{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004094248,0.0002130397,0.0002163122,0.0001204014,0.0002505546,0.00008389942,0.0005072238,0.0003552275,0.00000313258],"category_scores_gemma":[0.0003221995,0.0002028899,0.00008852741,0.00008689408,0.0001100188,0.0002919194,0.0004286118,0.0004383996,0.00002815778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005435691,"about_ca_system_score_gemma":0.00002082677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002785254,"about_ca_topic_score_gemma":0.000007374129,"domain_scores_codex":[0.9987755,0.00001040669,0.000183555,0.0005742906,0.0002420489,0.0002142387],"domain_scores_gemma":[0.9990226,0.0001740438,0.0002182855,0.000434152,0.0001289628,0.00002197419],"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":[0.000001128986,0.00000159996,0.000002378723,0.00003498327,0.000009458078,4.562883e-7,0.0001593895,0.00001234286,0.00001344158,0.2942324,0.00006654691,0.7054659],"study_design_scores_gemma":[0.000223667,0.0004795222,0.00006979646,0.0002137616,0.00004974196,0.000005491296,0.001105278,0.1159133,0.0001131378,0.6235907,0.2576081,0.0006274481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0001900908,0.01963463,0.8693165,0.01987885,0.001945995,0.005357195,0.0001288722,0.01674676,0.06680114],"genre_scores_gemma":[0.1319511,0.08517685,0.1903614,0.0005255127,0.0006479616,0.004260033,0.001830473,0.0003746959,0.5848719],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7048384,"threshold_uncertainty_score":0.8273608,"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."}}