{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00479068,0.0008965253,0.001222913,0.003062296,0.0007493807,0.002136772,0.002660547,0.0009835309,0.001400181],"category_scores_gemma":[0.02029542,0.0008180057,0.001587924,0.002420877,0.001552969,0.00485366,0.002928101,0.002729339,0.0008065366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000891359,"about_ca_system_score_gemma":0.001309009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000529818,"about_ca_topic_score_gemma":0.001009788,"domain_scores_codex":[0.9971609,0.0008797232,0.0002601449,0.0005526165,0.0009573309,0.0001893112],"domain_scores_gemma":[0.9825457,0.01277605,0.001193904,0.002159744,0.001116337,0.0002082653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002942688,0.0004893386,0.02673502,0.001163993,0.0003638676,0.0004674916,0.00131875,0.07563411,0.01041629,0.07956307,0.008423484,0.7951304],"study_design_scores_gemma":[0.000031274,0.0001183293,0.003623724,0.0002994262,0.0001111631,0.0002279646,0.0002829311,0.6661265,0.008665985,0.3159276,0.004546874,0.00003810133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06264909,0.00100396,0.9322869,0.0007559113,0.00008025341,0.0001319604,0.0008868421,0.0005878981,0.001617225],"genre_scores_gemma":[0.4073933,0.001536241,0.5810336,0.0002995279,0.0003471726,0.0004394352,0.005870045,0.0001449973,0.00293568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00479068,"threshold_uncertainty_score":0.02533585,"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."}}