{"id":"W4400800567","doi":"10.17615/qf3r-gk79","title":"Large‐margin classification with multiple decision rules","year":2024,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; BioClinica; Amorfix Life Sciences; Synarc; University of Southern California; Medpace; Biogen; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Bayer HealthCare; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Association","keywords":"Margin (machine learning); Computer science; Decision rule; Artificial intelligence; Data mining; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001854297,0.0001267905,0.0001611683,0.00006155217,0.0001014003,0.0001798327,0.00009788963,0.00006071194,0.0001221745],"category_scores_gemma":[0.0008319149,0.00008376572,0.00003354558,0.0001358596,0.00007609775,0.0004847029,0.00004714562,0.0001268613,0.00005009698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001539768,"about_ca_system_score_gemma":0.00005392605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001221002,"about_ca_topic_score_gemma":0.000007661277,"domain_scores_codex":[0.9991218,0.00004883796,0.000187723,0.0002572217,0.0001901815,0.000194262],"domain_scores_gemma":[0.9966899,0.002949523,0.00003149725,0.0002305641,0.00003254448,0.00006603866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005256024,0.00003602622,0.00007648731,0.00008465539,0.00001590545,0.0000128701,0.0004596038,0.000004368828,0.0001221202,0.9678369,0.003010372,0.02828818],"study_design_scores_gemma":[0.0001888659,0.00004127627,0.0002123918,0.0001416068,0.00002045688,0.000003492815,0.0002272005,0.02121423,0.0005560773,0.9492285,0.02804231,0.000123548],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005251511,0.0004327721,0.9900635,0.0003071487,0.0001415777,0.0001595949,0.00009142044,0.0003105933,0.00324188],"genre_scores_gemma":[0.07608369,0.000007749361,0.9225678,0.00005749492,0.00007847358,0.00002859259,0.00002340475,0.00003534884,0.001117411],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07083218,"threshold_uncertainty_score":0.3415867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1103658571258763,"score_gpt":0.3819690669988144,"score_spread":0.2716032098729381,"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."}}