{"id":"W2064169615","doi":"10.3352/jeehp.2014.11.28","title":"What steps are necessary to create written or web-based selected-response assessments?","year":2014,"lang":"en","type":"article","venue":"Journal of Educational Evaluation for Health Professions","topic":"Innovations in Medical Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal General Hospital; McGill University","funders":"","keywords":"Computer science; Process (computing); Work (physics); Health care; Health professionals; Online assessment; Medical education; Formative assessment; Medicine; Psychology; Mathematics education; Engineering","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01151004,0.0001974771,0.0004821787,0.0009268498,0.0005732498,0.00006655486,0.0002152436,0.0001591066,0.001472],"category_scores_gemma":[0.02507021,0.0001491844,0.0001136206,0.001394796,0.00005298399,0.000518647,0.00002213312,0.0005363796,0.00004293038],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001381066,"about_ca_system_score_gemma":0.02509226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005276138,"about_ca_topic_score_gemma":0.00001751983,"domain_scores_codex":[0.9951623,0.001178609,0.001459262,0.0002758555,0.001540767,0.0003832089],"domain_scores_gemma":[0.9879873,0.002205347,0.001537066,0.0003557884,0.007465312,0.0004491639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.007672837,0.003326524,0.01381113,0.0007818271,0.0001610512,6.743693e-7,0.00173629,0.0007511523,0.00107592,0.0008910057,0.9038714,0.0659202],"study_design_scores_gemma":[0.01286962,0.006175133,0.7206454,0.008689809,0.0005392822,0.0001392715,0.01564223,0.03586708,0.0002508106,0.00268759,0.1960029,0.0004908256],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4489622,0.0001629067,0.007129695,0.5370303,0.00438789,0.002220287,0.00001390062,0.00001736555,0.00007549943],"genre_scores_gemma":[0.8702363,0.00004983375,0.06934012,0.05234526,0.002247507,0.00105302,0.000388682,0.00006686462,0.004272378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7078685,"threshold_uncertainty_score":0.9994408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018934734433987,"score_gpt":0.5380365283357339,"score_spread":0.4361430548923352,"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."}}