{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003356242,0.00005323685,0.0001072045,0.00002775839,0.00004397467,0.00003202354,0.0001917438,0.0001150749,0.000004149813],"category_scores_gemma":[0.00005425863,0.00004350908,0.00003653854,0.0004922043,0.00003769936,0.00005980936,0.0001364592,0.0003566534,1.337509e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005051105,"about_ca_system_score_gemma":0.00004148314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.703387e-7,"about_ca_topic_score_gemma":0.00000179741,"domain_scores_codex":[0.9993231,0.0001633538,0.00009948212,0.0002159788,0.0001075491,0.00009058088],"domain_scores_gemma":[0.9991896,0.0003392523,0.00003918811,0.000306931,0.00007168118,0.00005331782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[3.73942e-7,0.00003500499,0.002088112,0.000009236032,0.0000103994,0.000005960732,0.00001701043,0.000009265216,0.03462324,0.7455025,0.0009242569,0.2167747],"study_design_scores_gemma":[0.0005185557,0.00009545366,0.5140406,0.0000486394,0.00003457131,0.0001149096,0.0000236055,0.1203405,0.04196933,0.2013337,0.1210871,0.0003930383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004275158,0.0009393663,0.9881334,0.003769472,0.0002003103,0.00004670259,9.368077e-7,0.00002982683,0.00260485],"genre_scores_gemma":[0.2694781,0.0000477917,0.7299666,0.0004146195,0.00002611985,0.000004475403,7.133123e-7,0.000002029973,0.00005952493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5441688,"threshold_uncertainty_score":0.1774249,"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."}}