{"id":"W4410537502","doi":"10.1145/3736407","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Coding (social sciences); Natural language processing; Artificial intelligence; Programming language; Statistics; Mathematics","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":[0.004622301,0.003275343,0.0008615781,0.001906073,0.001207936,0.001802578,0.002473565,0.002916135,0.007415007],"category_scores_gemma":[0.03073069,0.0005495879,0.001310533,0.001393273,0.001110955,0.002788967,0.002731407,0.003509878,0.008638643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001614277,"about_ca_system_score_gemma":0.002072805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01069346,"about_ca_topic_score_gemma":0.02915876,"domain_scores_codex":[0.9922357,0.003972553,0.0005622721,0.001456801,0.00140093,0.0003716477],"domain_scores_gemma":[0.9853184,0.008112648,0.0006775443,0.002442835,0.002658139,0.0007904847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002893943,0.001864627,0.02692045,0.003214469,0.0005139376,0.001126031,0.00279384,0.04178644,0.03892606,0.005330113,0.5992308,0.2753994],"study_design_scores_gemma":[0.001701753,0.00253443,0.04101764,0.0005626281,0.0002496949,0.001476216,0.002836728,0.5703126,0.05678223,0.01527173,0.3065495,0.0007048442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.407223,0.004532687,0.1453948,0.004032886,0.002372841,0.003202879,0.2473659,0.1524586,0.03341642],"genre_scores_gemma":[0.336225,0.0004527857,0.1273029,0.002258604,0.0002162049,0.003373704,0.5109161,0.006567552,0.01268712],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01069346,"threshold_uncertainty_score":0.02480561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0823360169353762,"score_gpt":0.3675850040090939,"score_spread":0.2852489870737177,"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."}}