{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01144251,0.002452062,0.001950518,0.002180653,0.0009334997,0.002545253,0.002825516,0.002541888,0.002525463],"category_scores_gemma":[0.05419636,0.0006678095,0.0009680668,0.0008445257,0.00199659,0.007452202,0.003103544,0.003000556,0.002338815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001165585,"about_ca_system_score_gemma":0.001712484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003190731,"about_ca_topic_score_gemma":0.003349086,"domain_scores_codex":[0.9896389,0.005123605,0.0003828376,0.002046894,0.002291872,0.0005158372],"domain_scores_gemma":[0.951912,0.03152313,0.002229751,0.01015454,0.003096835,0.001083854],"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":[0.003708192,0.0008448785,0.04103728,0.001704486,0.0007666629,0.0007463041,0.00105691,0.1157793,0.03199326,0.008939608,0.03542013,0.758003],"study_design_scores_gemma":[0.0002318547,0.001758879,0.01051589,0.0003368113,0.0003799196,0.001114198,0.0004915163,0.9306808,0.0248716,0.01351739,0.01590761,0.0001936186],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4146002,0.02102913,0.4695674,0.007720416,0.001748456,0.0006482319,0.001874612,0.06641728,0.01639427],"genre_scores_gemma":[0.9077764,0.001379099,0.08295448,0.001497583,0.0004438446,0.0001929571,0.001290867,0.001376417,0.003088515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01144251,"threshold_uncertainty_score":0.06051451,"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."}}