{"id":"W7082245200","doi":"10.48448/jv84-fv20","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Pipeline (software); Code (set theory); Construct (python library); Preference; Process (computing)","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":[0.00301552,0.002711704,0.0009653498,0.001283159,0.0004215341,0.00161407,0.003613897,0.001765211,0.009284564],"category_scores_gemma":[0.0192335,0.0009264745,0.00121954,0.0006775812,0.001429845,0.002717551,0.002433209,0.003751177,0.004974185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001603758,"about_ca_system_score_gemma":0.003202124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006778867,"about_ca_topic_score_gemma":0.01094467,"domain_scores_codex":[0.9967907,0.001093612,0.0001672023,0.0008472727,0.0008040244,0.0002972333],"domain_scores_gemma":[0.9921887,0.004076102,0.000384698,0.002063107,0.001025429,0.0002619698],"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":[0.0006604185,0.0005887851,0.007620165,0.0007962108,0.0002143747,0.0005098116,0.0002339595,0.4663075,0.01694916,0.00998895,0.05067218,0.4454586],"study_design_scores_gemma":[0.0001256363,0.0001268836,0.0003090282,0.00003564297,0.00001656735,0.00006338685,0.00002644906,0.9802889,0.008257902,0.004601576,0.006131793,0.00001639502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1225265,0.002366093,0.6647786,0.001546773,0.0005773215,0.0007650052,0.003008581,0.1861856,0.01824547],"genre_scores_gemma":[0.5450312,0.0004028233,0.4278477,0.00133476,0.0001009826,0.0008512486,0.0084193,0.008840715,0.007171401],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009284564,"threshold_uncertainty_score":0.03105992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177800085041945,"score_gpt":0.257227693440601,"score_spread":0.2454496925901816,"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."}}