{"id":"W4393901296","doi":"10.3138/cjpe-2024-0001","title":"Capturing Evaluation Capacity: Findings from a Mapping of Evaluation Capacity Instruments","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Rubric; Face validity; Construct validity; Content validity; Reliability (semiconductor); Concurrent validity; Construct (python library); Adaptation (eye); Psychology; Computer science; Applied psychology; Internal consistency; Process management; Psychometrics; Engineering; Clinical psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.09469199,0.0006442162,0.0008044346,0.02295831,0.002309329,0.005989609,0.001994007,0.0009337167,0.001986116],"category_scores_gemma":[0.3468906,0.0007156071,0.001170705,0.02279952,0.004636295,0.01023089,0.009891407,0.001892221,0.0002411776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007494883,"about_ca_system_score_gemma":0.01404155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007819884,"about_ca_topic_score_gemma":0.006652097,"domain_scores_codex":[0.9235073,0.04713644,0.008091351,0.002931539,0.01655014,0.001783161],"domain_scores_gemma":[0.4071412,0.5084608,0.02169715,0.01469938,0.04614264,0.00185885],"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":[0.0002268868,0.0002513933,0.3012944,0.005815542,0.0002538073,0.0004201943,0.1730775,0.001749983,0.0007921581,0.02349287,0.002222826,0.4904025],"study_design_scores_gemma":[0.00008768668,0.0006492882,0.555223,0.01546697,0.0006145834,0.001857299,0.3142759,0.005296325,0.004402869,0.02817089,0.07370554,0.0002496162],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8890694,0.01746673,0.04066558,0.003146908,0.0001354712,0.001225006,0.0007532408,0.00009830143,0.04743936],"genre_scores_gemma":[0.9714831,0.005692805,0.02040066,0.0003202748,0.00003769358,0.00100746,0.000382072,0.00006332239,0.0006126196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09469199,"threshold_uncertainty_score":0.5007851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5637636910939985,"score_gpt":0.4808963562487809,"score_spread":0.08286733484521763,"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."}}