{"id":"https://openalex.org/W7212045362","doi":"https://doi.org/10.48550/arxiv.2609.07729","title":"Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers","display_name":"Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers","publication_year":2026,"publication_date":"2026-09-07","ids":{"openalex":"https://openalex.org/W7212045362","doi":"https://doi.org/10.48550/arxiv.2609.07729"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.07729","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07729","pdf_url":"https://arxiv.org/pdf/2609.07729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.07729","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150899771","display_name":"Jakob Snel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726832","display_name":"T\u00fcbingen AI Center","ror":"https://ror.org/0107nyd78","country_code":"DE","type":"education","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521","https://openalex.org/I4401726832","https://openalex.org/I8087733"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Snel, Jakob","raw_affiliation_strings":["Hertie Institute for AI in Brain Health , University of T\u00fcbingen , T\u00fcbingen , Germany","T\u00fcbingen AI Center , University of T\u00fcbingen , T\u00fcbingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hertie Institute for AI in Brain Health , University of T\u00fcbingen , T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"T\u00fcbingen AI Center , University of T\u00fcbingen , T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I4401726832","https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000408018","display_name":"Marc-Andr\u00e9 Schulz","orcid":"https://orcid.org/0000-0002-1140-1841","observed_orcids":["https://orcid.org/0000-0002-1140-1841"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schulz, Marc-Andre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.4246000051498413,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.4246000051498413,"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":0.07599999755620956,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.07370000332593918,"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/training-data-attribution","display_name":"training data attribution","score":0.9269999861717224},{"id":"https://openalex.org/keywords/influence-function","display_name":"influence function","score":0.5559999942779541},{"id":"https://openalex.org/keywords/cohen-s-d","display_name":"Cohen's d","score":0.7590000033378601},{"id":"https://openalex.org/keywords/chronological-age-estimation","display_name":"chronological age estimation","score":0.6050000190734863},{"id":"https://openalex.org/keywords/brain-age","display_name":"brain age","score":0.5600000023841858},{"id":"https://openalex.org/keywords/type-2-diabetes","display_name":"type 2 diabetes","score":0.7670000195503235},{"id":"https://openalex.org/keywords/multiple-sclerosis","display_name":"multiple sclerosis","score":0.9980000257492065},{"id":"https://openalex.org/keywords/hba1c","display_name":"HbA1c","score":0.7749999761581421},{"id":"https://openalex.org/keywords/disease-risk-prediction","display_name":"disease risk prediction","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.8105999827384949},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4553000032901764},{"id":"https://openalex.org/C113280763","wikidata":"https://www.wikidata.org/wiki/Q2326546","display_name":"Subclinical infection","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3855000138282776},{"id":"https://openalex.org/C2781197716","wikidata":"https://www.wikidata.org/wiki/Q864574","display_name":"Biomarker","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C555293320","wikidata":"https://www.wikidata.org/wiki/Q12206","display_name":"Diabetes mellitus","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C74909509","wikidata":"https://www.wikidata.org/wiki/Q10387","display_name":"Gerontology","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C500499127","wikidata":"https://www.wikidata.org/wiki/Q332154","display_name":"Ageing","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2992879847","wikidata":"https://www.wikidata.org/wiki/Q374758","display_name":"Multilevel modelling","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C3017819807","wikidata":"https://www.wikidata.org/wiki/Q332154","display_name":"Healthy aging","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.07729","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07729","pdf_url":"https://arxiv.org/pdf/2609.07729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.07729","doi":"https://doi.org/10.48550/arxiv.2609.07729","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.07729","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.07729","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07729","pdf_url":"https://arxiv.org/pdf/2609.07729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.9537000060081482}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212045362.pdf","grobid_xml":"https://content.openalex.org/works/W7212045362.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2766141193","https://openalex.org/W2951042025","https://openalex.org/W3016088911","https://openalex.org/W3089258874","https://openalex.org/W4390429644","https://openalex.org/W4402552274","https://openalex.org/W4403784742","https://openalex.org/W7204636947","https://openalex.org/W7204655968"],"related_works":["https://openalex.org/W3144485242","https://openalex.org/W7136862790","https://openalex.org/W6906428882","https://openalex.org/W7131117753","https://openalex.org/W4415165071","https://openalex.org/W6948852928","https://openalex.org/W4230832329","https://openalex.org/W7166882143","https://openalex.org/W4406523762","https://openalex.org/W4393408837"],"abstract_inverted_index":{"Normative":[0],"age":[1,8,26,41],"models":[2],"are":[3,144],"trained":[4],"to":[5,15,44],"predict":[6],"chronological":[7,25],"in":[9,87,102],"a":[10,51,125],"nominally":[11],"healthy":[12],"cohort.":[13],"Applied":[14],"patients,":[16],"they":[17],"deviate,":[18],"and":[19,24,83,115,193],"the":[20,35,40,55,61,91,109,117,138,161,169,173,178],"gap":[21,42],"between":[22],"predicted":[23],"is":[27,176],"read":[28],"as":[29,54],"disease":[30],"risk.":[31],"Here,":[32],"we":[33],"attribute":[34],"disease-related":[36,99],"effect":[37,75,100,111,119,130],"size":[38,101,131],"of":[39,181],"directly":[43],"individual":[45],"training":[46,71,95],"samples,":[47],"rather":[48],"than":[49,107],"using":[50],"prediction-level":[52],"loss":[53],"attribution":[56],"target.":[57],"For":[58,165],"Cohen's":[59],"$d$,":[60],"resulting":[62],"closed-form":[63],"influence":[64],"functional,":[65],"validated":[66],"against":[67],"leave-one-out":[68],"retraining,":[69],"ranks":[70],"samples":[72,96,143],"by":[73,123],"their":[74],"on":[76,159],"held-out":[77,98],"case-control":[78],"separation.":[79],"Across":[80],"four":[81],"diseases":[82],"two":[84],"biomarker":[85],"modalities":[86],"UK":[88],"Biobank,":[89],"removing":[90],"10%":[92],"most":[93],"influential":[94],"raises":[97,116],"every":[103],"seed.":[104],"It":[105],"more":[106],"doubles":[108],"metabolomic-age":[110],"for":[112,120,191],"type-2":[113,166],"diabetes":[114],"brain-age":[118],"multiple":[121],"sclerosis":[122],"roughly":[124],"third.":[126],"Random":[127],"removal":[128],"leaves":[129],"flat":[132],"even":[133],"at":[134],"50%":[135],"removal,":[136],"confirming":[137],"gain":[139],"comes":[140],"from":[141],"which":[142],"removed,":[145],"not":[146],"how":[147],"many.":[148],"Flagged":[149],"subjects":[150],"carry":[151],"subclinical":[152],"cardiometabolic":[153],"burden":[154],"that":[155],"diagnosis-based":[156],"exclusion":[157],"misses,":[158],"markers":[160],"model":[162],"never":[163],"sees.":[164],"diabetes,":[167],"where":[168],"method":[170],"gains":[171],"most,":[172],"marker":[174],"recovered":[175],"HbA1c,":[177],"standard":[179],"measure":[180],"blood":[182],"sugar":[183],"control.":[184],"We":[185],"release":[186],"pyinfluence,":[187],"our":[188],"influence-function":[189],"package,":[190],"reproducibility":[192],"reuse.":[194]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}