{"id":"W4400836543","doi":"10.20944/preprints202407.1257.v1","title":"A Closest Resemblance Classifier with Feature Interval Learning and Outranking Measures for Improved Performance","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Overfitting; Artificial intelligence; Computer science; Machine learning; Random forest; Support vector machine; Classifier (UML); Pattern recognition (psychology); Feature (linguistics); Robustness (evolution); Random subspace method; Pairwise comparison; Artificial neural network; Data mining","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00121945,0.0005244303,0.0005500437,0.0002835867,0.0002336788,0.0003700367,0.001776494,0.000445214,0.000006898654],"category_scores_gemma":[0.0002616315,0.000459471,0.0001371172,0.0002880594,0.0001689769,0.0003938004,0.003878248,0.002329689,0.00005124762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001822079,"about_ca_system_score_gemma":0.0002780698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002072119,"about_ca_topic_score_gemma":0.00002103363,"domain_scores_codex":[0.9965595,0.0001325671,0.0004539998,0.0019342,0.0003865937,0.0005331095],"domain_scores_gemma":[0.9973065,0.0001379494,0.0003986938,0.001663682,0.0003610376,0.0001321714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001306763,0.0004399828,0.482632,0.01058908,0.001453412,0.00006599629,0.01001787,0.0005090641,0.1951732,0.02782024,0.003271294,0.2667212],"study_design_scores_gemma":[0.00204965,0.0006817594,0.1938511,0.007411948,0.0003216305,0.0002084537,0.0002292523,0.2671996,0.3234738,0.02106071,0.1796484,0.003863673],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.454318,0.001403756,0.5203366,0.008257281,0.001464268,0.003989132,0.0001132119,0.004041615,0.006076114],"genre_scores_gemma":[0.9534082,0.0004572127,0.04228503,0.0001363385,0.000193809,0.0009059573,0.00005736934,0.00007619814,0.002479881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4990902,"threshold_uncertainty_score":0.999972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09348759723230013,"score_gpt":0.342511839297815,"score_spread":0.2490242420655149,"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."}}