{"id":"https://openalex.org/W7225653108","doi":"https://doi.org/10.5281/zenodo.24053187","title":"Three corrections to model-validation tests (conformal coverage, shift resilience, situation testing): the false-alarm rate each removes and the power each costs, measured on planted data","display_name":"Three corrections to model-validation tests (conformal coverage, shift resilience, situation testing): the false-alarm rate each removes and the power each costs, measured on planted data","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225653108","doi":"https://doi.org/10.5281/zenodo.24053187"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24053187","doi":"https://doi.org/10.5281/zenodo.24053187","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053187","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.24053187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057549475","display_name":"Felipe A. Santib\u00e1\u00f1ez-Leal","orcid":"https://orcid.org/0000-0002-0150-3246","observed_orcids":["https://orcid.org/0000-0002-0150-3246"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Santib\u00e1\u00f1ez-Leal, Felipe","raw_affiliation_strings":["CAOS open-research programme, Santiago, Chile"],"raw_orcid":"https://orcid.org/0000-0002-0150-3246","affiliations":[{"raw_affiliation_string":"CAOS open-research programme, Santiago, Chile","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5057549475"],"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":0.20759999752044678,"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":0.20759999752044678,"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/T14374","display_name":"Statistical Methods in Epidemiology","score":0.05249999836087227,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.05079999938607216,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/model-validation","display_name":"model validation","score":0.6710000038146973},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.8289999961853027},{"id":"https://openalex.org/keywords/false-alarm-rate","display_name":"false alarm rate","score":0.8799999952316284},{"id":"https://openalex.org/keywords/statistical-power","display_name":"statistical power","score":0.9190000295639038},{"id":"https://openalex.org/keywords/permutation-tests","display_name":"permutation tests","score":0.7429999709129333},{"id":"https://openalex.org/keywords/risk-model-validation","display_name":"risk model validation","score":0.4480000138282776}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7067999839782715},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6819999814033508},{"id":"https://openalex.org/C2781315470","wikidata":"https://www.wikidata.org/wiki/Q193623","display_name":"Binomial (polynomial)","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C41054675","wikidata":"https://www.wikidata.org/wiki/Q185547","display_name":"Binomial distribution","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C165793278","wikidata":"https://www.wikidata.org/wiki/Q2301904","display_name":"Sign test","level":4,"score":0.4577000141143799},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C18747219","wikidata":"https://www.wikidata.org/wiki/Q620994","display_name":"Standard error","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C34602496","wikidata":"https://www.wikidata.org/wiki/Q2271882","display_name":"Sequential probability ratio test","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C148444598","wikidata":"https://www.wikidata.org/wiki/Q864022","display_name":"Binomial test","level":4,"score":0.27250000834465027},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C33643355","wikidata":"https://www.wikidata.org/wiki/Q5176731","display_name":"Count data","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C154606282","wikidata":"https://www.wikidata.org/wiki/Q7048579","display_name":"Nominal level","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24053187","doi":"https://doi.org/10.5281/zenodo.24053187","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053187","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.24053188","doi":"https://doi.org/10.5281/zenodo.24053188","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053188","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.24053187","doi":"https://doi.org/10.5281/zenodo.24053187","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053187","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225652905","https://openalex.org/W7225621281","https://openalex.org/W2784589584","https://openalex.org/W7225658821","https://openalex.org/W4402129803","https://openalex.org/W2786577639","https://openalex.org/W2787806740","https://openalex.org/W2787101927","https://openalex.org/W2385523400","https://openalex.org/W2785687334"],"abstract_inverted_index":{"The":[0,50],"literature":[1],"that":[2,18],"recommends":[3],"a":[4,54,66,82,93,148,169,175,191,208],"validation":[5],"test":[6,52,72,118,123,150],"rarely":[7],"states":[8],"its":[9,89,152,234],"size":[10,95,112,144,158,235],"and":[11,30,96,98,111,117,233,240,245],"power.":[12],"We":[13],"measure":[14],"the":[15,31,36,44,58,62,70,74,78,85,99,102,120,131,139,156,160,186,204,216,225,238,241],"error":[16,46,134],"rate":[17],"three":[19],"corrections":[20],"remove":[21],"in":[22,128,178,197,211],"an":[23,125],"open":[24],"risk-model":[25],"engine,":[26],"running":[27],"each":[28],"rule":[29,32,100],"it":[33],"replaces":[34],"on":[35,77,106,237],"same":[37,161],"seeded":[38],"draws":[39],"of":[40,47,53,65,108,130,172,180,193],"known-truth":[41],"generators,":[42],"with":[43,151],"standard":[45,195],"every":[48],"rate.":[49],"coverage":[51,122],"split-conformal":[55],"set":[56],"reads":[57,73],"covered":[59],"count":[60],"against":[61,81,136,183,199,213],"Beta-Binomial":[63,140],"law":[64],"finite":[67],"calibration":[68,116],"window;":[69],"resilience":[71],"AUC":[75],"drop":[76,171],"worst":[79],"subsample":[80],"permutation":[83,187],"reference;":[84],"situation-testing":[86],"light":[87],"takes":[88],"amber":[90],"cut":[91,104,153,205,217,226],"from":[92],"measured":[94],"power,":[97],"selects":[101],"engine's":[103],"0.20":[105,206,227],"one":[107],"four":[109],"design":[110],"pairs.":[113],"At":[114],"equal":[115],"windows":[119],"binomial":[121,149],"rejects":[124],"exchangeable":[126],"window":[127],"0.157":[129],"replications":[132,182],"(standard":[133],"0.006)":[135],"0.051":[137],"for":[138,185,215],"test,":[141],"whose":[142],"exact":[143,157],"never":[145],"exceeds":[146],"0.0499;":[147],"calibrated":[154],"to":[155],"has":[159],"power":[162,229],"within":[163],"0.019.":[164],"With":[165,201],"500":[166],"evaluation":[167],"rows":[168],"fixed":[170],"0.05":[173],"raises":[174,207],"false":[176,209],"alarm":[177,210],"0.175":[179],"shift-free":[181],"0.062":[184],"reference,":[188],"which":[189],"detects":[190],"shift":[192],"two":[194],"deviations":[196],"0.680":[198],"0.925.":[200],"400":[202],"applicants":[203,239],"0.014":[212],"0.114":[214],"0.10.":[218],"Of":[219],"10":[220],"predictions,":[221],"3":[222],"are":[223],"refuted:":[224],"costs":[228],"at":[230],"small":[231],"gaps,":[232],"depends":[236],"data":[242],"process.":[243],"Repository":[244],"reproducible":[246],"pipeline":[247],"(MIT):":[248],"https://github.com/fsantibanezleal/CAOS_Contraste":[249],".":[250]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
