{"id":"W2782689587","doi":"10.1002/lary.27085","title":"Validity evidence as a key marker of quality of technical skill assessment in OTL–HNS","year":2018,"lang":"en","type":"review","venue":"The Laryngoscope","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Context (archaeology); Psychology; External validity; Quality (philosophy); Internal validity; Content validity; Quality assessment; Evidence-based practice; Medical education; Applied psychology; Psychometrics; Medicine; Clinical psychology; Social psychology; External quality assessment","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004497708,0.0002663191,0.002080488,0.0001193323,0.00003066785,0.000007523816,0.0003305143,0.0002953092,0.001123903],"category_scores_gemma":[0.001878174,0.0001537363,0.0005074626,0.0005783644,0.0002857241,0.00005186469,0.0001953446,0.0006567268,0.00005330578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001300807,"about_ca_system_score_gemma":0.0005559473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002267147,"about_ca_topic_score_gemma":0.00003714437,"domain_scores_codex":[0.9963571,0.00112631,0.001320141,0.0003391869,0.0006219124,0.000235337],"domain_scores_gemma":[0.995353,0.002999383,0.0006513267,0.0007584437,0.0001380297,0.00009981106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001547883,0.003748737,0.01871105,0.1159671,0.001229016,0.0001764328,0.001124472,0.000008281479,0.00006676377,0.01125758,0.001710425,0.8444523],"study_design_scores_gemma":[0.001627196,0.0005693713,0.04009548,0.07311907,0.001020286,0.00004445316,0.00004207114,0.00004525528,0.00001435329,0.0003907889,0.8826678,0.0003638169],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00723927,0.9553186,0.00004662829,0.0003372428,0.0001682587,0.001681937,0.00002831187,0.00005023127,0.03512953],"genre_scores_gemma":[0.06621383,0.9325933,0.000418174,0.0001808637,0.0001168542,0.00005340565,0.00002909034,0.00003268714,0.0003617565],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8809574,"threshold_uncertainty_score":0.9997892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2561095236087899,"score_gpt":0.5013720499627823,"score_spread":0.2452625263539924,"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."}}