{"id":"W6949165601","doi":"10.5281/zenodo.10828316","title":"Replication Package for \"Effectiveness of ChatGPT for Static Analysis: How Far Are We?\"","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Code (set theory); Replication (statistics); Software; Static analysis; Work (physics)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009070394,0.002268926,0.002019411,0.002997008,0.001376876,0.002569772,0.003963535,0.002212229,0.1696259],"category_scores_gemma":[0.06431497,0.001675649,0.00262053,0.002482802,0.001171036,0.004030962,0.004706929,0.004220884,0.0720488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001171692,"about_ca_system_score_gemma":0.002807582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004064351,"about_ca_topic_score_gemma":0.003413791,"domain_scores_codex":[0.9916862,0.003330471,0.000705093,0.001208978,0.002542512,0.000526758],"domain_scores_gemma":[0.9187332,0.05214575,0.002563206,0.01677199,0.00838284,0.001402949],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002122096,0.0003682617,0.003291883,0.001903633,0.0003696512,0.0002338587,0.0007180587,0.002358783,0.005407093,0.01114581,0.8629287,0.1091522],"study_design_scores_gemma":[0.002951517,0.001590427,0.01767914,0.001449535,0.000585984,0.0007808899,0.0003781041,0.05526473,0.03346948,0.04093513,0.8442899,0.0006251017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"dataset","genre_scores_codex":[0.008831625,0.0007256301,0.2198478,0.003472156,0.003061816,0.001024958,0.1177995,0.6166401,0.02859649],"genre_scores_gemma":[0.1060198,0.0009294497,0.340654,0.00334988,0.00150357,0.007324728,0.1454683,0.3390866,0.05566364],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.9909296,"threshold_uncertainty_score":0.5674552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03584212901976255,"score_gpt":0.2779436582832275,"score_spread":0.2421015292634649,"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."}}