{"id":"W3105957474","doi":"","title":"Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Covariate; Computer science; Causal inference; Inference; Range (aeronautics); Outcome (game theory); Data mining; Machine learning; Econometrics; Artificial intelligence; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01874707,0.001757206,0.002593787,0.001867477,0.001242282,0.002586802,0.003596718,0.003444122,0.003098863],"category_scores_gemma":[0.0982236,0.001459563,0.0019159,0.001349239,0.002767947,0.004410677,0.003624629,0.00657473,0.0005053419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002786239,"about_ca_system_score_gemma":0.002796319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01380887,"about_ca_topic_score_gemma":0.01391118,"domain_scores_codex":[0.9917251,0.004355674,0.0004440355,0.001894044,0.00117608,0.0004050413],"domain_scores_gemma":[0.8632655,0.12411,0.004925638,0.004513371,0.002428157,0.0007573641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003313443,0.0001010339,0.008250934,0.0002649859,0.0003136371,0.0002952361,0.0004290343,0.8482685,0.0005079437,0.06784018,0.002931942,0.0704651],"study_design_scores_gemma":[0.00002229846,0.00002806927,0.000539149,0.00004591196,0.00004301938,0.00005160789,0.00002515883,0.9119007,0.0003990335,0.0861607,0.0007627102,0.00002171987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01555847,0.0006174899,0.9805198,0.001469441,0.00005933216,0.00006737464,0.00025702,0.0003632086,0.001087864],"genre_scores_gemma":[0.7801447,0.0008463545,0.2136258,0.001039486,0.0003938505,0.0002712403,0.0007412747,0.0001703705,0.002766994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01874707,"threshold_uncertainty_score":0.09914517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09777616248558647,"score_gpt":0.2031867187588504,"score_spread":0.1054105562732639,"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."}}