{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02476921,0.0001670229,0.0005948601,0.0004284455,0.0007006835,0.00006283446,0.0003314779,0.0001116148,0.0000228831],"category_scores_gemma":[0.0005070747,0.0001067623,0.000196574,0.0004602588,0.00005591646,0.0003138416,0.00004042106,0.00006718418,0.000005799631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0028173,"about_ca_system_score_gemma":0.0007025592,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04791549,"about_ca_topic_score_gemma":0.009729856,"domain_scores_codex":[0.9966524,0.0002961427,0.001947334,0.0003266724,0.0004846093,0.0002928438],"domain_scores_gemma":[0.9949992,0.00008797005,0.002910886,0.0008400692,0.001101724,0.00006014364],"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":[0.0005736895,0.0009082225,0.1529075,0.007503154,0.001185186,1.285131e-7,0.05247431,0.03321675,0.000289344,0.1040618,0.003829292,0.6430506],"study_design_scores_gemma":[0.004793185,0.0008884722,0.7581195,0.0004616552,0.0001336642,0.000008541157,0.01162477,0.2202705,0.0001563846,0.00202621,0.001267976,0.0002492077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962664,0.001951279,0.004560638,0.00652254,0.001438232,0.01928447,0.0009204849,0.00002449409,0.002633821],"genre_scores_gemma":[0.9955105,0.00002128464,0.0003795431,0.00002420306,0.0001723092,0.003428225,0.0002479742,0.00002533042,0.0001906399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6428014,"threshold_uncertainty_score":0.9584245,"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."}}