{"id":"W4400485071","doi":"10.1145/3664646.3664777","title":"Effectiveness of ChatGPT for Static Analysis: How Far Are We?","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007086535,0.0001130448,0.0002786241,0.0002932008,0.00005074647,0.0001442126,0.0004871207,0.00004081618,0.00001213608],"category_scores_gemma":[0.0001328484,0.00009084662,0.0001869223,0.001201857,0.00002790388,0.000362019,0.0001483203,0.0001003966,0.00000463752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003588442,"about_ca_system_score_gemma":0.00004312063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001768492,"about_ca_topic_score_gemma":0.000007665263,"domain_scores_codex":[0.9989699,0.0001590418,0.0001283195,0.0003664308,0.0001984723,0.0001778107],"domain_scores_gemma":[0.9984531,0.001015306,0.00006546101,0.0003510671,0.00007636314,0.00003872677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004187564,0.00007679372,0.00356328,0.003395067,0.002195883,0.00004022699,0.001757683,0.3451392,0.001432072,0.5969604,0.0004337947,0.04496371],"study_design_scores_gemma":[0.000164922,0.00005678964,0.002448222,0.0001185567,0.0001717066,0.000001127038,0.00009386861,0.9882518,0.001278468,0.006445731,0.0008437549,0.0001250215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00298788,0.0003280283,0.9943832,0.001361528,0.0003212034,0.0002200655,0.000004327009,0.0002070754,0.0001867288],"genre_scores_gemma":[0.935324,0.000008455515,0.06420432,0.00002069704,0.0000262976,0.00003434636,0.000003241107,0.00000997185,0.0003687157],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9323361,"threshold_uncertainty_score":0.3704618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01700652742124443,"score_gpt":0.2973846887178617,"score_spread":0.2803781612966172,"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."}}