{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03738422,0.0001537564,0.0003608995,0.0009283377,0.0003349678,0.0002104105,0.0007039417,0.00008309857,0.0003394002],"category_scores_gemma":[0.004105913,0.00009972147,0.0001559598,0.001318365,0.0001667052,0.0008497999,0.00001540814,0.0002865021,0.00000414697],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004810285,"about_ca_system_score_gemma":0.006250327,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004483304,"about_ca_topic_score_gemma":0.06565318,"domain_scores_codex":[0.9907619,0.002271673,0.001457823,0.000272409,0.004972918,0.0002633174],"domain_scores_gemma":[0.9929871,0.0002928448,0.001544457,0.000541518,0.004391194,0.0002428932],"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":[0.0001070495,0.001099474,0.3056978,0.00001801419,0.0001473313,0.000003895128,0.1080043,0.1452007,0.001742634,0.0002048066,0.0002499816,0.4375241],"study_design_scores_gemma":[0.005159802,0.005559172,0.6719835,0.0001007163,0.0006424922,0.00003626164,0.07724205,0.2316402,0.0008028976,0.006179592,0.0004133384,0.0002399604],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944438,0.00009907216,0.001211145,0.0006277495,0.0003855788,0.002904041,0.000007249643,0.000005546581,0.0003158259],"genre_scores_gemma":[0.9969576,0.00000232172,0.002746803,0.00006091767,0.0001228114,0.00008791818,0.000006646874,0.00001016368,0.000004814938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4372841,"threshold_uncertainty_score":0.9993833,"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."}}