{"id":"W2019936193","doi":"10.1177/0163278713475868","title":"Evidence for the Validity of Grouped Self-Assessments in Measuring the Outcomes of Educational Programs","year":2013,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Psychology; Correlation; Self-assessment; Applied psychology; Clinical psychology; Social psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0486081,0.000130406,0.0002894218,0.0001299077,0.0008927021,0.00007169443,0.00103765,0.00005248429,0.001077815],"category_scores_gemma":[0.006584603,0.0000517177,0.0001282632,0.0008862115,0.0001229121,0.0005083616,0.0001430466,0.0002435325,0.0000496569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002124421,"about_ca_system_score_gemma":0.003252528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003419926,"about_ca_topic_score_gemma":0.0005935377,"domain_scores_codex":[0.9907905,0.003745806,0.001513669,0.0002857424,0.003364509,0.0002997776],"domain_scores_gemma":[0.9774145,0.0182735,0.001305989,0.0009160389,0.002025337,0.00006461882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003754543,0.0005722886,0.8401332,0.00007166668,0.00005809484,4.774261e-9,0.0128044,0.001010135,0.00006463919,0.005576507,0.005803326,0.1338681],"study_design_scores_gemma":[0.000512785,0.0001220281,0.8980064,0.0001629812,0.00003427896,2.685553e-7,0.006454256,0.06970942,0.00002539808,0.02457193,0.0003447131,0.00005551933],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7293256,0.0005438737,0.002422104,0.2557138,0.001376498,0.01029663,0.000007575048,0.0000142099,0.0002997844],"genre_scores_gemma":[0.993075,0.00009887759,0.00147115,0.0009809423,0.00006361611,0.003812935,0.000007729868,0.000008016662,0.0004817729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2637494,"threshold_uncertainty_score":0.9998353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7640554176157064,"score_gpt":0.6509811233514293,"score_spread":0.1130742942642771,"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."}}