{"id":"https://openalex.org/W7162138311","doi":"https://doi.org/10.48550/arxiv.2605.21552","title":"Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift","display_name":"Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162138311","doi":"https://doi.org/10.48550/arxiv.2605.21552"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21552","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21552","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001024380","display_name":"Jinzong Dong","orcid":"https://orcid.org/0000-0001-9742-0295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Jinzong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136813889","display_name":"Zhaohui Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Zhaohui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136803131","display_name":"Bo Gyeong Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Bo","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7429999709129333,"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":0.7429999709129333,"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":0.04600000008940697,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.040300000458955765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.9028000235557556},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6786999702453613},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.5029000043869019},{"id":"https://openalex.org/keywords/confidence-region","display_name":"Confidence region","score":0.47130000591278076},{"id":"https://openalex.org/keywords/coverage-probability","display_name":"Coverage probability","score":0.44859999418258667},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.43380001187324524},{"id":"https://openalex.org/keywords/confidence-distribution","display_name":"Confidence distribution","score":0.37130001187324524}],"concepts":[{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.9028000235557556},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6786999702453613},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6435999870300293},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5716999769210815},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C143380155","wikidata":"https://www.wikidata.org/wiki/Q5160088","display_name":"Confidence region","level":3,"score":0.47130000591278076},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.44130000472068787},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C13662513","wikidata":"https://www.wikidata.org/wiki/Q5160087","display_name":"Confidence distribution","level":3,"score":0.37130001187324524},{"id":"https://openalex.org/C10590107","wikidata":"https://www.wikidata.org/wiki/Q7814221","display_name":"Tolerance interval","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C2779915747","wikidata":"https://www.wikidata.org/wiki/Q17058619","display_name":"Inverse probability weighting","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C18747219","wikidata":"https://www.wikidata.org/wiki/Q620994","display_name":"Standard error","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2809000015258789},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C66520545","wikidata":"https://www.wikidata.org/wiki/Q7353538","display_name":"Robust confidence intervals","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21552","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21552","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8291949033737183,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Confidence":[0],"calibration":[1,18,37,70,84,110],"for":[2,82,108,177],"classification":[3],"models":[4],"is":[5,142],"vital":[6],"in":[7],"safety-critical":[8],"decision-making":[9],"scenarios":[10],"and":[11,22,27,48,79,103,149,169,191],"has":[12,159],"received":[13],"extensive":[14],"attention.":[15],"General":[16],"confidence":[17,69,83,102,109,131],"methods":[19,38],"assume":[20],"training":[21],"test":[23],"data":[24],"are":[25,58],"independent":[26],"identically":[28],"distributed,":[29],"limiting":[30],"their":[31],"effectiveness":[32,184],"under":[33,39,71,85],"covariate":[34,40,72,86,94,113,193],"shifts.":[35,73],"Previous":[36],"shift":[41,194],"struggle":[42],"with":[43,144],"class-wise":[44,147],"or":[45,60],"canonical":[46,145],"calibrations":[47],"often":[49],"rely":[50],"on":[51,188],"unstable":[52],"importance":[53],"weighting":[54],"when":[55],"density":[56],"ratios":[57],"large":[59],"unbounded.":[61],"Given":[62],"the":[63,133,160,183],"above":[64],"limitations,":[65],"this":[66,121],"paper":[67,122],"rethinks":[68],"First,":[74],"we":[75,153,181],"derive":[76],"a":[77,105,171],"necessary":[78],"sufficient":[80],"condition":[81,107],"shifts,":[87],"named":[88,136],"Expectation":[89,118,137],"consistency":[90,119,138],"condition,":[91,120],"which":[92,141],"reveals":[93],"shifts":[95],"do":[96],"not":[97],"necessarily":[98],"lead":[99],"to":[100,129],"uncalibrated":[101],"provides":[104],"weaker":[106],"than":[111],"global":[112],"distribution":[114],"alignment.":[115],"Then,":[116],"utilizing":[117],"proposes":[123],"an":[124],"unsupervised":[125],"domain":[126],"adaptation":[127],"loss":[128,139,158],"calibrate":[130],"of":[132,185],"target":[134],"domain,":[135],"(ECL),":[140],"compatible":[143],"calibration,":[146,148],"top-label":[150],"calibration.":[151],"Third,":[152],"prove":[154],"that":[155],"computing":[156],"ECL":[157,178],"same":[161],"sample":[162],"complexity":[163],"as":[164],"Expected":[165],"Calibration":[166],"Error":[167],"(ECE)":[168],"provide":[170],"theoretically":[172],"grounded":[173],"mini-batch":[174],"trainable":[175],"scheme":[176],"loss.":[179],"Finally,":[180],"validate":[182],"our":[186],"method":[187],"both":[189],"simulated":[190],"real-world":[192],"datasets.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}