{"id":"W4385849703","doi":"10.5281/zenodo.8252499","title":"Supplementary Information for: Reducing Training Data Needs with Minimal Multilevel Machine Learning (M3L)","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Training (meteorology); Computer science; Machine learning; Artificial intelligence; Training set; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001713858,0.002950752,0.002119745,0.002006302,0.0008786659,0.00236096,0.003949762,0.001615134,0.7959443],"category_scores_gemma":[0.01823646,0.001440521,0.001509848,0.002840769,0.0004866004,0.002309485,0.002066386,0.002276198,0.4218875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001052452,"about_ca_system_score_gemma":0.001979761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003945887,"about_ca_topic_score_gemma":0.009605813,"domain_scores_codex":[0.9987902,0.000212322,0.0001519905,0.0003299802,0.0003755527,0.0001399148],"domain_scores_gemma":[0.9908117,0.0055613,0.0003222966,0.0014394,0.001392226,0.0004730485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002409789,0.0000958186,0.0003629091,0.001014352,0.00004020956,0.00005724505,0.00002993997,0.0014949,0.001361845,0.002314892,0.9723737,0.02061316],"study_design_scores_gemma":[0.001833235,0.000301973,0.003399271,0.0007707998,0.0001352637,0.0004007901,0.0001278531,0.03428918,0.01998958,0.04807556,0.890399,0.0002775144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0009612597,0.0001825755,0.03147919,0.000437851,0.0006765684,0.0001678594,0.917959,0.04075813,0.007377512],"genre_scores_gemma":[0.01005589,0.0002744574,0.09111503,0.0008237385,0.0002945885,0.001364786,0.8378338,0.04679397,0.01144383],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7959443,"threshold_uncertainty_score":0.2910607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3082396181610623,"score_gpt":0.4235564814636357,"score_spread":0.1153168633025735,"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."}}