{"id":"W3207601856","doi":"10.1038/s41592-021-01302-4","title":"The class imbalance problem","year":2021,"lang":"en","type":"article","venue":"Nature Methods","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Class (philosophy); Computational biology; Computer science; Biology; Chemistry; Artificial intelligence","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":[0.008079479,0.001320605,0.001937911,0.002770375,0.002218923,0.004705153,0.002815435,0.00325899,0.005627441],"category_scores_gemma":[0.02939067,0.0007376373,0.001395862,0.003267115,0.002314137,0.006263892,0.003822938,0.005574533,0.002771192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001232632,"about_ca_system_score_gemma":0.00153258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006840087,"about_ca_topic_score_gemma":0.0006953332,"domain_scores_codex":[0.9886464,0.003408674,0.0004466336,0.002840033,0.00424651,0.0004117694],"domain_scores_gemma":[0.9827659,0.01084167,0.001362412,0.002627604,0.001967031,0.0004355209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002605738,0.0002230535,0.006433096,0.000597191,0.0002735753,0.0003465239,0.0003109282,0.01676417,0.003162766,0.2504852,0.09247631,0.6286667],"study_design_scores_gemma":[0.00007354764,0.0001172841,0.003758243,0.0002222251,0.0001278027,0.001676475,0.0002803028,0.2131863,0.005262394,0.6668453,0.1083855,0.00006467552],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0133427,0.006339598,0.9433529,0.008021293,0.00241732,0.0002650016,0.0009775934,0.0006976541,0.02458594],"genre_scores_gemma":[0.4651839,0.01092945,0.4414906,0.008034532,0.01424857,0.001470771,0.004920753,0.0006609972,0.05306039],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008079479,"threshold_uncertainty_score":0.0427289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01395549485720575,"score_gpt":0.3723376864885252,"score_spread":0.3583821916313195,"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."}}