{"id":"W4399311294","doi":"10.4310/23-sii781","title":"Scalable inference for individual treatment effect","year":2024,"lang":"en","type":"article","venue":"Statistics and Its Interface","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Inference; Causal inference; Computer science; Scalability; Econometrics; Statistics; Mathematics; Computational biology; Artificial intelligence; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002893018,0.0001676695,0.000505452,0.0001358394,0.0001144476,0.000236847,0.0001014583,0.00007350442,0.0002737514],"category_scores_gemma":[0.001521167,0.0001677854,0.00004425401,0.0000669568,0.00003325977,0.0001798312,0.00003513806,0.00007501701,0.0007912503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001974225,"about_ca_system_score_gemma":0.00007546239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001193787,"about_ca_topic_score_gemma":0.00004218159,"domain_scores_codex":[0.9980742,0.00006932894,0.00114135,0.0004105549,0.00004173755,0.0002627825],"domain_scores_gemma":[0.9972101,0.002260795,0.0002373538,0.0001482275,0.00003268606,0.0001107878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000266303,0.00005222146,0.002101946,0.00141692,0.000243481,0.000001954992,0.002784914,0.0001113586,0.00001099421,0.9221712,0.06354227,0.007536055],"study_design_scores_gemma":[0.001895562,0.002551096,0.003491726,0.0004797266,0.00008580378,0.0000115351,0.000425763,0.2528764,0.0004672686,0.1082065,0.6286728,0.0008358506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2283044,0.04300292,0.6784267,0.01076009,0.003479564,0.002847378,0.02835688,0.0002049803,0.004617094],"genre_scores_gemma":[0.9850025,0.0004635256,0.008804027,0.0006382071,0.0002155561,0.0002073067,0.000114701,0.00003718933,0.004516966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8139648,"threshold_uncertainty_score":0.9999868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2719650785614487,"score_gpt":0.4660830249175639,"score_spread":0.1941179463561152,"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."}}