{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02420363,0.0004598855,0.002689329,0.0003983632,0.0002152955,0.0001949665,0.004664835,0.0004512361,4.463808e-7],"category_scores_gemma":[0.00249768,0.0003018246,0.0002859263,0.004233078,0.00007560143,0.0001215885,0.001867332,0.001048172,0.000005353782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273688,"about_ca_system_score_gemma":0.0005869198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006528913,"about_ca_topic_score_gemma":0.00001400628,"domain_scores_codex":[0.9866039,0.01058807,0.001397264,0.0007614369,0.0002952285,0.0003541278],"domain_scores_gemma":[0.9859893,0.01023698,0.0009396999,0.0025724,0.0002304347,0.00003116992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[7.240207e-8,0.00003617672,0.00002059967,0.7119082,0.00006311138,0.000007692264,0.0001040282,0.000001251685,3.576129e-8,0.005108516,0.00001641925,0.2827339],"study_design_scores_gemma":[0.00007472459,0.00000633415,0.0002760331,0.9889358,0.0001102957,0.00005576884,0.000003571235,0.0003413412,0.000001821139,0.0006853059,0.00922112,0.0002878971],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000008214607,0.9103828,0.08668094,0.00005258816,0.0001919001,0.00246191,0.00000545672,0.0001434218,0.00007276495],"genre_scores_gemma":[0.0007484073,0.9926068,0.006216871,0.00004232463,0.00001187326,0.000303777,0.00004247849,0.00001756769,0.000009898548],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.282446,"threshold_uncertainty_score":0.9999434,"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."}}