{"id":"W138034719","doi":"","title":"Constructing new and better evaluation measures for machine learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Ottawa","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Measure (data warehouse); Construct (python library); Artificial neural network; Greedy algorithm; Mean squared error; Data mining; Algorithm; 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":[0.001942638,0.0000622315,0.00006309541,0.00006900593,0.0001339861,0.000117025,0.0001337243,0.0000307892,0.00001652117],"category_scores_gemma":[0.0004926905,0.00005355402,0.00001594916,0.00009726969,0.00001425763,0.0003294561,0.0000468445,0.00009969679,0.000005238767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002147928,"about_ca_system_score_gemma":0.0000320645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001091313,"about_ca_topic_score_gemma":0.00009194275,"domain_scores_codex":[0.9992604,0.00004976451,0.0001363547,0.0002236855,0.0001947723,0.0001350812],"domain_scores_gemma":[0.9994233,0.00021812,0.00007053569,0.0001502854,0.00007693766,0.00006084505],"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":[0.000003329712,0.000002586478,0.02248413,0.000003451474,0.000003717625,1.085432e-7,0.00010393,0.00001968038,0.0004968246,0.03472172,0.0001996606,0.9419609],"study_design_scores_gemma":[0.0007968988,0.0000683078,0.02443466,0.0000100579,0.00001521911,0.00002268935,0.0001086173,0.925386,0.001647767,0.00508101,0.04225826,0.0001705897],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00821802,0.0001251092,0.9840258,0.002884514,0.00009053011,0.0001378485,4.201192e-7,0.0001209721,0.004396837],"genre_scores_gemma":[0.6986954,0.000003108627,0.3002826,0.000334531,0.0001047518,0.000003640098,0.00002627235,0.000005012618,0.0005447525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9417903,"threshold_uncertainty_score":0.218387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04615306708286241,"score_gpt":0.3140166668024245,"score_spread":0.267863599719562,"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."}}