{"id":"W4366724034","doi":"10.3138/cjpe.019.001","title":"Toward a Best Practice for Evaluating the Impact of Government Programs on Job Creation","year":2004,"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":"University of Alberta","funders":"Industry Canada","keywords":"Government (linguistics); Interpretation (philosophy); Strengths and weaknesses; Computer science; Management science; Engineering; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"category_scores_codex":[0.02614124,0.0001590306,0.0002675348,0.0002386379,0.0002809721,0.0004279948,0.0005063194,0.00007786175,0.0002888215],"category_scores_gemma":[0.01499979,0.00009291763,0.0003295924,0.0007021402,0.0001127791,0.0007465472,0.00001101117,0.0002065136,0.00002456882],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001766742,"about_ca_system_score_gemma":0.007049449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001787156,"about_ca_topic_score_gemma":0.003815482,"domain_scores_codex":[0.9934768,0.0006118919,0.00118535,0.0002173905,0.004205285,0.000303272],"domain_scores_gemma":[0.9918616,0.0008921915,0.001791258,0.0003534747,0.004802335,0.0002991358],"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":[0.0002268323,0.0003032114,0.004665802,0.000006572122,0.0000987406,0.000001320748,0.002916553,0.07458051,0.0001123141,0.001097617,0.0003857145,0.9156048],"study_design_scores_gemma":[0.02103389,0.1482309,0.1691387,0.001404512,0.002292288,0.0004362581,0.045682,0.467676,0.0018991,0.1080516,0.03298752,0.001167348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775556,0.0002999478,0.005927701,0.006834525,0.0005835471,0.004501705,0.00002810957,0.000006702105,0.004262113],"genre_scores_gemma":[0.9892898,0.00001043771,0.01003534,0.0001044868,0.0001834031,0.0002684539,0.00001085165,0.00001292904,0.00008435058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9144375,"threshold_uncertainty_score":0.9985797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5293612574148838,"score_gpt":0.6057482510986992,"score_spread":0.07638699368381541,"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."}}