{"id":"W2608565195","doi":"10.1007/s00464-017-5569-y","title":"Establishing meaningful benchmarks: the development of a formative feedback tool for advanced laparoscopic suturing","year":2017,"lang":"en","type":"article","venue":"Surgical Endoscopy","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Formative assessment; Likert scale; Medicine; Medical physics; Task (project management); Psychology; Mathematics education","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04033469,0.002006324,0.0007776587,0.002623207,0.0007936614,0.004799411,0.003356571,0.001726029,0.005977632],"category_scores_gemma":[0.1821547,0.0005846597,0.0007853987,0.001114299,0.0009122607,0.004205632,0.003739197,0.002071798,0.001988805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001479357,"about_ca_system_score_gemma":0.003308794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008691736,"about_ca_topic_score_gemma":0.001232147,"domain_scores_codex":[0.9760171,0.01347131,0.002422092,0.001251627,0.00619005,0.0006478739],"domain_scores_gemma":[0.8023943,0.1441711,0.007442677,0.01094924,0.03060555,0.004437166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009751374,0.001967023,0.01048826,0.001321248,0.00009098521,0.000229891,0.01110727,0.003671591,0.01201693,0.003572932,0.02157408,0.9329846],"study_design_scores_gemma":[0.003248722,0.01820091,0.1003534,0.009295907,0.001175044,0.003394297,0.02764452,0.28551,0.1997223,0.05992288,0.2890863,0.0024457],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1158552,0.0003307515,0.8316564,0.002949,0.0008690285,0.006662012,0.001443385,0.02830286,0.0119314],"genre_scores_gemma":[0.1567347,0.000242741,0.8340499,0.0004497626,0.0001163543,0.003484066,0.001148382,0.001116036,0.002658032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04033469,"threshold_uncertainty_score":0.2133127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03242681642580231,"score_gpt":0.3328721437959679,"score_spread":0.3004453273701656,"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."}}