{"id":"W4413640367","doi":"10.1109/compsac65507.2025.00178","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Code generation; Code (set theory); Programming language; Software engineering; Operating system","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":[0.006881955,0.00256942,0.001283323,0.003046178,0.0006545513,0.002188104,0.003288663,0.001580888,0.002576803],"category_scores_gemma":[0.070202,0.00105017,0.0009461566,0.001213015,0.001256124,0.004258795,0.003348477,0.002395983,0.001789272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001367777,"about_ca_system_score_gemma":0.003492985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002903819,"about_ca_topic_score_gemma":0.004926231,"domain_scores_codex":[0.9895192,0.003217757,0.0007026591,0.001644589,0.004401467,0.0005142541],"domain_scores_gemma":[0.9488879,0.02772707,0.004340946,0.008326548,0.00970976,0.00100769],"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":[0.0009618684,0.001212681,0.0212736,0.0008711268,0.0001561758,0.0004151455,0.001321382,0.1337031,0.07119501,0.003776048,0.01388231,0.7512317],"study_design_scores_gemma":[0.0001260359,0.0003795849,0.002063617,0.00006780696,0.00005720541,0.0001644263,0.0001522871,0.9551924,0.03293676,0.004900522,0.003893274,0.00006598653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1540348,0.001022585,0.7617103,0.001549592,0.0001805338,0.000875009,0.0006957799,0.07565252,0.004278685],"genre_scores_gemma":[0.5263819,0.0001991941,0.4628181,0.000666645,0.00009402922,0.0006882308,0.001806461,0.00506055,0.002284972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006881955,"threshold_uncertainty_score":0.03639567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03443670114263099,"score_gpt":0.2833394831243433,"score_spread":0.2489027819817123,"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."}}