[134],"length":[137,151],"grows,":[138],"and":[139,152],"decomposition":[141],"largely":[142],"matches":[143],"desiderata:":[145],"shrinks":[148],"with":[149],"highest":[154],"sparsely":[156],"regions":[158],"within":[159],"span":[161],"data,":[165],"while":[166],"dominates":[169],"near":[170],"decision":[171],"boundaries":[172],"where":[173],"classes":[174],"overlap.":[175]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-02-07T00:00:00"}