{"id":"W2943859994","doi":"10.1142/s0218001420510131","title":"Functional Correlations in the Pursuit of Performance Assessment of Classifiers","year":2020,"lang":"en","type":"preprint","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Confusion; Association (psychology); Correlation; Artificial intelligence; Computer science; Machine learning; Mathematics; Psychology","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":[0.001010777,0.0001315216,0.000321607,0.0001929735,0.00002501333,0.00004345344,0.0003960758,0.00009433334,0.0001668817],"category_scores_gemma":[0.0006463035,0.0001013732,0.0001289383,0.00008120803,0.0001452293,0.0001063312,0.0001246466,0.0006288505,0.000001800278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004295787,"about_ca_system_score_gemma":0.000118633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009790768,"about_ca_topic_score_gemma":0.00001360473,"domain_scores_codex":[0.9976348,0.0001799341,0.001189662,0.0001520273,0.0007562838,0.00008724935],"domain_scores_gemma":[0.9968748,0.001149194,0.001111524,0.00008921182,0.0007298756,0.00004538842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002238866,0.000579587,0.001842375,0.0003165056,0.000236706,0.00003492061,0.001941616,0.003131929,0.001276801,0.04802361,0.0001262913,0.9422657],"study_design_scores_gemma":[0.0001073485,0.0001941373,0.004437325,0.0008395391,0.00008190971,0.00003995113,0.001114359,0.04410522,0.002334539,0.9465721,0.00004037351,0.0001331538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09108628,0.000026415,0.9059261,0.001525992,0.0008236388,0.0001441568,0.0001882707,0.000002847452,0.000276311],"genre_scores_gemma":[0.9537574,0.0002356301,0.04559823,0.0001440067,0.000214283,0.00000877319,0.00002790146,0.000008799781,0.000004942723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9421326,"threshold_uncertainty_score":0.413388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.474298146738228,"score_gpt":0.4775713525521258,"score_spread":0.003273205813897839,"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."}}