{"id":"W4393086187","doi":"10.1038/s41592-024-02234-5","title":"Comparing classifier performance with baselines","year":2024,"lang":"en","type":"article","venue":"Nature Methods","topic":"Statistical Methods and Applications","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Classifier (UML); Computer science; Computational biology; George (robot); Artificial intelligence; Biology","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":[0.001184871,0.0001293886,0.000207962,0.00006304812,0.00008117839,0.00006492875,0.0001276529,0.0001515666,0.0001096668],"category_scores_gemma":[0.000636091,0.00008276483,0.00004132766,0.0003864836,0.0000552113,0.00006004787,0.00003072391,0.0006938454,0.0000177553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002214261,"about_ca_system_score_gemma":0.00003191644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001324365,"about_ca_topic_score_gemma":0.000001843777,"domain_scores_codex":[0.9990547,0.0001881327,0.0001734695,0.0002553909,0.0001558149,0.0001725037],"domain_scores_gemma":[0.9965535,0.003020374,0.00002816952,0.0002677824,0.00006572724,0.00006447749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001308828,0.00002686292,0.0003106453,0.0002772859,0.00003914957,0.000005087815,0.00007964534,0.00000294417,0.0009600703,0.7283441,0.004736867,0.2652043],"study_design_scores_gemma":[0.0002651314,0.0000899766,0.0035235,0.0004364053,0.0002439676,0.00007060834,0.00008538629,0.1451939,0.01465826,0.4857141,0.3492481,0.0004706286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007052842,0.0007428768,0.9738845,0.0005388007,0.0002748363,0.0001426477,0.00000695513,0.0002274931,0.01712902],"genre_scores_gemma":[0.07566303,0.00001696846,0.9227279,0.0001257246,0.0002227885,0.00004821645,0.000002939039,0.00002838863,0.001163991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3445113,"threshold_uncertainty_score":0.3375052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1483906697713013,"score_gpt":0.5096182819771905,"score_spread":0.3612276122058892,"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."}}