{"id":"W115533587","doi":"10.1007/978-3-642-30353-1_30","title":"Mining the Hidden Structure of Inductive Learning Data Sets","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Cluster analysis; Curse of dimensionality; Visualization; Machine learning; Domain (mathematical analysis); Variety (cybernetics); Process (computing); Class (philosophy); Data mining; Pattern recognition (psychology); Mathematics","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":[0.001080116,0.0004210261,0.0004562144,0.0004982699,0.0002766468,0.0002956504,0.01039829,0.0003230785,0.000023115],"category_scores_gemma":[0.0002958246,0.000310508,0.00005513986,0.0006639596,0.001004966,0.001464812,0.005343677,0.001241873,0.000009016763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001617688,"about_ca_system_score_gemma":0.0004485416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002266307,"about_ca_topic_score_gemma":0.00003126063,"domain_scores_codex":[0.9964565,0.00009062765,0.000542762,0.00135067,0.001021304,0.0005381063],"domain_scores_gemma":[0.9943174,0.0006690514,0.0007171374,0.003927879,0.0002728261,0.00009577163],"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":[0.000002295868,0.00001018446,0.0002071977,0.00002373541,0.00001423692,0.000004878962,0.001607397,0.000449003,0.001314727,0.01246177,0.00008155927,0.983823],"study_design_scores_gemma":[0.0005507007,0.0003836497,0.003581949,0.001371432,0.00007384687,0.0002991593,0.000007604913,0.650172,0.04598125,0.270817,0.02413267,0.002628747],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002312133,0.0005002102,0.9965992,0.0006075052,0.0007935161,0.0003532288,0.00004541215,0.0001733987,0.0006963319],"genre_scores_gemma":[0.3719559,0.00004586184,0.6271897,0.000356928,0.0002985117,0.000003207507,0.00005924834,0.00002891049,0.00006168365],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9811943,"threshold_uncertainty_score":0.9999347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04681161006848464,"score_gpt":0.2897300678363297,"score_spread":0.2429184577678451,"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."}}