{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00176177,0.00005035152,0.00007222422,0.0001901128,0.0002368316,0.00003916961,0.0002055136,0.00001635188,0.00004801567],"category_scores_gemma":[0.0007168973,0.00004502609,0.00002251812,0.0004542863,0.000009003073,0.0001545617,0.00009672559,0.00008433616,4.95149e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003237895,"about_ca_system_score_gemma":0.00007968384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003141282,"about_ca_topic_score_gemma":6.503994e-7,"domain_scores_codex":[0.9990312,0.0001578878,0.0001502315,0.0002108351,0.0003783306,0.00007152238],"domain_scores_gemma":[0.9991223,0.0003578981,0.0001328971,0.0002091985,0.0001542473,0.00002351042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000711652,0.0003183841,0.02449007,0.0001135961,0.00002001856,1.572776e-7,0.0009571876,0.1403383,0.06264071,0.05736047,0.0009220889,0.7127678],"study_design_scores_gemma":[0.0007940807,0.0001221342,0.003172532,0.000003290778,0.000008794806,8.000728e-7,0.00007061271,0.9888697,0.004316795,0.0002583701,0.002326122,0.00005676673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03983379,0.00004690532,0.9584715,0.0009205036,0.0000789708,0.0002294849,0.000005061208,0.00005647007,0.0003573434],"genre_scores_gemma":[0.9091454,0.000001406147,0.0904277,0.00006220881,0.000008734402,0.0000714151,0.0001631053,0.000003967812,0.0001161285],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8693116,"threshold_uncertainty_score":0.1836111,"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."}}