{"id":"W1998167404","doi":"10.1136/bmj.328.7450.1240","title":"Review of instruments for peer assessment of physicians","year":2004,"lang":"en","type":"review","venue":"BMJ","topic":"Innovations in Medical Education","field":"Medicine","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Snowball sampling; Psychology; Reliability (semiconductor); Inclusion (mineral); Construct validity; Construct (python library); Rating scale; Validity; Medical education; MEDLINE; Applied psychology; Psychometrics; Medicine; Clinical psychology; Computer science; Social psychology","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":[0.0008870625,0.0001480357,0.001446831,0.0001236925,0.00001325146,0.000001292798,0.0001196274,0.0001287816,0.00009219946],"category_scores_gemma":[0.001164451,0.0001151107,0.0003401812,0.0004482742,0.00005711518,0.00002001771,0.00002148,0.0001926472,0.00000524463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002388121,"about_ca_system_score_gemma":0.001665861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003779822,"about_ca_topic_score_gemma":8.359908e-8,"domain_scores_codex":[0.9981281,0.00003290288,0.001097481,0.0001569181,0.0004757582,0.0001088509],"domain_scores_gemma":[0.9978354,0.00003841631,0.0009786456,0.000431572,0.0007005922,0.00001538109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[4.963699e-7,0.0001219216,0.000001418298,0.3814144,0.00008206852,1.151624e-7,0.000005528375,1.207206e-8,1.365535e-7,0.0005612011,0.05290689,0.5649058],"study_design_scores_gemma":[0.0001583254,0.00006758894,0.00001073128,0.3830335,0.000859661,0.000006054013,0.000005595153,0.000001061473,0.000001242657,0.00002107876,0.6157858,0.00004943228],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001296419,0.9908979,0.0003562966,0.001823787,0.0005157455,0.003447795,0.00004410625,0.000007653651,0.002905439],"genre_scores_gemma":[0.000001599375,0.9741449,0.02235507,0.001042665,0.0002981859,0.0005549183,0.0009031242,0.00002631913,0.0006731953],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5648564,"threshold_uncertainty_score":0.4694077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08450779594144721,"score_gpt":0.5199320443232025,"score_spread":0.4354242483817553,"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."}}