{"id":"W3184573320","doi":"10.1038/s41592-021-01232-1","title":"Graphical assessment of tests and classifiers","year":2021,"lang":"en","type":"article","venue":"Nature Methods","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","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":[0.01389783,0.001556976,0.001522554,0.006998193,0.0007170307,0.004898609,0.0028425,0.003013354,0.0161527],"category_scores_gemma":[0.1200446,0.0005733201,0.001861364,0.002472509,0.002314526,0.004427897,0.002759799,0.002264601,0.003496065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001579641,"about_ca_system_score_gemma":0.001458771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001882985,"about_ca_topic_score_gemma":0.001939797,"domain_scores_codex":[0.9766717,0.01357352,0.0009154794,0.002673393,0.005394701,0.0007712091],"domain_scores_gemma":[0.8812075,0.08775061,0.005122596,0.01072703,0.01377665,0.001415637],"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":[0.001780348,0.0003955281,0.03033627,0.001039943,0.0006281963,0.0004782532,0.0004006258,0.1543302,0.007181788,0.199779,0.03287607,0.5707737],"study_design_scores_gemma":[0.0001253841,0.0002961339,0.007121839,0.0002006264,0.0001777458,0.0002320213,0.0001328812,0.6648722,0.006097836,0.3131311,0.007543442,0.00006868788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02864801,0.0006775467,0.9525214,0.001374856,0.0002651902,0.0002347043,0.001944965,0.003367131,0.0109661],"genre_scores_gemma":[0.775031,0.0004552643,0.2119137,0.0006986532,0.0004503763,0.0005741939,0.004074979,0.000884269,0.00591751],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0161527,"threshold_uncertainty_score":0.07349968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02148692106232721,"score_gpt":0.431169260004915,"score_spread":0.4096823389425878,"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."}}