{"id":"W4411241451","doi":"10.1145/3744553","title":"Assessing the Effectiveness of ChatGPT in Secure Code Development: A Systematic Literature Review","year":2025,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Outaouais","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Systematic review; Code (set theory); Programming language; Software engineering; MEDLINE","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01525275,0.001134888,0.004161607,0.01482745,0.0006961779,0.002597873,0.002182933,0.001488578,0.005148533],"category_scores_gemma":[0.07694162,0.001028038,0.003423643,0.01318894,0.001211489,0.00411022,0.002288189,0.001473163,0.0009307452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002763382,"about_ca_system_score_gemma":0.01734696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006357058,"about_ca_topic_score_gemma":0.02039643,"domain_scores_codex":[0.9920605,0.002970023,0.002212936,0.0006593029,0.001886599,0.0002105996],"domain_scores_gemma":[0.9067228,0.07397299,0.007629923,0.001393527,0.009448416,0.0008322924],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001680705,0.00005220489,0.001344444,0.6380163,0.001908842,0.0001063549,0.0006105867,0.0002301948,0.0002910863,0.0008725876,0.00432337,0.352076],"study_design_scores_gemma":[0.00009936819,0.0003313693,0.005423992,0.8936366,0.01405936,0.0004734768,0.0009095032,0.0001922881,0.0004996978,0.0008173778,0.08349899,0.00005799197],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009035671,0.9974179,0.0003989078,0.0003330787,0.00006912594,0.0001444711,0.0001821395,0.00001565188,0.0005351414],"genre_scores_gemma":[0.006874523,0.9913439,0.0009354318,0.0002869916,0.00004243951,0.0002282935,0.0001857456,0.00001286865,0.00008982072],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9847472,"threshold_uncertainty_score":0.08066523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02705706420670426,"score_gpt":0.344935638852457,"score_spread":0.3178785746457528,"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."}}