{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3414418,0.001377689,0.001572259,0.001557242,0.007664184,0.01148951,0.00998159,0.004257931,0.004888508],"category_scores_gemma":[0.372896,0.001507775,0.001285288,0.001625769,0.005457147,0.008984932,0.007464928,0.00675625,0.0009883911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02401171,"about_ca_system_score_gemma":0.05346369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02018537,"about_ca_topic_score_gemma":0.03222946,"domain_scores_codex":[0.6252229,0.3204527,0.01262704,0.004041854,0.02732638,0.01032913],"domain_scores_gemma":[0.5510771,0.2806847,0.01055596,0.02800186,0.1087531,0.02092724],"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":[0.00563074,0.05295735,0.05827211,0.008224814,0.0005451003,0.005344516,0.1794395,0.02668718,0.01206482,0.02248964,0.02612405,0.6022203],"study_design_scores_gemma":[0.009465878,0.1320763,0.07777134,0.01564313,0.0007363808,0.003296119,0.4642676,0.0494835,0.03135223,0.02088416,0.1937391,0.001284381],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8175352,0.001569211,0.07589044,0.02933972,0.0007890931,0.04609401,0.0005537929,0.000756536,0.027472],"genre_scores_gemma":[0.8285161,0.0006091969,0.1490563,0.001840537,0.0001131353,0.01651685,0.0003372776,0.0002086637,0.002801951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3414418,"threshold_uncertainty_score":0.8121196,"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."}}