{"id":"W4378223319","doi":"10.1002/ev.20539","title":"Meeting the challenges of educating internal evaluators","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Queen's University","funders":"","keywords":"Front line; Public relations; Geopolitics; Coronavirus disease 2019 (COVID-19); Pandemic; Program evaluation; Political science; Business; Medicine; Public administration","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0243713,0.0001005506,0.0001610651,0.0004154885,0.0004779745,0.00009592403,0.0003741297,0.00004715356,0.0007444051],"category_scores_gemma":[0.01048717,0.00006631506,0.0001503054,0.001265866,0.0000421683,0.0002871208,0.0000567223,0.00008789517,0.0002198569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020664,"about_ca_system_score_gemma":0.0005498398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009024751,"about_ca_topic_score_gemma":0.0004390223,"domain_scores_codex":[0.9960158,0.0005099875,0.0006999962,0.0003111025,0.002276029,0.0001870935],"domain_scores_gemma":[0.9951709,0.002535522,0.0004472402,0.0004326838,0.001357785,0.00005587844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001666749,0.00004034591,0.00194449,0.000007415414,0.00003356827,1.683456e-8,0.004373027,0.01080351,0.0004864877,0.006708819,0.02214313,0.9534425],"study_design_scores_gemma":[0.001354817,0.0001968208,0.1086238,0.00008520552,0.0001590046,0.000004377574,0.01843545,0.7021917,0.003418212,0.09723347,0.06809587,0.0002012833],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8167965,0.002155344,0.00535571,0.03241059,0.006582715,0.002995843,0.00001947544,0.0002715464,0.1334123],"genre_scores_gemma":[0.9955015,0.0001431534,0.0007614358,0.00005847383,0.0004195982,0.0002911571,0.00001314216,0.00001277766,0.002798749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9532412,"threshold_uncertainty_score":0.9978479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3888663697506948,"score_gpt":0.5659171151344419,"score_spread":0.1770507453837471,"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."}}