{"id":"W4287448176","doi":"10.1080/15366367.2021.1991742","title":"Using Think-aloud Interviews to Examine a Clinically Oriented Performance Assessment Rubric","year":2022,"lang":"en","type":"article","venue":"Measurement Interdisciplinary Research and Perspectives","topic":"Innovations in Medical Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Rubric; Operationalization; Psychology; Context (archaeology); Peer assessment; Think aloud protocol; Rating scale; Applied psychology; Educational measurement; Medical education; Computer science; Mathematics education; Pedagogy; Medicine; Developmental psychology","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":[0.0318062,0.001556749,0.0006970007,0.002344997,0.002596188,0.002475677,0.001251118,0.001374357,0.001883308],"category_scores_gemma":[0.08227836,0.0005929035,0.000434813,0.00120916,0.004199168,0.002070897,0.002229909,0.002723053,0.001026752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003140833,"about_ca_system_score_gemma":0.004079199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001505786,"about_ca_topic_score_gemma":0.002875063,"domain_scores_codex":[0.9713538,0.02219187,0.001460029,0.001483212,0.002547676,0.0009634117],"domain_scores_gemma":[0.888649,0.08873363,0.006610456,0.002253373,0.01231686,0.001436656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002705064,0.0005481189,0.007239294,0.000587613,0.00001761247,0.0007755785,0.920875,0.0006556044,0.02744507,0.002823958,0.001707095,0.03705465],"study_design_scores_gemma":[0.0001419666,0.002444668,0.01543754,0.001052639,0.00004252368,0.001329717,0.8730238,0.006209029,0.03876148,0.01175526,0.0494661,0.0003353754],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8703209,0.0003492739,0.1123885,0.001238586,0.0002272829,0.004842086,0.0004731667,0.0002952259,0.009864938],"genre_scores_gemma":[0.8772358,0.0006413499,0.105634,0.001350067,0.0001256891,0.009267593,0.0003918671,0.0001599335,0.005193755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0318062,"threshold_uncertainty_score":0.1682093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3522250709098728,"score_gpt":0.5102631214747934,"score_spread":0.1580380505649206,"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."}}