{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005336025,0.00008743078,0.00008408802,0.00006178256,0.0001567214,0.0000898459,0.0005510832,0.00006106064,0.0000164899],"category_scores_gemma":[0.00008697464,0.00008380182,0.00007055295,0.0001935262,0.00001952097,0.0002605686,0.0001021138,0.00006811581,0.00001641038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003659025,"about_ca_system_score_gemma":0.00005488547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009471813,"about_ca_topic_score_gemma":0.000005479632,"domain_scores_codex":[0.9990732,0.000006488755,0.0001869291,0.0002949541,0.0001607556,0.000277636],"domain_scores_gemma":[0.9991807,0.0002132426,0.00004776713,0.0003789094,0.00009795006,0.00008142518],"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":[0.00002211907,0.0001179847,0.001140691,0.00004498738,0.00002427927,0.000002260522,0.002069163,0.0060382,0.0004651353,0.8763534,0.02799296,0.08572886],"study_design_scores_gemma":[0.0002330498,0.00002371408,0.0005858032,0.000006709434,0.000002073231,0.000003318004,0.00002569054,0.9721258,0.002733405,0.01676002,0.007349858,0.0001505331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004945528,0.00003911617,0.9902802,0.0003975884,0.0002853762,0.0001537442,0.000001309796,0.0002644389,0.00363277],"genre_scores_gemma":[0.3322551,0.000001415447,0.6660784,0.001067714,0.00007473398,0.000007469962,0.000002696653,0.000005015847,0.0005074482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9660876,"threshold_uncertainty_score":0.3417339,"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."}}