{"id":"W4392943351","doi":"10.1109/icmla58977.2023.00048","title":"Preferential Proximal Policy Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007951681,0.00007900534,0.0001117008,0.0006377672,0.000124441,0.0002471969,0.0003080134,0.00006160674,0.001549819],"category_scores_gemma":[0.001029362,0.00005480982,0.00005725974,0.002799397,0.00002860687,0.0003788076,0.00009260121,0.00004471673,0.002226247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001461166,"about_ca_system_score_gemma":0.0001040347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004679925,"about_ca_topic_score_gemma":0.00000959878,"domain_scores_codex":[0.9982924,0.00007378729,0.0003549845,0.0002821153,0.0007903053,0.0002063955],"domain_scores_gemma":[0.9991697,0.0001285721,0.00009495675,0.0003163615,0.000209439,0.00008098464],"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":[0.00001634558,0.00001946878,0.004047904,4.994581e-7,0.000004567424,0.000001196332,0.0001880606,0.8902717,0.00005094719,0.01123932,0.05640886,0.03775111],"study_design_scores_gemma":[0.0002709311,0.0000371011,0.008224244,0.000001662939,0.000003989888,0.000002592118,0.0001479252,0.9441412,0.0004644041,0.009111733,0.03746267,0.0001315406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03637714,0.000009400404,0.7449472,0.003545955,0.0006279095,0.0003485643,0.00001211368,0.0006407603,0.213491],"genre_scores_gemma":[0.9145741,0.0002147368,0.01310881,0.0002231027,0.0004510947,0.00001960359,0.00007432143,0.00001669927,0.0713175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.878197,"threshold_uncertainty_score":0.9993629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1161325673453281,"score_gpt":0.4136075758443717,"score_spread":0.2974750084990436,"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."}}