{"id":"W2416463881","doi":"","title":"Honest assessments of automatic learning algorithm performance.","year":2000,"lang":"en","type":"article","venue":"PubMed","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Variance (accounting); Machine learning; Task (project management); Algorithm; Artificial intelligence; Probabilistic logic; Data mining","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":[0.1350684,0.001248347,0.0008725738,0.003189565,0.001064048,0.002876834,0.001721347,0.002810157,0.003417748],"category_scores_gemma":[0.4447562,0.0004615856,0.001350341,0.001551079,0.003116644,0.004209439,0.003181739,0.001694024,0.001400676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00115598,"about_ca_system_score_gemma":0.001088683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003414649,"about_ca_topic_score_gemma":0.0005948713,"domain_scores_codex":[0.8619945,0.08825366,0.01152762,0.008823855,0.02846732,0.0009331219],"domain_scores_gemma":[0.4020756,0.4803919,0.03272003,0.04038485,0.04282417,0.001603324],"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":[0.01317641,0.001229765,0.230269,0.004431756,0.003824774,0.0002929213,0.004077495,0.05633103,0.0224019,0.01515682,0.01156818,0.63724],"study_design_scores_gemma":[0.002052054,0.02391542,0.4098297,0.002088528,0.001988042,0.00330445,0.002559222,0.33807,0.1298916,0.05361837,0.03167039,0.001012205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5022005,0.008453839,0.4575241,0.001772995,0.001064976,0.001997555,0.001808498,0.001878579,0.02329889],"genre_scores_gemma":[0.8731021,0.0004977607,0.1211329,0.0005095482,0.0002558243,0.001092089,0.001128913,0.0003015971,0.001979299],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1350684,"threshold_uncertainty_score":0.7143185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01461906660654779,"score_gpt":0.2286218472149917,"score_spread":0.2140027806084439,"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."}}