{"id":"W3083830176","doi":"10.1214/20-sts786","title":"On Nearly Assumption-Free Tests of Nominal Confidence Interval Coverage for Causal Parameters Estimated by Machine Learning","year":2020,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Shanghai University of Finance and Economics; University of Toronto; Eidgenössische Technische Hochschule Zürich; University of Washington; Office of Naval Research; Harvard University; National Science Foundation","keywords":"Estimator; Mathematics; Smoothness; Statistics; Confidence interval; Null hypothesis; Null (SQL); Algorithm; Computer science; Mathematical analysis","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":[0.09213686,0.002029962,0.003960662,0.005596853,0.001689131,0.004909622,0.005704682,0.004066926,0.005661245],"category_scores_gemma":[0.557745,0.000922098,0.003444355,0.005619261,0.01354095,0.009473423,0.007209993,0.00652071,0.0009943149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001771157,"about_ca_system_score_gemma":0.002271543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002123682,"about_ca_topic_score_gemma":0.0008198161,"domain_scores_codex":[0.9070449,0.06290876,0.004211684,0.01037353,0.01339832,0.002062852],"domain_scores_gemma":[0.1868656,0.7742075,0.01626034,0.01595336,0.005371536,0.001341725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002247165,0.0002356879,0.05726473,0.001713902,0.002453558,0.001761401,0.00162091,0.1200926,0.001808531,0.6576873,0.005582693,0.1475316],"study_design_scores_gemma":[0.0003493077,0.0006996385,0.01634957,0.0009029239,0.0004205603,0.001106255,0.0005426016,0.2737927,0.002948084,0.6956941,0.006964542,0.0002296676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07639241,0.004871472,0.9004841,0.003207047,0.0003280423,0.0003179322,0.001912002,0.0009439102,0.01154291],"genre_scores_gemma":[0.8549904,0.002035806,0.1338486,0.002423785,0.001168562,0.001198971,0.003070422,0.0003342675,0.000929094],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09213686,"threshold_uncertainty_score":0.4872721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1482724978566601,"score_gpt":0.4273872417202583,"score_spread":0.2791147438635982,"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."}}