{"id":"W4366384160","doi":"10.3138/cjpe.22.004","title":"Using Public Databases to Study Relative Program Impact","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Impact assessment; Database; Computer science; Control (management); Impact evaluation; Statistics; Political science; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04258688,0.0001707963,0.0002923579,0.001703802,0.0003759208,0.0007028366,0.0005433068,0.00005133728,0.002281259],"category_scores_gemma":[0.007306867,0.0001232426,0.0001556822,0.002416717,0.0000667675,0.001732843,0.00002821969,0.0002667394,0.00008255824],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012191,"about_ca_system_score_gemma":0.008199334,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001525843,"about_ca_topic_score_gemma":0.04971362,"domain_scores_codex":[0.9937333,0.000774198,0.001320048,0.0002912941,0.003351304,0.0005297888],"domain_scores_gemma":[0.9920642,0.0003718588,0.0008163736,0.0004276573,0.005060794,0.0012591],"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":[0.00002076156,0.0002356806,0.2237663,7.137686e-7,0.0000580831,0.00001677117,0.001798741,0.001060526,0.00002159147,0.0001477144,0.0004263151,0.7724468],"study_design_scores_gemma":[0.001764775,0.003935724,0.9071324,0.00004640298,0.0002064861,0.000110968,0.01123767,0.03483536,0.0000737013,0.00211892,0.03822026,0.0003173302],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9817213,0.0001545925,0.01193205,0.0006884004,0.0006391436,0.00342382,0.00001044089,0.00001672823,0.001413472],"genre_scores_gemma":[0.9676183,7.942863e-7,0.03195297,0.0001095803,0.0002125429,0.00004775395,0.00001134919,0.00001324018,0.00003346953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7721294,"threshold_uncertainty_score":0.9986308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7796421792303019,"score_gpt":0.6674537745782021,"score_spread":0.1121884046520998,"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."}}