{"id":"W4366675251","doi":"10.3138/cjpe.019.005","title":"An Empirical Study of Building the Evaluation Capacity of K–12 Site-Managed Project Personnel","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Argument (complex analysis); Psychology; Medical education; Program evaluation; Professional development; Evaluation methods; Capacity building; Applied psychology; Pedagogy; Political science; Engineering; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0258151,0.0003375697,0.0002723716,0.001041308,0.003744675,0.002128777,0.001466841,0.0007234177,0.002900505],"category_scores_gemma":[0.0632002,0.0005768006,0.0002895893,0.0006535857,0.002402245,0.001438752,0.002396876,0.001635481,0.0003855016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00349956,"about_ca_system_score_gemma":0.00862353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009282048,"about_ca_topic_score_gemma":0.01498484,"domain_scores_codex":[0.9761721,0.01793783,0.0007550257,0.0009076697,0.001728419,0.00249903],"domain_scores_gemma":[0.8779622,0.07186505,0.01415841,0.006471634,0.01965414,0.009888516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00139994,0.01691382,0.5693737,0.0007544888,0.0001879613,0.0008119243,0.2353866,0.001560003,0.006839876,0.001426764,0.002078391,0.1632666],"study_design_scores_gemma":[0.000314908,0.01052483,0.6830956,0.0004200324,0.0001026438,0.0003728111,0.2856335,0.002733069,0.006841015,0.0005505122,0.009281681,0.0001292877],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988193,0.0000221605,0.0001683184,0.00005753705,0.000001879562,0.00005872858,0.00000606716,0.000004030638,0.0008619227],"genre_scores_gemma":[0.9991536,0.0000266267,0.0004816443,0.00003011072,0.00000280405,0.00007144114,0.00001138729,0.000001802719,0.0002205776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0258151,"threshold_uncertainty_score":0.1365249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5928942452671162,"score_gpt":0.566262734771,"score_spread":0.02663151049611623,"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."}}