{"id":"W4313421210","doi":"10.1007/s10994-022-06268-8","title":"The class imbalance problem in deep learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; National Research Council Canada; University of Alberta","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Machine learning; Class (philosophy); Context (archaeology)","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":[0.001594122,0.0001366829,0.000138481,0.00013024,0.001227841,0.0002133822,0.001556248,0.00002933665,0.0000339925],"category_scores_gemma":[0.0002161822,0.000117784,0.00004187259,0.0008189601,0.00004274244,0.000287173,0.001078749,0.001330353,0.00002558936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804565,"about_ca_system_score_gemma":0.00003920694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007687417,"about_ca_topic_score_gemma":0.00004413929,"domain_scores_codex":[0.9977947,0.000683082,0.0002989678,0.000421414,0.0003990731,0.0004028009],"domain_scores_gemma":[0.9989344,0.000276936,0.0002117651,0.000503498,0.00003239681,0.00004094506],"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":[0.00003796087,0.0001318572,0.2537819,0.00002802194,0.00002185796,0.00006463336,0.003214826,0.1116962,0.005872093,0.157999,0.001389754,0.4657619],"study_design_scores_gemma":[0.0001943378,0.00009053003,0.008757674,0.00000590597,9.981333e-7,0.00002240645,0.0001248601,0.60501,0.0001643542,0.001644659,0.3838211,0.0001631786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01687898,0.002367247,0.9346989,0.0142694,0.0005359176,0.0009831137,0.000005267758,0.003266586,0.02699455],"genre_scores_gemma":[0.9791753,0.00007677604,0.01763399,0.0002723296,0.00002787327,0.0002595936,0.00002543767,0.000021608,0.002507115],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622963,"threshold_uncertainty_score":0.9443681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007893058798280584,"score_gpt":0.2351205030355744,"score_spread":0.2272274442372938,"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."}}