{"id":"W7134957359","doi":"10.1109/icdmw69685.2025.00164","title":"Security Charter Effectiveness in Large Language Model Code Generation: A Multi-Phase Experimental Analysis Revealing Task-Dependent Responsiveness and Architectural Differences","year":2025,"lang":"","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Charter; Code (set theory); Key (lock); Modeling language; Semantics (computer science); Code-switching","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":[0.01808183,0.0010993,0.0008200497,0.00060639,0.0003984857,0.002015739,0.001294181,0.0010089,0.00243249],"category_scores_gemma":[0.1148859,0.0005552809,0.0006397369,0.0003994291,0.001081705,0.00303472,0.002052306,0.00223028,0.001144901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007092148,"about_ca_system_score_gemma":0.001053682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001091629,"about_ca_topic_score_gemma":0.0009932792,"domain_scores_codex":[0.9868117,0.008537625,0.001013918,0.001916283,0.001347578,0.000372934],"domain_scores_gemma":[0.8881164,0.09551155,0.004373876,0.008387701,0.002287633,0.001322787],"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":[0.04392203,0.01061632,0.04998676,0.002282969,0.001279825,0.0003437661,0.008778602,0.0934465,0.1260376,0.004976752,0.01361149,0.6447175],"study_design_scores_gemma":[0.008824706,0.09083862,0.154274,0.0006411987,0.001411685,0.0006979792,0.003638576,0.5100685,0.1732356,0.02127735,0.0341055,0.0009862178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665195,0.0004628796,0.02550445,0.0003103282,0.0001440796,0.000738595,0.0003971262,0.002407345,0.003515744],"genre_scores_gemma":[0.9703159,0.0001449416,0.02399019,0.0003095115,0.00004751539,0.001215634,0.0009149504,0.0006789628,0.002382308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01808183,"threshold_uncertainty_score":0.09562701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620770453928511,"score_gpt":0.3530747111129729,"score_spread":0.3268670065736878,"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."}}