{"id":"W4294012667","doi":"10.1097/jte.0000000000000248","title":"Vertical Versus Horizontal Assessment Methods for Scoring Physiotherapy Entrance Interviews","year":2022,"lang":"en","type":"article","venue":"Journal of Physical Therapy Education","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Intraclass correlation; Inter-rater reliability; Reliability (semiconductor); Descriptive statistics; Correlation; Statistics; Psychology; Cohort; Mathematics; Psychometrics; Rating scale","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":[],"consensus_categories":[],"category_scores_codex":[0.005769381,0.0001402711,0.0003887296,0.000130813,0.0002587457,0.0001335548,0.0007473353,0.00001981639,0.0002674314],"category_scores_gemma":[0.0003830143,0.0000968222,0.000516392,0.0003902395,0.00004577062,0.0003346463,0.00004553091,0.0003071603,0.000003861906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004038217,"about_ca_system_score_gemma":0.0004388603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004862414,"about_ca_topic_score_gemma":5.036877e-7,"domain_scores_codex":[0.9963887,0.0009987791,0.0007505515,0.0002638427,0.001401492,0.0001965871],"domain_scores_gemma":[0.9970173,0.001651965,0.0004244936,0.0003266212,0.0004714236,0.0001082145],"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":[0.0009415298,0.00213149,0.0001802811,0.000004957501,0.00007366938,1.438787e-7,0.001338593,0.0004106678,0.1451698,0.003310242,0.002062166,0.8443764],"study_design_scores_gemma":[0.005441609,0.01129827,0.007903546,0.00006019395,0.00005808314,0.000007781629,0.006200686,0.007083123,0.04208951,0.1457202,0.7737235,0.0004135704],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8790997,0.0009591678,0.108949,0.003784121,0.006264397,0.0005572204,0.00000357359,0.000008286534,0.0003744841],"genre_scores_gemma":[0.9781375,0.0001039997,0.01977107,0.0003685518,0.00140636,0.0001166891,0.000001788864,0.00001373525,0.00008033614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8439628,"threshold_uncertainty_score":0.3948295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2341806624339205,"score_gpt":0.5653326466877174,"score_spread":0.3311519842537969,"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."}}