{"id":"W1566313113","doi":"10.3233/ida-140686","title":"Hybrid probabilistic sampling with random subspace for imbalanced data learning","year":2014,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; China Scholarship Council","keywords":"Subspace topology; Probabilistic logic; Sampling (signal processing); Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002186187,0.0002541456,0.0005280615,0.0003498665,0.0002377474,0.0004890584,0.007184432,0.00004802144,0.00001394557],"category_scores_gemma":[0.002894549,0.0002097933,0.00008381191,0.001155706,0.00009121896,0.0013171,0.001747645,0.0002092223,0.00003287746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006322006,"about_ca_system_score_gemma":0.00007070463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007258933,"about_ca_topic_score_gemma":0.0001229576,"domain_scores_codex":[0.9968399,0.0001819621,0.0005054117,0.001619042,0.0004367183,0.0004169095],"domain_scores_gemma":[0.9901934,0.0009276264,0.0003759363,0.007991597,0.0003881595,0.0001232773],"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":[0.0008452552,0.001024277,0.03448427,0.000565801,0.008448068,0.00001811516,0.0007685627,0.08135494,0.002722771,0.09839477,0.04793306,0.7234401],"study_design_scores_gemma":[0.0002867813,0.00006727901,0.0002435883,0.00002404122,0.0005120763,0.000002127702,0.000019808,0.8882022,0.001882525,0.0013096,0.1071528,0.0002972297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003462285,0.00007415733,0.9974277,0.0004374546,0.00007589365,0.0004671803,0.0006117253,0.0004650526,0.00009462376],"genre_scores_gemma":[0.3211091,0.0001392245,0.6562586,0.0001805843,0.0001476616,0.0001060828,0.02184737,0.00003237735,0.0001789168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8068472,"threshold_uncertainty_score":0.9981872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08624709222993643,"score_gpt":0.333776344110833,"score_spread":0.2475292518808965,"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."}}