{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1008096,0.00190525,0.008812129,0.02499807,0.001453639,0.005017176,0.00425447,0.002344757,0.00406388],"category_scores_gemma":[0.3739631,0.001478289,0.006576895,0.0195485,0.002375725,0.005660977,0.003431269,0.001828655,0.0006985448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005897322,"about_ca_system_score_gemma":0.02285904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004068232,"about_ca_topic_score_gemma":0.01010649,"domain_scores_codex":[0.851573,0.07112639,0.04051942,0.002864767,0.03281444,0.001102027],"domain_scores_gemma":[0.6429651,0.2430693,0.05217781,0.00573198,0.05454684,0.001508983],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002900983,0.00005181917,0.002351678,0.6388522,0.003950293,0.00008443018,0.0007767447,0.0001564787,0.0001085417,0.0007731036,0.006530033,0.3460746],"study_design_scores_gemma":[0.000753568,0.0005168229,0.01679887,0.8848994,0.02082979,0.0005681764,0.00142185,0.0003773211,0.0005073871,0.001302789,0.07189623,0.0001277434],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002338197,0.9862429,0.002131488,0.001594617,0.001074579,0.004396401,0.0004906579,0.00004262157,0.001688533],"genre_scores_gemma":[0.04003679,0.9292828,0.01738233,0.001079542,0.0005209764,0.01054567,0.0007900145,0.00002769946,0.0003342743],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8991904,"threshold_uncertainty_score":0.5331386,"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."}}