{"id":"W1520065212","doi":"10.1007/11871842_16","title":"Evaluating Misclassifications in Imbalanced Data","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Classifier (UML); Artificial intelligence; Confidence interval; Pattern recognition (psychology); Class (philosophy); Computer science; Machine learning; Statistics; Mathematics","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002355254,0.0005391503,0.0005632251,0.001301996,0.0002216292,0.0006499742,0.0111762,0.0003655259,0.00001607285],"category_scores_gemma":[0.0003722066,0.0005453579,0.00006304822,0.001273576,0.000649464,0.001486419,0.003320976,0.001030739,0.00006084747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006046802,"about_ca_system_score_gemma":0.001027331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006956494,"about_ca_topic_score_gemma":0.0002314512,"domain_scores_codex":[0.9941157,0.00007921199,0.0009879121,0.002773762,0.001293442,0.0007500474],"domain_scores_gemma":[0.9921114,0.0006030814,0.0005519406,0.006334033,0.000283493,0.0001160684],"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":[0.000004236292,0.0000886862,0.000240977,0.00004638769,0.000006760084,0.00004510794,0.0002005944,0.01312194,0.00216791,0.03993151,0.0008286773,0.9433172],"study_design_scores_gemma":[0.0002639717,0.00006078196,0.00139664,0.0003527728,0.0000050202,0.00002493938,9.859999e-8,0.896128,0.00118863,0.09670936,0.003206053,0.0006637413],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002196894,0.0002734618,0.9899546,0.001547404,0.000667181,0.0006429614,0.00006627142,0.0004008782,0.006425297],"genre_scores_gemma":[0.04483546,0.00005005103,0.9531062,0.0007101952,0.000287512,0.00004388829,0.0002840322,0.00004604004,0.0006366135],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9426535,"threshold_uncertainty_score":0.9996998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0892702449882283,"score_gpt":0.3475017225279319,"score_spread":0.2582314775397035,"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."}}