{"id":"https://openalex.org/W7224102129","doi":"https://doi.org/10.5281/zenodo.23737416","title":"Benchmark record: per-replicate predictions and goodness-of-fit results with the true risk known (Tabular foundation models are not a shortcut to calibrated clinical risk prediction)","display_name":"Benchmark record: per-replicate predictions and goodness-of-fit results with the true risk known (Tabular foundation models are not a shortcut to calibrated clinical risk prediction)","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224102129","doi":"https://doi.org/10.5281/zenodo.23737416"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23737416","doi":"https://doi.org/10.5281/zenodo.23737416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23737416","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":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23737416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143623642","display_name":"Ebrahim Khaled","orcid":"https://orcid.org/0009-0006-7839-8778","observed_orcids":["https://orcid.org/0009-0006-7839-8778"]},"institutions":[{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Ebrahim, Ebrahim Khaled","raw_affiliation_strings":["Department of Applied Statistics, Faculty of Business, Alexandria University, Alexandria, Egypt"],"raw_orcid":"https://orcid.org/0009-0006-7839-8778","affiliations":[{"raw_affiliation_string":"Department of Applied Statistics, Faculty of Business, Alexandria University, Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5143623642"],"corresponding_institution_ids":["https://openalex.org/I84524832"],"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/T14374","display_name":"Statistical Methods in Epidemiology","score":0.5062999725341797,"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"}},"topics":[{"id":"https://openalex.org/T14374","display_name":"Statistical Methods in Epidemiology","score":0.5062999725341797,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.34940001368522644,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.08420000225305557,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/clinical-risk-prediction","display_name":"clinical risk prediction","score":0.8980000019073486},{"id":"https://openalex.org/keywords/forecast-calibration","display_name":"forecast calibration","score":0.6499999761581421},{"id":"https://openalex.org/keywords/tabular-foundation-models","display_name":"tabular foundation models","score":0.9580000042915344},{"id":"https://openalex.org/keywords/tabpfn","display_name":"TabPFN","score":0.6679999828338623},{"id":"https://openalex.org/keywords/platt-scaling","display_name":"Platt scaling","score":0.6850000023841858},{"id":"https://openalex.org/keywords/firth-logistic-regression","display_name":"Firth logistic regression","score":0.7409999966621399},{"id":"https://openalex.org/keywords/ridge-regression","display_name":"ridge regression","score":0.6549999713897705},{"id":"https://openalex.org/keywords/goodness-of-fit","display_name":"goodness of fit","score":0.6830000281333923},{"id":"https://openalex.org/keywords/benchmark-simulation","display_name":"benchmark simulation","score":0.49000000953674316},{"id":"https://openalex.org/keywords/sepsis-survival","display_name":"sepsis survival","score":0.7329999804496765},{"id":"https://openalex.org/keywords/international-stroke-trial","display_name":"International Stroke Trial","score":0.8180000185966492},{"id":"https://openalex.org/keywords/recalibration","display_name":"recalibration","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5741999745368958},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C91998498","wikidata":"https://www.wikidata.org/wiki/Q1541178","display_name":"Contingency table","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C37945671","wikidata":"https://www.wikidata.org/wiki/Q7336207","display_name":"Risk-based testing","level":5,"score":0.2946999967098236},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C2778371416","wikidata":"https://www.wikidata.org/wiki/Q558116","display_name":"Firth","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C7515471","wikidata":"https://www.wikidata.org/wiki/Q1936882","display_name":"Stress testing (software)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23737416","doi":"https://doi.org/10.5281/zenodo.23737416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23737416","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":"Dataset"},{"id":"doi:10.5281/zenodo.23737417","doi":"https://doi.org/10.5281/zenodo.23737417","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23737417","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":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23737416","doi":"https://doi.org/10.5281/zenodo.23737416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23737416","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":"Dataset"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8048999905586243,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4413898935","https://openalex.org/W7220924736"],"related_works":["https://openalex.org/W7224120964","https://openalex.org/W7220924736","https://openalex.org/W7197004602","https://openalex.org/W7204222326","https://openalex.org/W7167054047","https://openalex.org/W7128430922","https://openalex.org/W7211926255","https://openalex.org/W4417356564","https://openalex.org/W7221537574","https://openalex.org/W2784589584"],"abstract_inverted_index":{"The":[0,32,233,283],"per-replicate":[1],"predictions":[2],"and":[3,87,90,97,101,116,119,137,144,164,171,178,181,194,203,217,255,260,279],"test":[4,60,192],"results":[5,193,221,235],"behind":[6],"the":[7,25,43,51,66,70,109,112,114,117,148,154,160,174,179,197,204,213,239,242,248,258,263,266,269,287],"article":[8,259],"\"Tabular":[9],"foundation":[10],"models":[11],"are":[12,222,236],"not":[13],"a":[14,21,55,276,280],"shortcut":[15],"to":[16,95],"calibrated":[17],"clinical":[18],"risk":[19,72],"prediction:":[20],"pre-registered":[22,35],"simulation":[23],"against":[24],"true":[26,71,110],"risk\"":[27],"by":[28],"Ebrahim":[29],"Khaled":[30],"Ebrahim.":[31],"study":[33],"was":[34],"on":[36,64,159,165],"OSF":[37],"Registries":[38],"(doi:10.17605/OSF.IO/8HMTZ);":[39],"this":[40],"record":[41,288],"is":[42,231,289],"open":[44],"benchmark":[45],"planned":[46],"in":[47],"Section":[48],"14":[49],"of":[50,84,93,122,153,168,185,241,257],"protocol,":[52],"so":[53],"that":[54,285],"new":[56],"calibration":[57,183],"method":[58],"or":[59,228],"can":[61],"be":[62],"run":[63],"exactly":[65],"same":[67],"predictions,":[68,191],"with":[69,130,136,147,238,272],"known.":[73],"Simulation.":[74],"For":[75,212],"58":[76],"scenarios":[77],"(four":[78],"true-risk":[79,180],"shapes":[80],"at":[81],"event":[82],"rates":[83],"3,":[85],"10":[86],"30":[88],"%":[89],"development":[91],"sizes":[92],"200":[94,172],"3,000,":[96],"five":[98],"stress":[99],"families)":[100],"1,000":[102],"random":[103],"designs:":[104],"for":[105,196],"every":[106,123,151,186,252],"evaluation":[107,162],"record,":[108],"risk,":[111],"outcome,":[113],"covariates,":[115],"prediction":[118],"exact-null":[120],"outcome":[121],"arm":[124],"(logistic":[125],"regression,":[126],"Firth":[127],"logistic":[128],"regression":[129],"intercept":[131],"correction,":[132],"ridge,":[133],"GAM,":[134],"LightGBM":[135],"without":[138],"Platt":[139],"scaling,":[140],"TabPFN-3.5,":[141],"TabICLv2,":[142],"Mitra-v2,":[143],"side":[145],"arms),":[146],"recalibration":[149],"ladder;":[150],"row":[152],"goodness-of-fit":[155],"layer":[156],"(ebrahim.gof":[157],"2.10.0)":[158],"full":[161],"sets":[163],"nested":[166],"subsamples":[167],"about":[169],"50":[170],"events;":[173],"oracle":[175],"size":[176],"study;":[177],"empirical":[182],"estimands":[184,195],"fit.":[187],"Real":[188],"data.":[189],"Per-replicate":[190],"Sepsis":[198],"Survival":[199],"Minimal":[200],"Clinical":[201],"Records":[202],"PhysioNet/CinC":[205],"Challenge":[206],"2012,":[207],"whose":[208],"licences":[209],"allow":[210],"it.":[211],"International":[214],"Stroke":[215],"Trial":[216],"CRASH-2,":[218],"only":[219],"aggregate":[220],"included;":[223],"no":[224],"row-level,":[225],"per-patient,":[226],"per-subsample":[227],"per-hospital":[229],"result":[230],"deposited.":[232],"CRASH-2":[234],"published":[237],"permission":[240],"trial's":[243],"Chief":[244],"Investigators.":[245],"Also":[246],"included:":[247],"tidy":[249],"analysis":[250],"tables,":[251,265,268],"summary":[253],"table":[254],"figure":[256],"its":[261,273],"supplement,":[262],"computing-cost":[264],"design":[267],"registered":[270],"protocol":[271],"deviations":[274],"log,":[275],"loader":[277],"(benchmark_loader.py)":[278],"data":[281],"dictionary.":[282],"code":[284],"produced":[286],"archived":[290],"separately":[291],"(doi:10.5281/zenodo.23737378).":[292],"Licence:":[293],"CC":[294],"BY":[295],"4.0.":[296]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}