{"id":"W4362681872","doi":"10.1109/csde56538.2022.10089291","title":"Novel Metrics for Evaluation and Validation of Regression-based Supervised Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; MNIST database; Consistency (knowledge bases); Regression; Random forest; Metric (unit); Regression analysis; Sample (material); Deep learning; Data mining; Statistics; 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":[0.04707249,0.002961561,0.001625139,0.005455729,0.001045083,0.002759734,0.002913344,0.002731893,0.0009917137],"category_scores_gemma":[0.1705247,0.0005169316,0.001541022,0.003277675,0.002784584,0.00385533,0.003370286,0.003556882,0.0006416872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001797143,"about_ca_system_score_gemma":0.002156144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003275044,"about_ca_topic_score_gemma":0.003626412,"domain_scores_codex":[0.9547685,0.01781123,0.006217586,0.006203927,0.01407311,0.000925598],"domain_scores_gemma":[0.8239037,0.1016028,0.02059075,0.02284281,0.02955195,0.001508052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00123305,0.0008441133,0.0901707,0.001696836,0.001861702,0.0003683978,0.0008602564,0.548924,0.0214604,0.01929448,0.01291545,0.3003707],"study_design_scores_gemma":[0.00007672814,0.0007889044,0.01943674,0.0002777835,0.0001432928,0.0003693475,0.0002585399,0.9305851,0.03244132,0.01069541,0.004773478,0.0001533248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1028295,0.002430636,0.8835945,0.0004153111,0.0003658152,0.0006453472,0.001867303,0.004668135,0.003183583],"genre_scores_gemma":[0.5881302,0.0005321023,0.4001359,0.0005523399,0.0002002172,0.001301375,0.006508909,0.001331667,0.001307309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04707249,"threshold_uncertainty_score":0.2489461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0586198536974564,"score_gpt":0.3268673302560574,"score_spread":0.2682474765586009,"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."}}