{"id":"W347468065","doi":"10.3138/cjpe.0023.005","title":"The Road to Evaluation Capacity Building: A Case Study from Israel","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Presentation (obstetrics); Curriculum; Outcome (game theory); Relation (database); Capacity building; Psychology; Political science; Mathematics education; Sociology; Medical education; Pedagogy; Economics; History; Computer science; Medicine; Law; Archaeology","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0451154,0.000172242,0.0002643322,0.0005860731,0.0008591939,0.001234757,0.000699055,0.00007258916,0.0006401814],"category_scores_gemma":[0.008174784,0.000112154,0.0001383557,0.001196364,0.00005828659,0.0006923013,0.0000141848,0.0002840401,0.00008419783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008702355,"about_ca_system_score_gemma":0.004507436,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.009889596,"about_ca_topic_score_gemma":0.1698368,"domain_scores_codex":[0.9913501,0.001891026,0.001309218,0.0003273156,0.004753226,0.000369147],"domain_scores_gemma":[0.9911759,0.0004465278,0.0007884051,0.0005969718,0.00625914,0.0007330246],"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":[0.00002095424,0.00009706214,0.01168296,2.245599e-7,0.00003056772,0.00004572726,0.004168433,0.0035854,0.00004706303,0.0001168996,0.00165484,0.9785499],"study_design_scores_gemma":[0.003692471,0.004481605,0.5596265,0.00005526825,0.0005900239,0.0007032326,0.04675965,0.3119587,0.0001238653,0.03904397,0.03250885,0.000455788],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885021,0.0003136889,0.0007815619,0.005369626,0.001090214,0.003144827,0.000007287293,0.000009685716,0.0007809813],"genre_scores_gemma":[0.9964235,0.000002132902,0.002587524,0.0004728946,0.0003371447,0.0001196039,0.00000374754,0.000007735796,0.00004567788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9780941,"threshold_uncertainty_score":0.9998021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5869895881998264,"score_gpt":0.5568682661750065,"score_spread":0.03012132202481987,"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."}}