{"id":"W4412889972","doi":"10.18653/v1/2025.acl-long.1253","title":"Delta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer’s Disease Detection","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Context (archaeology); Selection (genetic algorithm); Computer science; Disease; Delta; Artificial intelligence; Machine learning; Medicine; Engineering; Biology; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000978059,0.0003063669,0.0003290457,0.0007950042,0.0001982024,0.0002482728,0.0005616483,0.0003499221,0.00000634923],"category_scores_gemma":[0.0007005585,0.0003491605,0.0001278097,0.0006058169,0.00001585053,0.0003680733,0.0005362579,0.001620264,0.000003453972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004509124,"about_ca_system_score_gemma":0.0008152218,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006096037,"about_ca_topic_score_gemma":0.01961428,"domain_scores_codex":[0.997295,0.0004316053,0.0006665267,0.0009271412,0.0002389015,0.0004407807],"domain_scores_gemma":[0.9987028,0.0003238353,0.0003147903,0.0003469787,0.0001963532,0.0001152742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006103975,0.00004228817,0.05096181,0.0004841701,0.00001442186,0.000003185938,0.0006419219,0.1347179,0.00007449302,0.003425648,0.00001364161,0.8095595],"study_design_scores_gemma":[0.0003361322,0.00007044606,0.05458435,0.0001898738,0.0000190274,0.00000186158,0.00006348824,0.941507,0.0003180531,0.002448868,0.0001745243,0.0002864164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04696662,0.0004285131,0.9479777,0.001383855,0.0008471824,0.001661068,0.000002861413,0.000426983,0.0003051949],"genre_scores_gemma":[0.9822911,0.00001683228,0.01646217,0.0002193512,0.0001198423,0.0006429894,0.00003103354,0.00001710224,0.0001996035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9353244,"threshold_uncertainty_score":0.999896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02893686410533181,"score_gpt":0.3161260530222992,"score_spread":0.2871891889169674,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}