{"id":"W4237250537","doi":"10.47004/wp.cem.2021.2121","title":"Layered policy analysis program evaluation using the marginal treatment effect","year":2021,"lang":"en","type":"report","venue":"","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Chicago","keywords":"Statistics; Econometrics; Computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00182366,0.0003619062,0.0007648275,0.001083902,0.0002833639,0.0003589318,0.001060042,0.0003775318,0.0001726583],"category_scores_gemma":[0.0002928413,0.0001990331,0.000844449,0.005335723,0.00007504528,0.0001673751,0.0004139991,0.00023679,0.00001492774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118653,"about_ca_system_score_gemma":0.002724194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006097474,"about_ca_topic_score_gemma":0.001756398,"domain_scores_codex":[0.9966919,0.0005130895,0.000387628,0.0008531241,0.00120478,0.0003494685],"domain_scores_gemma":[0.9965339,0.0001516561,0.0003431101,0.002386001,0.0005258017,0.00005947624],"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":[0.000003265342,0.0001733808,0.003455135,0.00002032299,0.008275014,0.00005791518,0.00004436058,0.001288675,0.00001853131,0.0008315821,0.001014951,0.9848168],"study_design_scores_gemma":[0.0005785281,0.000523286,0.005963139,0.00004413598,0.02523656,0.0002098799,0.00003844053,0.8602215,0.0008181679,0.0004308259,0.105239,0.0006964859],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01112011,0.007595459,0.9229303,0.005860764,0.0009702565,0.004990121,0.0001107639,0.001838889,0.04458333],"genre_scores_gemma":[0.8123186,0.002875204,0.1611223,0.0002961301,0.001600808,0.003184738,0.004216268,0.0000844808,0.0143015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9841204,"threshold_uncertainty_score":0.9217597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09699698981932352,"score_gpt":0.4357708634362343,"score_spread":0.3387738736169107,"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."}}