{"id":"W4387207464","doi":"","title":"Sample Boosting Algorithm (SamBA) -An Interpretable Greedy Ensemble Classifier Based On Local Expertise For Fat Data","year":2023,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université Laval","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Compute Canada; Canadian Institute for Advanced Research; Aix-Marseille Université","keywords":"Boosting (machine learning); Classifier (UML); Greedy algorithm; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00385486,0.0009028066,0.002689604,0.001329315,0.0009090041,0.001349167,0.002615318,0.001577605,0.00248774],"category_scores_gemma":[0.006736766,0.0005466906,0.00145325,0.001093348,0.0006589143,0.001520149,0.002226943,0.002344595,0.001763314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005239375,"about_ca_system_score_gemma":0.001350376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002092141,"about_ca_topic_score_gemma":0.003123202,"domain_scores_codex":[0.9981747,0.0006839198,0.00008662503,0.0003307444,0.0005609326,0.0001630611],"domain_scores_gemma":[0.9977228,0.0008980382,0.00009556094,0.0003583269,0.0007994537,0.0001258416],"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":[0.0005530666,0.0002604775,0.003286609,0.0001609074,0.0003039021,0.000108469,0.0001397926,0.1981084,0.01228508,0.01538284,0.011635,0.7577755],"study_design_scores_gemma":[0.00001642027,0.00005674673,0.0002641006,0.00001019844,0.00002443385,0.00004443957,0.0000101204,0.9901934,0.001324748,0.006910692,0.001136887,0.000007812389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009423316,0.0002522624,0.9886892,0.0001108175,0.00006056994,0.00004608679,0.000062316,0.0008424816,0.0005128094],"genre_scores_gemma":[0.274772,0.0003168523,0.7200173,0.0003227615,0.0002289884,0.0002245692,0.0007176408,0.0003976667,0.003002241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00385486,"threshold_uncertainty_score":0.0203867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06381920132074156,"score_gpt":0.295999057353533,"score_spread":0.2321798560327915,"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."}}