{"id":"W1985629392","doi":"10.1198/073500102288618702","title":"Was There a Riverside Miracle? A Hierarchical Framework for Evaluating Programs With Grouped Data","year":2003,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Connaught Fund","keywords":"Pooling; Computer science; Econometrics; Independence (probability theory); Statistics; Mathematics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1372245,0.001689747,0.003186507,0.005372453,0.001917439,0.004228075,0.003714006,0.002743787,0.004261999],"category_scores_gemma":[0.2682575,0.001230341,0.004051457,0.004839745,0.005050017,0.007988214,0.005461274,0.003889709,0.0004482844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007822596,"about_ca_system_score_gemma":0.006712893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02717545,"about_ca_topic_score_gemma":0.03156167,"domain_scores_codex":[0.8124772,0.1640678,0.003738088,0.007569761,0.01031375,0.001833454],"domain_scores_gemma":[0.7295191,0.2224856,0.01745032,0.02201378,0.006171466,0.002359647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001059331,0.0006646292,0.04240867,0.0009421499,0.003179711,0.0003127434,0.001853332,0.3386764,0.0008676,0.4181609,0.005750299,0.1861241],"study_design_scores_gemma":[0.0003024177,0.001676923,0.01116758,0.0004137142,0.0005639098,0.00007248791,0.000540628,0.6385711,0.0008896115,0.3399256,0.00574102,0.0001350757],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04649674,0.001083476,0.9388754,0.003139275,0.0001045435,0.001726457,0.001310021,0.0006270086,0.006637026],"genre_scores_gemma":[0.3742076,0.0003893004,0.6198512,0.0007659894,0.00008550224,0.002561177,0.0007972191,0.0001203869,0.001221548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1372245,"threshold_uncertainty_score":0.7257211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2549804226516588,"score_gpt":0.4273379998675451,"score_spread":0.1723575772158863,"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."}}