{"id":"W4382795963","doi":"10.1007/978-981-99-3157-6_11","title":"Learning Evaluation for Intelligence","year":2023,"lang":"en","type":"book-chapter","venue":"Advanced technologies and societal change","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Popularity; Quarter (Canadian coin); Field (mathematics); Artificial intelligence; Computer science; Data science; Psychology; History; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007189971,0.001132632,0.001416768,0.002000063,0.001020757,0.004260876,0.001722801,0.00165466,0.02605116],"category_scores_gemma":[0.02469172,0.0003049544,0.0005259283,0.001594708,0.002269559,0.006802495,0.001799438,0.002602306,0.005307322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003171431,"about_ca_system_score_gemma":0.001295982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001844335,"about_ca_topic_score_gemma":0.002329811,"domain_scores_codex":[0.9921328,0.003458061,0.0003208929,0.0009178139,0.002874087,0.0002963001],"domain_scores_gemma":[0.9905015,0.005549508,0.0002831283,0.00149145,0.001963212,0.0002111192],"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":[0.0001405091,0.0001025885,0.0006677698,0.0002614496,0.00004506648,0.00003423338,0.0001281738,0.01022193,0.0004377328,0.3420452,0.09071506,0.5552003],"study_design_scores_gemma":[0.00003375683,0.0001274654,0.00098066,0.0002858145,0.00003781156,0.0001169107,0.0001280799,0.1706747,0.001988304,0.7223601,0.1032304,0.00003601212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01400549,0.02296079,0.6202501,0.01263685,0.002864791,0.0004427815,0.001207534,0.00265473,0.3229769],"genre_scores_gemma":[0.4411041,0.005960281,0.2951024,0.002782317,0.003045583,0.0008788301,0.00349378,0.001418587,0.2462141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02605116,"threshold_uncertainty_score":0.0871498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1153400596369206,"score_gpt":0.3355145313406429,"score_spread":0.2201744717037222,"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."}}