{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.007316228,0.000478138,0.0004774299,0.0003436092,0.000652782,0.001320939,0.006143487,0.0003591645,0.00002956522],"category_scores_gemma":[0.004902675,0.0005049208,0.0001767139,0.0004910977,0.0001779359,0.0006369741,0.004226105,0.0008908209,0.00006812623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002279035,"about_ca_system_score_gemma":0.0004081166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003687152,"about_ca_topic_score_gemma":0.001583781,"domain_scores_codex":[0.9919681,0.003862488,0.0007183131,0.00216605,0.0006827806,0.0006022963],"domain_scores_gemma":[0.9847382,0.004406074,0.000648341,0.008681376,0.001220965,0.0003050298],"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":[0.00002315376,0.000655174,0.0003443384,0.0001789522,0.00005203188,0.000005001245,0.002707358,0.001756786,0.0005387093,0.03806458,0.006056175,0.9496177],"study_design_scores_gemma":[0.0004530353,0.00000271104,0.0005615637,0.0009788532,0.00002705958,0.000002464542,0.00007447222,0.9706163,0.002818217,0.00314852,0.02082356,0.000493178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002964007,0.0001287481,0.9839568,0.01001955,0.0006245688,0.0006686428,0.0007515565,0.000939003,0.00261476],"genre_scores_gemma":[0.2031023,0.00007322283,0.7783819,0.0004300203,0.00008928202,0.0002835008,0.01395914,0.0001084526,0.003572183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9688596,"threshold_uncertainty_score":0.9997402,"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."}}