{"id":"W4405301127","doi":"10.48550/arxiv.2412.08052","title":"CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Credit Risk and Financial Regulations","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Human Genome Research Institute; National Institutes of Health; U.S. National Library of Medicine; Canadian Institute for Advanced Research","keywords":"Counterfactual thinking; Computer science; Political science; Economics; Psychology; Social psychology","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":[0.06029419,0.002698861,0.004244118,0.002468186,0.001185716,0.004716988,0.004784786,0.004385132,0.007782569],"category_scores_gemma":[0.2243923,0.00157516,0.002002431,0.002090739,0.004566363,0.006082432,0.006209605,0.006253411,0.001130493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003161603,"about_ca_system_score_gemma":0.005163485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003326555,"about_ca_topic_score_gemma":0.003349387,"domain_scores_codex":[0.9572305,0.0326961,0.001221469,0.003663476,0.004292994,0.0008955482],"domain_scores_gemma":[0.7463828,0.223243,0.006853557,0.01620439,0.005513042,0.001803165],"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":[0.001543646,0.0003792589,0.007822784,0.0008103386,0.0005260106,0.0003705964,0.0003359445,0.5929789,0.001180922,0.2152837,0.008407714,0.1703603],"study_design_scores_gemma":[0.0001058835,0.0001554056,0.0004749141,0.0001430454,0.00004079614,0.00005639373,0.00002983511,0.8702896,0.001094126,0.1251641,0.002411911,0.00003400028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008302113,0.0007362317,0.9855399,0.0009926336,0.0001245319,0.0002741867,0.0004573124,0.0008944772,0.002678507],"genre_scores_gemma":[0.5049413,0.0008206972,0.4852062,0.001520938,0.0003797783,0.001357287,0.001881384,0.0006890137,0.003203478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06029419,"threshold_uncertainty_score":0.31887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1443634423835982,"score_gpt":0.2109082769568782,"score_spread":0.06654483457328006,"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."}}