{"id":"W2555801311","doi":"10.5220/0006033800210029","title":"Classification Confusion within Nefclass Caused by Feature Value Skewness in Multi-dimensional Datasets","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mount Allison University; University of Guelph","funders":"","keywords":"Confusion; Skewness; Feature (linguistics); Computer science; Value (mathematics); Pattern recognition (psychology); Artificial intelligence; Data mining; Statistics; Machine learning; Mathematics; Psychology; Linguistics","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":[0.0005714552,0.0002246064,0.0002050527,0.0001929696,0.0001029368,0.000110222,0.001216038,0.0002049671,0.00002544178],"category_scores_gemma":[0.0001537829,0.000151438,0.00003178163,0.0004825167,0.0001042164,0.001243546,0.0003407903,0.0001886091,0.000139261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001837092,"about_ca_system_score_gemma":0.0001281366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005983928,"about_ca_topic_score_gemma":0.00006507274,"domain_scores_codex":[0.9978371,0.0001856355,0.0003983461,0.000810441,0.0004461609,0.0003223353],"domain_scores_gemma":[0.9979815,0.0001748772,0.0002212169,0.001386213,0.0001134725,0.0001227427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001360397,0.0002383422,0.001249152,0.000008978449,0.000006926431,0.000007910515,0.00008617986,0.000004458837,0.6601064,0.1759913,0.1554481,0.006838585],"study_design_scores_gemma":[0.004583468,0.0001515118,0.1061664,0.0003289335,0.00001184213,0.00003538175,0.00005616022,0.2233805,0.5671266,0.008247298,0.08848599,0.001425844],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003925731,0.0000321123,0.9826102,0.01154881,0.000257497,0.0004333276,0.0004337336,0.0005886775,0.0001698553],"genre_scores_gemma":[0.7483239,0.00003940974,0.2442503,0.002605769,0.00003413896,0.0001631247,0.001368658,0.00003543928,0.003179191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7443982,"threshold_uncertainty_score":0.617546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03241016102305022,"score_gpt":0.2910278246572896,"score_spread":0.2586176636342394,"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."}}