{"id":"W1516042217","doi":"10.1007/3-540-45153-6_1","title":"A Case Study for Learning from Imbalanced Data Sets","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Skew; Machine learning; Artificial intelligence; Rule induction; Quality (philosophy); Focus (optics); Data mining; Set (abstract data type); Variety (cybernetics); Training set","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001464077,0.0005971793,0.0006603533,0.0006528834,0.0004584725,0.0008841066,0.008369105,0.0003014752,0.00001542154],"category_scores_gemma":[0.0003372057,0.0005785472,0.00007939698,0.0006281859,0.0003664044,0.001346648,0.004166593,0.0009725435,0.00002387743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002844726,"about_ca_system_score_gemma":0.0004889936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002035277,"about_ca_topic_score_gemma":0.0003222198,"domain_scores_codex":[0.9945927,0.0000756158,0.000706483,0.003051849,0.0008786819,0.0006946958],"domain_scores_gemma":[0.9928198,0.001066883,0.0005162214,0.00510736,0.000321121,0.0001686072],"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":[0.00001014208,0.0001146312,0.0003414367,0.00001926958,0.00002869891,0.002037832,0.001218469,0.002263379,0.00009610532,0.001389996,0.0001878061,0.9922922],"study_design_scores_gemma":[0.0006518735,0.0004122335,0.00008413367,0.0001751931,0.00002326207,0.0009475803,0.000003141293,0.9391872,0.0002939793,0.0509522,0.006326633,0.0009425458],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002763933,0.0001445992,0.9956408,0.0003001814,0.0008974869,0.001455899,0.0001057104,0.0006179712,0.0005610019],"genre_scores_gemma":[0.2087847,0.00003472341,0.78964,0.0005820552,0.0004152734,0.00007093212,0.000226933,0.00005900059,0.0001863573],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9913497,"threshold_uncertainty_score":0.9996666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07340706613005715,"score_gpt":0.3196770846606314,"score_spread":0.2462700185305743,"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."}}