{"id":"W7106797090","doi":"10.48448/wa3x-s037","title":"ACING: Actor-Critic for Instruction Learning in Black-Box LLMs","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Robustness (evolution); Baseline (sea); Code (set theory); Reinforcement learning; Quality (philosophy)","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":[0.001530395,0.001502167,0.00084444,0.0003406394,0.0003741643,0.001019052,0.002191794,0.001669515,0.01171202],"category_scores_gemma":[0.007166072,0.0006073898,0.0006500451,0.0002773423,0.001102473,0.00116132,0.001621278,0.003575702,0.003017611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038501,"about_ca_system_score_gemma":0.001736744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005493449,"about_ca_topic_score_gemma":0.008515807,"domain_scores_codex":[0.9994184,0.0002172461,0.00003100441,0.0001587979,0.0001126309,0.00006202416],"domain_scores_gemma":[0.998184,0.001218282,0.00009915896,0.000180257,0.0002091877,0.0001090674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003441565,0.0001530511,0.0009292659,0.0003947012,0.00008065633,0.0001637962,0.0001638129,0.7907376,0.00531488,0.02068618,0.01489089,0.1661411],"study_design_scores_gemma":[0.00002592655,0.00001866463,0.00002935847,0.00001368488,0.000004555577,0.000007699206,0.000004753668,0.9920228,0.0008859061,0.00585489,0.00112783,0.000004101695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009178402,0.000469302,0.9651118,0.0004980856,0.0001869493,0.0001542497,0.0002877449,0.01739647,0.006716929],"genre_scores_gemma":[0.4673672,0.0003189979,0.5149984,0.0007893764,0.0001279659,0.0006276388,0.001112981,0.002638701,0.0120187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01171202,"threshold_uncertainty_score":0.03918058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04062401577801058,"score_gpt":0.3401972624251489,"score_spread":0.2995732466471383,"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."}}