{"id":"W1987289444","doi":"10.1145/1321631.1321691","title":"A buffer overflow benchmark for software model checkers","year":2007,"lang":"en","type":"article","venue":"","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Benchmark (surveying); Buffer overflow; Software; Buffer (optical fiber); Operating system; Telecommunications","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":[0.004925265,0.001638577,0.000713795,0.002580502,0.000879965,0.001134303,0.002683463,0.001064251,0.002696539],"category_scores_gemma":[0.01829492,0.0006594675,0.001072745,0.003808682,0.0008950143,0.002070996,0.001372028,0.001524951,0.0004235004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001575618,"about_ca_system_score_gemma":0.001982941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009278229,"about_ca_topic_score_gemma":0.01176068,"domain_scores_codex":[0.9942493,0.002415256,0.0005383376,0.0006174166,0.001615835,0.0005638152],"domain_scores_gemma":[0.9832696,0.01023388,0.0007259289,0.002834927,0.00251714,0.0004185422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002770544,0.002941917,0.03041736,0.002345137,0.0006712827,0.001349082,0.001159083,0.6287056,0.03726474,0.05231623,0.07952482,0.1605343],"study_design_scores_gemma":[0.0007838737,0.0008234967,0.006393041,0.0001276158,0.0001529692,0.0002856087,0.0002241279,0.904572,0.04356623,0.0231737,0.0198175,0.00007980762],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8196279,0.001812507,0.1194932,0.001012369,0.0002250156,0.0006464892,0.01142705,0.03211323,0.01364231],"genre_scores_gemma":[0.8377649,0.0005535943,0.1329025,0.0002325021,0.00004573242,0.0006377908,0.02283628,0.002414512,0.002612273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009278229,"threshold_uncertainty_score":0.02604759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03086025562768321,"score_gpt":0.2862900344783689,"score_spread":0.2554297788506857,"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."}}