{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005505922,0.0001706905,0.0002998537,0.00004733938,0.0001379353,0.00007333191,0.0005515435,0.0000486324,0.0001099777],"category_scores_gemma":[0.02688372,0.0001505633,0.00003382602,0.0002847667,0.0008994704,0.0002433791,0.0001492053,0.0002689288,0.00001308411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008225333,"about_ca_system_score_gemma":0.0001010529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008126993,"about_ca_topic_score_gemma":0.00001233284,"domain_scores_codex":[0.9982417,0.00005419803,0.0003773005,0.0004346647,0.0005218887,0.0003702349],"domain_scores_gemma":[0.9954509,0.003709844,0.0001918199,0.0002308281,0.0001803929,0.0002362201],"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":[0.0003118929,0.0001488826,0.0007905522,0.0001917293,0.00001195906,0.00001797032,0.0004322147,0.0003183645,0.1156857,0.8700598,0.003989927,0.008041013],"study_design_scores_gemma":[0.0006900828,0.003284235,0.001217223,0.0001772728,0.00003933303,0.000007445393,0.00004056526,0.1683531,0.0338299,0.791889,0.00008898525,0.0003829433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07653661,0.000006662123,0.9218857,0.000299299,0.00003840901,0.0003351156,0.000523079,0.0001476699,0.0002275152],"genre_scores_gemma":[0.7049569,0.000001943401,0.2948143,0.0001498091,0.000006613461,0.00002250266,0.00001422695,0.00001220447,0.00002144146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6284204,"threshold_uncertainty_score":0.9813132,"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."}}