{"id":"W7123349179","doi":"10.1109/esem64174.2025.00058","title":"A Fully Automated Agent for End-to-End Code Translation and Validation","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Correctness; Java; Code (set theory); Program comprehension; Source code; Static program analysis; Software; Code generation; Software development","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":[0.004652232,0.001211057,0.0006427795,0.0009641819,0.0006168678,0.001751715,0.002004752,0.001555395,0.00795409],"category_scores_gemma":[0.0199112,0.0008026727,0.0008734347,0.0002837462,0.001056532,0.002222078,0.00324578,0.00185344,0.006016936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006436009,"about_ca_system_score_gemma":0.001849513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009370047,"about_ca_topic_score_gemma":0.0008521967,"domain_scores_codex":[0.9960325,0.001560184,0.0003573294,0.0006956676,0.001163446,0.0001908821],"domain_scores_gemma":[0.9822909,0.007456358,0.001591328,0.00471757,0.003379253,0.0005645417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002391786,0.001777086,0.01133228,0.001191397,0.0002894532,0.001658212,0.003436361,0.0488322,0.2135722,0.01864542,0.03991983,0.6569537],"study_design_scores_gemma":[0.0003415777,0.0007692673,0.00254213,0.0002273771,0.0001086916,0.0008710138,0.000299389,0.7350531,0.1419497,0.01051971,0.1071465,0.0001715236],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01988054,0.00006428839,0.9042389,0.0002290557,0.00008035367,0.0007265544,0.0002399256,0.07164972,0.002890639],"genre_scores_gemma":[0.1186657,0.00006060875,0.8697848,0.0003338816,0.00003511185,0.0008274596,0.001028838,0.004571859,0.004691725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00795409,"threshold_uncertainty_score":0.02660906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04136943109915722,"score_gpt":0.3246982982946076,"score_spread":0.2833288671954504,"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."}}