{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008235553,0.0001906677,0.0001931984,0.0002123107,0.000232787,0.000984968,0.001991584,0.0001040031,0.0001083656],"category_scores_gemma":[0.0004777203,0.0001788243,0.00004451552,0.0007616716,0.00004892865,0.001487138,0.001235354,0.0008586929,0.0002820563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001960799,"about_ca_system_score_gemma":0.0000627634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000364906,"about_ca_topic_score_gemma":0.00001454529,"domain_scores_codex":[0.9981203,0.0001369618,0.0002743007,0.0008033075,0.0003033802,0.0003617276],"domain_scores_gemma":[0.9978846,0.0003652968,0.00008102619,0.001566554,0.00002491175,0.00007766645],"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":[0.00001199718,0.00004831285,0.00474761,0.0001878003,0.0001007246,0.00005380204,0.002120903,0.0007716095,0.005558932,0.9098765,0.03043951,0.04608225],"study_design_scores_gemma":[0.00006270727,0.00002771466,0.0001446939,0.0002786042,0.000008681578,0.00002698992,0.00002850601,0.6696479,0.0002721084,0.03169284,0.2975399,0.0002693991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001204861,0.0007508159,0.988619,0.002149554,0.000597755,0.0001166661,0.0000239432,0.002739631,0.004882169],"genre_scores_gemma":[0.7488422,0.0001103476,0.2487443,0.0003120111,0.0001320426,0.00001534901,0.0002437787,0.00003440879,0.001565578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8781837,"threshold_uncertainty_score":0.9498069,"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."}}