{"id":"W2625529206","doi":"10.1002/ev.20241","title":"Evaluation at the Time of Health Systems Reform: Chinese Policymakers’ Need for a Robust System of Evaluations to Assess Progress in the Implementation of Reform Efforts","year":2017,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Healthcare Systems and Reforms","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"China; Capacity building; Program evaluation; Political science; Evaluation methods; Economic growth; Public administration; Public relations; Economics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3998632,0.0008794977,0.002309658,0.007065792,0.008777276,0.0191307,0.004198353,0.004074499,0.005260134],"category_scores_gemma":[0.3123251,0.0009906702,0.001080783,0.005473319,0.01955709,0.01898642,0.01558735,0.006509815,0.0002334003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.06793053,"about_ca_system_score_gemma":0.2157802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1471385,"about_ca_topic_score_gemma":0.09829311,"domain_scores_codex":[0.7186878,0.2254996,0.01390101,0.007656405,0.02356612,0.01068908],"domain_scores_gemma":[0.5910687,0.2555616,0.02007386,0.02498625,0.09533241,0.01297717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0009305603,0.0005778749,0.1121723,0.004837655,0.0006565424,0.0004628922,0.09111272,0.01432776,0.002811313,0.3643701,0.03996667,0.3677737],"study_design_scores_gemma":[0.001316002,0.001137999,0.2603628,0.01754925,0.001072353,0.0002033841,0.1479473,0.05311975,0.01008498,0.3238639,0.1821298,0.001212445],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3045489,0.01894003,0.07578576,0.4905304,0.001404172,0.004971537,0.0008615531,0.0005366536,0.102421],"genre_scores_gemma":[0.9742045,0.0009981904,0.01545308,0.006406554,0.0001407912,0.00148525,0.000122073,0.00003671631,0.00115297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3998632,"threshold_uncertainty_score":0.7400755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1460740830988409,"score_gpt":0.4342321583106813,"score_spread":0.2881580752118404,"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."}}