{"id":"W2001536048","doi":"10.1109/icmla.2012.144","title":"A Dynamic Sampling Framework for Multi-class Imbalanced Data","year":2012,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Sampling (signal processing); Computer science; Classifier (UML); Data mining; Machine learning; Oversampling; Artificial intelligence; Class (philosophy); Set (abstract data type); Sampling distribution; Training set; Pattern recognition (psychology); Bandwidth (computing); Mathematics; Statistics","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":[0.0005893592,0.000148182,0.0001626463,0.0000787353,0.0001258398,0.0001465301,0.002896677,0.0001157314,0.00001379022],"category_scores_gemma":[0.0004462308,0.0001339922,0.00003615517,0.000275784,0.00003639978,0.001700933,0.0008699223,0.0001490242,0.00007428631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006505416,"about_ca_system_score_gemma":0.00004153237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005860725,"about_ca_topic_score_gemma":0.000004438057,"domain_scores_codex":[0.9985403,0.00002863144,0.0002578894,0.0005065174,0.0001746054,0.0004920057],"domain_scores_gemma":[0.9965461,0.0002791991,0.0001240679,0.002855259,0.00007478534,0.0001205226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005925904,0.0002039489,0.0008508606,0.00003144227,0.00002085291,2.08597e-7,0.0001930562,0.000003848513,0.004796364,0.9327622,0.004870106,0.05626117],"study_design_scores_gemma":[0.0003449099,0.00002853243,0.005049469,0.00003792123,0.000008368096,0.000007786636,0.00003750903,0.9092165,0.004374166,0.01491747,0.06556634,0.0004110017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001279527,0.000108351,0.9966996,0.0008764361,0.0004347588,0.000409202,0.0001103375,0.001000583,0.0002327777],"genre_scores_gemma":[0.1173407,0.00001933811,0.8814121,0.0006701392,0.0000579332,0.00009698066,0.0001906775,0.00001579833,0.0001963472],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9178447,"threshold_uncertainty_score":0.5464044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1637551525145151,"score_gpt":0.401709392639956,"score_spread":0.2379542401254409,"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."}}