{"id":"W3209066245","doi":"10.48550/arxiv.2110.15907","title":"Learning to Be Cautious","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Counterfactual thinking; Regret; Computer science; Construct (python library); Task (project management); Reinforcement learning; Counterfactual conditional; Function (biology); Artificial intelligence; Key (lock); Machine learning; Subroutine; Field (mathematics); Psychology; Computer security; Social psychology; Mathematics","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":[0.004015494,0.001101218,0.0009060826,0.0004431359,0.0008737522,0.001384013,0.001907846,0.001942782,0.003821339],"category_scores_gemma":[0.02454198,0.000628388,0.0007089653,0.0002509299,0.003240131,0.002571149,0.002407428,0.003390995,0.00100331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00122378,"about_ca_system_score_gemma":0.003058968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00286755,"about_ca_topic_score_gemma":0.00326671,"domain_scores_codex":[0.996624,0.001111179,0.0001734965,0.001015333,0.0007007127,0.0003753429],"domain_scores_gemma":[0.9899154,0.005144028,0.001624463,0.001958137,0.0007739659,0.0005839489],"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":[0.0004937981,0.0003311739,0.008406685,0.0002609388,0.0002026541,0.0004240271,0.0008872609,0.7515466,0.01243537,0.1005052,0.007385398,0.1171209],"study_design_scores_gemma":[0.00004278056,0.0001144618,0.0008245537,0.00005630923,0.00002410815,0.0001259653,0.00006827167,0.9079426,0.003995572,0.08396941,0.002796665,0.00003935932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0780324,0.0001956775,0.9073392,0.001652186,0.00008999363,0.000180911,0.0001186788,0.001645611,0.01074529],"genre_scores_gemma":[0.8649889,0.0001122042,0.1284608,0.0005605333,0.00003830959,0.000191863,0.0001554515,0.0002636194,0.005228296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004015494,"threshold_uncertainty_score":0.02123618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05876060420039689,"score_gpt":0.203762131608785,"score_spread":0.1450015274083881,"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."}}