{"id":"W4376460741","doi":"10.1007/978-3-031-29937-7_10","title":"A Tutorial of Analyzing Accuracy in Conceptual Change","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in big data","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Variance (accounting); Statistical model; Statistics; Logistic regression; Econometrics; Artificial intelligence; Machine learning; 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":[0.002224693,0.001181547,0.0008153559,0.003204242,0.00063816,0.002681798,0.001082866,0.001050603,0.03472866],"category_scores_gemma":[0.01043878,0.0005818734,0.0007681125,0.005185493,0.001686746,0.007312166,0.001100575,0.002349909,0.01168085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001851666,"about_ca_system_score_gemma":0.001166499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002828394,"about_ca_topic_score_gemma":0.004549229,"domain_scores_codex":[0.99907,0.0004335757,0.0000497833,0.0001025813,0.0003082974,0.00003581321],"domain_scores_gemma":[0.991572,0.007151478,0.0001214422,0.0003131424,0.0007601901,0.00008182735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001053394,0.00003045965,0.0004115391,0.0003880162,0.00002525439,0.00007221376,0.0005984702,0.002128431,0.0002706778,0.5667378,0.191386,0.2379406],"study_design_scores_gemma":[0.000002908331,0.00001056944,0.0006393554,0.0003342979,0.00001618002,0.0001424092,0.000187406,0.004351321,0.0003291939,0.6427544,0.351215,0.0000169479],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001904122,0.04830475,0.6573406,0.0115517,0.003555496,0.00009257221,0.001471907,0.00186311,0.2739158],"genre_scores_gemma":[0.06058647,0.05244729,0.4142292,0.005650651,0.005105665,0.0006150332,0.003491525,0.003349787,0.4545244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03472866,"threshold_uncertainty_score":0.1161789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9221514815937679,"score_gpt":0.5738906529598677,"score_spread":0.3482608286339002,"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."}}