{"id":"W4255851291","doi":"10.3138/cjpe.209","title":"Challenges in Evaluating a Prototype Project in a Large Health Authority: Lessons Learned","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fraser Health; Centre for Advancing Health Outcomes","funders":"","keywords":"Pace; Health care; Bureaucracy; Bridge (graph theory); Process (computing); Process management; Business; Program evaluation; Test (biology); Public relations; Public sector; Nursing; Knowledge management; Medicine; Computer science; Political science; Public administration","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1021472,0.0001499329,0.0004231306,0.001888825,0.0001167763,0.000270003,0.0004554402,0.0001068136,0.0001875055],"category_scores_gemma":[0.01105023,0.0001231458,0.00008145295,0.001675201,0.00004332843,0.0007417122,0.0000218014,0.0004753309,0.00003959179],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001511299,"about_ca_system_score_gemma":0.03183288,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002346766,"about_ca_topic_score_gemma":0.3681619,"domain_scores_codex":[0.9914559,0.00299533,0.001508714,0.000354835,0.003118108,0.0005671718],"domain_scores_gemma":[0.9956593,0.0002115539,0.0009145286,0.000321694,0.00235021,0.0005427509],"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":[0.00005686246,0.0001144828,0.03123679,0.00001140848,0.000006659727,0.000009134797,0.01388509,0.001385003,0.000002105488,0.0007432563,0.000340167,0.9522091],"study_design_scores_gemma":[0.009585535,0.00687681,0.3379953,0.0006801749,0.00003860334,0.0000956289,0.05463804,0.4602758,0.00001135051,0.05913385,0.07019137,0.0004776307],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8629527,0.01049502,0.0004089483,0.1015586,0.001579002,0.01217216,0.00001665188,0.00003137063,0.01078562],"genre_scores_gemma":[0.9951974,0.00008833483,0.003961964,0.0001558077,0.0001191834,0.0004056781,0.000008720473,0.0000129377,0.0000499312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9517314,"threshold_uncertainty_score":0.9972801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8786268415298759,"score_gpt":0.6676318817317606,"score_spread":0.2109949597981153,"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."}}