{"id":"W2270983878","doi":"10.5430/air.v5n1p135","title":"Cost-sensitive performance metric for comparing multiple ordinal classifiers","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Food and Drug Administration; National Institutes of Health","keywords":"Pairwise comparison; Classifier (UML); Computer science; Metric (unit); Ordinal data; Data mining; Machine learning; Artificial intelligence; Ordinal optimization; Performance metric","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003127733,0.0001752659,0.0002405246,0.00076044,0.0005544286,0.0002801591,0.001674029,0.000112477,0.00001783204],"category_scores_gemma":[0.002261718,0.0001334582,0.00008127392,0.001906872,0.0004636693,0.001054873,0.0004756748,0.0003065764,0.0005352576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003621986,"about_ca_system_score_gemma":0.0002119647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004782954,"about_ca_topic_score_gemma":0.00004372841,"domain_scores_codex":[0.9967325,0.0002436684,0.0004952835,0.0007715583,0.0007948175,0.0009621439],"domain_scores_gemma":[0.995475,0.002088413,0.0001108308,0.00096825,0.001153195,0.0002043266],"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":[0.00008387272,0.00008421453,0.001285463,0.00001674512,0.00001236281,0.000003288978,0.0002310023,0.00002128485,0.0318733,0.1573969,0.001174401,0.8078172],"study_design_scores_gemma":[0.00006902255,0.0002481835,0.001110756,0.00006926871,0.000002323055,0.000006389032,0.0002931334,0.2217363,0.7543113,0.01549713,0.00641107,0.0002451551],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01337911,0.00002035751,0.9816271,0.002485919,0.0002325076,0.0009996715,0.00001798144,0.0002920254,0.0009453247],"genre_scores_gemma":[0.9513673,0.00008404741,0.0476767,0.00004605389,0.000124348,0.0003871778,0.000006741193,0.00001826252,0.0002893686],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9379882,"threshold_uncertainty_score":0.6879832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4412564894946245,"score_gpt":0.4524121439856832,"score_spread":0.01115565449105876,"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."}}