{"id":"W4391127911","doi":"10.1007/s10994-023-06497-5","title":"Empirical analysis of performance assessment for imbalanced classification","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Machine learning; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0006608437,0.0001098201,0.0002252641,0.000476814,0.00009858361,0.0001301749,0.0005084097,0.00005464385,0.00001774563],"category_scores_gemma":[0.00007636415,0.00009833213,0.0001277267,0.001575593,0.00003018467,0.0003798237,0.00009610483,0.0001965219,0.000005518411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008525913,"about_ca_system_score_gemma":0.00006897278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005158606,"about_ca_topic_score_gemma":0.000002404414,"domain_scores_codex":[0.9987916,0.00007597259,0.0003221052,0.0004027307,0.0002345013,0.0001730865],"domain_scores_gemma":[0.9990535,0.0002341208,0.0001255892,0.0004541644,0.00009603596,0.00003652575],"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":[0.00002011132,0.0001420359,0.3650208,0.0003686534,0.0007687629,0.000002430708,0.000970721,0.007109936,0.04656546,0.1615127,0.001520892,0.4159975],"study_design_scores_gemma":[0.00006167423,0.00007099031,0.1288364,0.00001801263,0.00007347651,8.269856e-7,0.000006957651,0.8422994,0.001633587,0.0001761679,0.02672972,0.00009273946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01192235,0.00009733842,0.9847929,0.001092578,0.00009992925,0.0001656775,0.00001717364,0.0005798422,0.001232197],"genre_scores_gemma":[0.8673596,0.00003926843,0.1319536,0.00005645655,0.00002256784,0.00008065172,0.000181885,0.000009805745,0.0002961593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8554372,"threshold_uncertainty_score":0.4009868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0385424843247923,"score_gpt":0.3639158091002024,"score_spread":0.3253733247754101,"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."}}