{"id":"W3189589852","doi":"10.1007/s12630-021-02077-0","title":"Comparing simulation design tools: expecting the unexpected to improve summative assessment integrity","year":2021,"lang":"en","type":"letter","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Simulation-Based Education in Healthcare","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Memorial University of Newfoundland","funders":"","keywords":"Summative assessment; Computer science; Reliability engineering; Engineering; Psychology; Formative assessment; 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":[0.03005282,0.0004125157,0.0007079421,0.0007789214,0.004735059,0.003389569,0.002021821,0.02503027,0.01265927],"category_scores_gemma":[0.2087077,0.0005977836,0.00102585,0.0004001127,0.00268328,0.003753053,0.002525378,0.01528595,0.004021915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005226992,"about_ca_system_score_gemma":0.01938249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01090913,"about_ca_topic_score_gemma":0.03051406,"domain_scores_codex":[0.9737914,0.01387895,0.003466297,0.0008691428,0.00665252,0.001341718],"domain_scores_gemma":[0.7867395,0.1638487,0.004767683,0.003578328,0.02710143,0.01396431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005511059,0.0004669994,0.01261281,0.0002398505,0.00006166765,0.002681234,0.003555509,0.001082553,0.0007403651,0.008307982,0.8556385,0.1140615],"study_design_scores_gemma":[0.0008388708,0.001607958,0.01011803,0.001883708,0.0001542435,0.005506898,0.008688617,0.0107003,0.001653355,0.03769052,0.9208606,0.0002968868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.004791653,0.0003004554,0.002166936,0.9765568,0.006337571,0.00009535053,0.00004360951,0.0001474389,0.00956029],"genre_scores_gemma":[0.1465078,0.001055665,0.01812874,0.799126,0.01320656,0.000840145,0.0001124123,0.0002381362,0.02078453],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.03005282,"threshold_uncertainty_score":0.1589364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0919199925542302,"score_gpt":0.3359335137548998,"score_spread":0.2440135212006696,"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."}}