{"id":"W4409540887","doi":"10.32388/y43w9w","title":"Review of: \"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey\"","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Code (set theory); Reinforcement learning; Reinforcement; Computer science; Psychology; Programming language; Artificial intelligence; Social psychology","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":[0.005119144,0.0007258758,0.0008245686,0.003742374,0.0006097595,0.001807792,0.001889379,0.001488924,0.01381685],"category_scores_gemma":[0.0300661,0.0004713754,0.0005706286,0.005038124,0.001073222,0.004406254,0.001335928,0.001428236,0.007171974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001588715,"about_ca_system_score_gemma":0.004565074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005223876,"about_ca_topic_score_gemma":0.005382127,"domain_scores_codex":[0.997029,0.0007631836,0.0002983131,0.0003477125,0.001410014,0.0001517797],"domain_scores_gemma":[0.9622125,0.01544013,0.001445147,0.001553624,0.01822058,0.001128006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005851763,0.00004826253,0.000337957,0.007476669,0.00004603214,0.00004247042,0.0001239317,0.001376317,0.0007480973,0.003980011,0.2321426,0.7536191],"study_design_scores_gemma":[0.00001471521,0.0001186449,0.001031164,0.004016165,0.00006788728,0.0001856589,0.0001282562,0.001386016,0.001516724,0.001772722,0.9897307,0.00003139949],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"commentary","genre_scores_codex":[0.003784859,0.8490828,0.05414368,0.05069131,0.01232023,0.0002999925,0.0008125477,0.002103145,0.02676137],"genre_scores_gemma":[0.02909268,0.8733307,0.03072169,0.01612262,0.00914395,0.0003327079,0.002451647,0.001373542,0.03743035],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.01381685,"threshold_uncertainty_score":0.04622203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03996985594023222,"score_gpt":0.3369271904147481,"score_spread":0.2969573344745159,"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."}}