{"id":"W2794879539","doi":"10.1111/bju.14219","title":"Implementing assessments of robot‐assisted technical skill in urological education: a systematic review and synthesis of the validity evidence","year":2018,"lang":"en","type":"review","venue":"British Journal of Urology","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; University of Toronto","funders":"","keywords":"PsycINFO; Crowdsourcing; MEDLINE; Psychometrics; Educational measurement; Computer science; Rating scale; Medical education; Psychology; Applied psychology; Data science; Medicine; Clinical psychology; World Wide Web","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003956997,0.0001666758,0.003152065,0.0001357424,0.00004006525,0.00001088374,0.0002801964,0.0002441974,0.0001243193],"category_scores_gemma":[0.009543061,0.0001120112,0.0005173252,0.0003761358,0.0002017486,0.00005530332,0.0001378941,0.0005755519,7.324513e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005662292,"about_ca_system_score_gemma":0.0005150251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008186049,"about_ca_topic_score_gemma":0.00000790608,"domain_scores_codex":[0.9952523,0.00162354,0.00238944,0.0001961817,0.0003373071,0.0002012831],"domain_scores_gemma":[0.9941577,0.002559818,0.002605492,0.0002269515,0.0003617298,0.0000883644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0000273026,0.0005436106,0.001192125,0.6309894,0.0003249779,0.000119357,0.000008172674,3.699662e-7,5.817842e-7,0.00003912821,0.0001069049,0.366648],"study_design_scores_gemma":[0.0005905288,0.0004974119,0.01265563,0.931662,0.01105858,0.02511512,0.00001528485,0.000005505651,3.863477e-7,0.00004487302,0.01821508,0.000139638],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002953586,0.9982245,0.00003482898,0.0001798682,0.0001087536,0.0009218033,0.000005950443,0.000003675352,0.0002252536],"genre_scores_gemma":[0.05911494,0.9402006,0.0003016345,0.0002581301,0.00006389654,0.00003489035,0.000001845769,0.00001246917,0.00001159161],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3665084,"threshold_uncertainty_score":0.9988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1426079141418255,"score_gpt":0.4390190372596769,"score_spread":0.2964111231178514,"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."}}