{"id":"W4390906071","doi":"10.1007/s10994-023-06414-w","title":"Understanding imbalanced data: XAI & interpretable ML framework","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Class (philosophy); Deep learning; Focus (optics); Key (lock); Outlier; Set (abstract data type); Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.00983663,0.001259227,0.001362034,0.003394571,0.0009979117,0.005569299,0.003895729,0.00203926,0.007212304],"category_scores_gemma":[0.0418264,0.0008175491,0.001434623,0.002480729,0.002998597,0.006762307,0.00638959,0.005795203,0.002308895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002015585,"about_ca_system_score_gemma":0.002098256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002723748,"about_ca_topic_score_gemma":0.002741284,"domain_scores_codex":[0.9959677,0.001710824,0.0002082179,0.0007258177,0.001129535,0.0002577612],"domain_scores_gemma":[0.9860086,0.008598516,0.001120131,0.002184212,0.001682195,0.0004062269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002410929,0.0002118399,0.006457333,0.0003051315,0.0001476506,0.0004437292,0.0009012761,0.2376208,0.001892511,0.3846643,0.03307332,0.334041],"study_design_scores_gemma":[0.00001339799,0.00001759185,0.0003250655,0.00005344181,0.0000129933,0.00005933583,0.00007944109,0.7520838,0.000662263,0.2408735,0.005804778,0.00001444101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002040732,0.00021517,0.9927679,0.001523945,0.00005839688,0.00004649629,0.0003455016,0.001655078,0.001346784],"genre_scores_gemma":[0.2667902,0.0007436272,0.7226338,0.001307176,0.0007373204,0.0005600579,0.002114244,0.001083407,0.004030206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00983663,"threshold_uncertainty_score":0.05202168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.138257778875946,"score_gpt":0.3413448925674502,"score_spread":0.2030871136915041,"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."}}