{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000369409,0.0003787343,0.0004221108,0.0003271536,0.0003382414,0.0003348181,0.002445341,0.0003333863,0.00007857879],"category_scores_gemma":[0.0003167843,0.0004973959,0.000239778,0.001026509,0.00006035342,0.0004123113,0.007000145,0.001700462,0.00009972727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003679984,"about_ca_system_score_gemma":0.0003543435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003213288,"about_ca_topic_score_gemma":0.00007454516,"domain_scores_codex":[0.9971266,0.0003884276,0.0002111706,0.0015951,0.0001675364,0.0005111413],"domain_scores_gemma":[0.9977152,0.0001641085,0.0002265627,0.001380672,0.0002222716,0.0002911777],"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":[0.00000783361,0.00002884274,0.001351078,0.00003472002,0.00005732739,0.0009969036,0.001556329,0.9588834,0.00003008077,0.03589944,0.0001504633,0.001003567],"study_design_scores_gemma":[0.0003598003,0.00007387844,0.0009119809,0.0001282795,0.00005903593,0.000015334,0.0007156064,0.9899048,0.00007645073,0.003407322,0.003541538,0.0008060046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2281971,0.00003251577,0.7664061,0.0006137975,0.0009689076,0.0001774494,0.000001599343,0.0005039132,0.003098653],"genre_scores_gemma":[0.9809979,0.00003791897,0.01431649,0.0004468951,0.0001289124,0.000001070963,0.00001878901,0.0000317823,0.004020279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7528008,"threshold_uncertainty_score":0.9997478,"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."}}