{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001451399,0.0002698592,0.0002669845,0.00009265079,0.0002155462,0.00020562,0.001266959,0.0001080032,0.00002440937],"category_scores_gemma":[0.00002548934,0.0002516938,0.00008426396,0.001071338,0.0000911575,0.001299029,0.0003666773,0.0003507459,0.0001468953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006854869,"about_ca_system_score_gemma":0.0001514989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001176034,"about_ca_topic_score_gemma":0.00006206538,"domain_scores_codex":[0.9982786,0.0001322884,0.0001440053,0.0008936824,0.0001413373,0.0004101245],"domain_scores_gemma":[0.9986911,0.0001288691,0.0001038096,0.000583743,0.0001552123,0.0003372038],"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":[0.00005023995,0.00002598667,0.001404934,0.00005437667,0.00004895206,0.000390331,0.0007867808,0.7309415,0.0001947206,0.2647175,0.0002513374,0.001133309],"study_design_scores_gemma":[0.0005117723,0.0002345656,0.00006954261,0.00006313567,0.00003078816,0.00000747698,0.0001015013,0.9846305,0.000280259,0.01364001,0.00007588974,0.0003545514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09901419,0.00001525308,0.8992108,0.0003779313,0.00005287083,0.0001424298,0.000003885856,0.0003889829,0.0007937129],"genre_scores_gemma":[0.9968722,0.00001955306,0.002493791,0.0004110369,0.00003680375,0.000001110208,0.000004573827,0.0000147652,0.0001461844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.897858,"threshold_uncertainty_score":0.9999935,"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."}}