{"id":"W2125722086","doi":"10.1007/978-3-540-78671-9_23","title":"GP Classification under Imbalanced Data sets: Active Sub-sampling and AUC Approximation","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association","keywords":"Computer science; Artificial intelligence; Machine learning; Statistic; Classifier (UML); Binary classification; Estimator; Naive Bayes classifier; Boosting (machine learning); Support vector machine; Mathematics; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.0008621073,0.0005398377,0.0005020737,0.000785378,0.00040696,0.0005863931,0.004754582,0.0004166956,0.000003892559],"category_scores_gemma":[0.0001838173,0.0005330083,0.00004832722,0.0006792275,0.0009076613,0.002467187,0.002416795,0.0008302116,0.00002212876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004732983,"about_ca_system_score_gemma":0.0005580834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001424137,"about_ca_topic_score_gemma":0.00002708635,"domain_scores_codex":[0.9952855,0.00005922993,0.0006440048,0.002480478,0.0009756855,0.000555154],"domain_scores_gemma":[0.9947,0.0005121903,0.0006214739,0.003688469,0.0003233424,0.0001545677],"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":[0.00001020173,0.00003992588,0.00004449216,0.00004948821,0.00001571656,0.00000953705,0.0005400014,0.001000192,0.003224983,0.02615987,0.0001636752,0.9687419],"study_design_scores_gemma":[0.0003056068,0.00008081693,0.003589903,0.0003205515,0.00001143223,0.0001225103,9.063448e-7,0.8934623,0.00651915,0.09240349,0.002272509,0.0009108405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001196426,0.0002837178,0.9957755,0.001323415,0.0005220751,0.000668312,0.00007855699,0.0004664354,0.0007622953],"genre_scores_gemma":[0.1282294,0.0008906479,0.868889,0.001125953,0.0002536461,0.00003668603,0.0004591471,0.00005401011,0.00006152307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9678311,"threshold_uncertainty_score":0.9997122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07612656226787208,"score_gpt":0.3049186266414283,"score_spread":0.2287920643735562,"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."}}