{"id":"https://openalex.org/W7225619873","doi":"https://doi.org/10.5281/zenodo.24053185","title":"A leakage-safe validation protocol per case with invariance gates: the bias of the holdout AUC under fitting-path leaks, their detection by the gates, and what validation tests see of a development-only leak","display_name":"A leakage-safe validation protocol per case with invariance gates: the bias of the holdout AUC under fitting-path leaks, their detection by the gates, and what validation tests see of a development-only leak","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225619873","doi":"https://doi.org/10.5281/zenodo.24053185"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24053185","doi":"https://doi.org/10.5281/zenodo.24053185","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053185","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.24053185","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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.6991999745368958,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.6991999745368958,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.1542000025510788,"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/T13141","display_name":"Statistical Methods and Applications","score":0.025499999523162842,"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/data-leakage","display_name":"data leakage","score":0.8740000128746033},{"id":"https://openalex.org/keywords/credit-scoring","display_name":"credit scoring","score":0.6859999895095825},{"id":"https://openalex.org/keywords/model-validation","display_name":"model validation","score":0.4440000057220459},{"id":"https://openalex.org/keywords/stability-index","display_name":"stability index","score":0.5389999747276306},{"id":"https://openalex.org/keywords/weight-of-evidence","display_name":"weight of evidence","score":0.7059999704360962},{"id":"https://openalex.org/keywords/loan-default-prediction","display_name":"loan default prediction","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5630999803543091},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5489000082015991},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5482000112533569},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48100000619888306},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3822000026702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C184389593","wikidata":"https://www.wikidata.org/wiki/Q603159","display_name":"Curve fitting","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24053185","doi":"https://doi.org/10.5281/zenodo.24053185","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053185","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.24053186","doi":"https://doi.org/10.5281/zenodo.24053186","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053186","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.24053185","doi":"https://doi.org/10.5281/zenodo.24053185","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24053185","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/W7164300880","https://openalex.org/W7169790169","https://openalex.org/W2785870876","https://openalex.org/W7207648793","https://openalex.org/W7172534574","https://openalex.org/W7154319394","https://openalex.org/W2787806740","https://openalex.org/W7225653108","https://openalex.org/W7203462512","https://openalex.org/W7213427970"],"abstract_inverted_index":{"Binning,":[0],"weights":[1],"of":[2,17,57,93,105,120,146,170,175,189,201,215],"evidence,":[3],"screens,":[4],"configuration":[5],"choices":[6],"and":[7,43,97,109,127,153,179,251],"calibration":[8],"maps":[9],"are":[10],"fitted":[11,51],"with":[12,90,122,134,230],"rows":[13,58],"that":[14,47,65],"the":[15,60,66,75,78,80,94,111,115,156,164,181,199,202,210,231,247],"validation":[16],"a":[18,26,31,37,50,55,118,128,173,187,195,240],"probability-of-default":[19],"model":[20],"treats":[21],"as":[22],"new.":[23],"We":[24,63],"state":[25],"leakage-safe":[27],"protocol":[28,79],"per":[29],"case:":[30],"split":[32,197],"fixed":[33],"before":[34],"any":[35],"fit,":[36],"training":[38,61],"window":[39],"for":[40,144],"dated":[41,245],"cases,":[42],"three":[44,223],"invariance":[45],"gates":[46,236],"fail":[48],"when":[49,71],"parameter":[52],"changes":[53],"under":[54],"perturbation":[56],"outside":[59],"slice.":[62],"prove":[64],"holdout":[67,123],"estimate":[68],"is":[69,86,161],"unbiased":[70],"no":[72],"step":[73],"read":[74],"holdout.":[76],"Under":[77],"AUC":[81,165],"bias":[82],"on":[83,102,110,130,155],"planted":[84,116],"data":[85,117],"0.000":[87],"\u00b1":[88],"0.002":[89],"95.3%":[91],"coverage":[92,135],"95%":[95],"interval,":[96],"its":[98],"interval":[99],"contains":[100],"zero":[101],"2,500-row":[103],"samples":[104],"30,000":[106],"card":[107],"holders":[108],"product's":[112],"scorecard.":[113],"On":[114,191],"weight":[119],"evidence":[121],"labels":[124],"adds":[125],"+0.018":[126],"fit":[129],"every":[131],"row":[132],"+0.025,":[133],"falling":[136],"to":[137,217],"66.7%.":[138],"At":[139],"least":[140],"one":[141],"gate":[142],"fails":[143],"each":[145],"15":[147],"leaks":[148],"in":[149,168,184],"all":[150],"100":[151],"draws,":[152],"none":[154],"protocol.":[157],"A":[158],"development-only":[159],"leak":[160],"detected":[162],"by":[163,180],"against":[166],"development":[167],"99.0%":[169],"repetitions":[171],"at":[172,186],"shift":[174,188],"0.5":[176],"standard":[177,207],"deviations":[178],"stability":[182],"index":[183],"14.2%":[185],"one.":[190],"five":[192],"loan":[193],"cohorts":[194],"random":[196],"reproduces":[198],"level":[200],"5-year":[203],"rate":[204],"within":[205],"1.2":[206],"errors,":[208],"where":[209],"declared":[211],"cohort":[212],"shows":[213],"gaps":[214],"up":[216],"16.2":[218],"points.":[219],"Of":[220],"nine":[221],"predictions,":[222],"did":[224],"not":[225,238],"hold;":[226],"they":[227,233],"were":[228],"written":[229],"outputs":[232],"decide.":[234],"The":[235],"do":[237],"detect":[239],"feature":[241],"built":[242],"from":[243],"information":[244],"after":[246],"observation":[248],"date.":[249],"Repository":[250],"reproducible":[252],"pipeline":[253],"(MIT):":[254],"https://github.com/fsantibanezleal/CAOS_Contraste":[255],".":[256]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
