{"id":"https://openalex.org/W7225316155","doi":"https://doi.org/10.5281/zenodo.23967812","title":"An Exact-Bayes Account of the Few-Label Protocol Gap in Tabular Foundation Models","display_name":"An Exact-Bayes Account of the Few-Label Protocol Gap in Tabular Foundation Models","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225316155","doi":"https://doi.org/10.5281/zenodo.23967812"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23967812","doi":"https://doi.org/10.5281/zenodo.23967812","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23967812","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23967812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051159291","display_name":"Felipe Provezano Coutinho","orcid":"https://orcid.org/0000-0001-7206-5856","observed_orcids":["https://orcid.org/0000-0001-7206-5856"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Coutinho, Felipe Provezano","raw_affiliation_strings":["Independent researcher"],"raw_orcid":"https://orcid.org/0000-0001-7206-5856","affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051159291"],"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.7056000232696533,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.7056000232696533,"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":0.27559998631477356,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.004600000102072954,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/tabular-foundation-models","display_name":"tabular foundation models","score":0.9139999747276306},{"id":"https://openalex.org/keywords/class-priors","display_name":"class priors","score":0.753000020980835},{"id":"https://openalex.org/keywords/share-classes","display_name":"class shares","score":0.902999997138977},{"id":"https://openalex.org/keywords/balanced-accuracy","display_name":"balanced accuracy","score":0.9269999861717224},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.40700000524520874},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.48399999737739563},{"id":"https://openalex.org/keywords/binary-classification","display_name":"binary classification","score":0.37700000405311584},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"multi-class classification","score":0.8840000033378601}],"concepts":[{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5751000046730042},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5040000081062317},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4560000002384186},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.5281/zenodo.23967812","doi":"https://doi.org/10.5281/zenodo.23967812","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23967812","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23967813","doi":"https://doi.org/10.5281/zenodo.23967813","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23967813","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23976352","doi":"https://doi.org/10.5281/zenodo.23976352","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23976352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24091828","doi":"https://doi.org/10.5281/zenodo.24091828","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24091828","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24113635","doi":"https://doi.org/10.5281/zenodo.24113635","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24113635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.24116441","doi":"https://doi.org/10.5281/zenodo.24116441","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24116441","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.23967812","doi":"https://doi.org/10.5281/zenodo.23967812","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23967812","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7167575126","https://openalex.org/W7214710076","https://openalex.org/W7223145601","https://openalex.org/W7223222201","https://openalex.org/W7166702486","https://openalex.org/W7214887749","https://openalex.org/W7214634886","https://openalex.org/W7160642232","https://openalex.org/W7164328898","https://openalex.org/W7201855661"],"abstract_inverted_index":{"Few-label":[0],"benchmarks":[1],"for":[2,110,114,178],"tabular":[3],"foundation":[4],"models":[5,48,153,224],"often":[6],"label":[7],"equally":[8],"many":[9,45],"rows":[10],"per":[11],"class.":[12],"Compared":[13],"with":[14],"random":[15],"labelling,":[16],"this":[17,32,163],"stratified":[18,56],"labelling":[19,232],"raises":[20,27],"balanced":[21,111],"accuracy,":[22],"lowers":[23],"accuracy":[24,112],"and":[25,29,95,125,162,187,234],"usually":[26],"macro-F1,":[28],"we":[30,66,147,202],"call":[31,67],"difference":[33],"the":[34,51,62,70,73,78,93,101,105,120,135,149,155,159,169,188,207,213,231,235],"protocol":[35,189,233],"gap.":[36,53,137],"We":[37],"show":[38,206],"that":[39,89,98,123,128,222],"an":[40],"exact":[41,136,160],"Bayesian":[42],"classifier,":[43],"which":[44,65,201],"of":[46,119,144,151,158,168,172,174],"these":[47,223],"approximate,":[49],"has":[50,212],"same":[52,208,214],"Since":[54],"a":[55,87,96,126,183],"labelled":[57],"set":[58],"says":[59],"nothing":[60],"about":[61],"class":[63,68,102],"priors,":[64],"shares,":[69],"classifier":[71],"favours":[72],"common":[74],"classes":[75,94],"only":[76],"when":[77],"labels":[79],"are":[80,107,225],"random.":[81],"The":[82],"gap":[83],"splits":[84],"exactly":[85],"into":[86],"part":[88,97],"comes":[90,99],"from":[91,100],"learning":[92],"shares.":[103],"When":[104],"features":[106],"weak,":[108],"decoding":[109,177],"or":[113],"macro-F1":[115,179,194],"removes":[116],"almost":[117],"all":[118],"gain":[121,171],"in":[122],"metric,":[124],"network":[127],"was":[129],"trained":[130],"on":[131],"such":[132],"tasks":[133],"reproduces":[134],"On":[138],"50":[139],"new":[140],"real":[141],"tables,":[142,200],"43":[143],"them":[145],"binary,":[146],"divided":[148],"outputs":[150],"four":[152],"by":[154],"class-share":[156],"estimate":[157],"Bayesian,":[161],"removed":[164],"52%":[165],"to":[166],"79%":[167],"balanced-accuracy":[170],"three":[173],"them.":[175],"After":[176],"no":[180],"model":[181],"keeps":[182],"significantly":[184],"positive":[185],"gain,":[186],"alone":[190],"reverses":[191],"most":[192],"pairwise":[193],"orders.":[195],"A":[196],"further":[197],"18":[198],"multiclass":[199],"analyse":[203],"as":[204],"exploratory,":[205],"signs.":[209],"Logistic":[210],"regression":[211],"signature,":[215],"so":[216],"our":[217],"account":[218],"does":[219],"not":[220],"imply":[221],"Bayesian.":[226],"Evaluations":[227],"should":[228],"therefore":[229],"report":[230],"decision":[236],"rule.":[237]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-06T00:00:00"}