{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1347974,0.001062089,0.0007723171,0.004977331,0.001193106,0.00271335,0.001733261,0.0006287154,0.006164004],"category_scores_gemma":[0.2125311,0.0007528992,0.001497822,0.004394433,0.001766619,0.002115411,0.005155982,0.001011402,0.001336977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002357821,"about_ca_system_score_gemma":0.003058448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001753299,"about_ca_topic_score_gemma":0.005055936,"domain_scores_codex":[0.7356939,0.1906653,0.02852113,0.01119264,0.0318353,0.002091758],"domain_scores_gemma":[0.6296126,0.2093039,0.06104058,0.03086509,0.06754816,0.001629764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003201665,0.0005118464,0.2938856,0.00614357,0.001002836,0.0001677481,0.02613135,0.002706423,0.01345031,0.01331069,0.01426212,0.6252258],"study_design_scores_gemma":[0.001518518,0.006612525,0.7384366,0.009364203,0.0009744512,0.001509339,0.03844199,0.04713555,0.02913929,0.01837221,0.1076976,0.0007978039],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.373069,0.002429038,0.5701834,0.001050691,0.001163099,0.0221508,0.00418205,0.001028701,0.02474315],"genre_scores_gemma":[0.4682891,0.0008556391,0.4744432,0.0004178472,0.0003027326,0.05041622,0.002408716,0.0003019013,0.002564549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1347974,"threshold_uncertainty_score":0.7128855,"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."}}