{"id":"W6912068948","doi":"10.5281/zenodo.15605218","title":"Performance Dataset for Hardware Model Checking on Btor2 Benchmarks (Technical Report, May 2025)","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Set (abstract data type); Construct (python library); Scripting language; Selection (genetic algorithm)","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001315455,0.0001870104,0.0001908546,0.000285153,0.002261386,0.000755815,0.002515098,0.0001009085,0.000665683],"category_scores_gemma":[0.001536604,0.0001974408,0.00006442336,0.0006495485,0.0001009729,0.0005748355,0.002760393,0.0004909005,0.0003945363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002230094,"about_ca_system_score_gemma":0.00001896693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004681141,"about_ca_topic_score_gemma":1.496909e-7,"domain_scores_codex":[0.9978575,0.0001677452,0.0003638385,0.0007556237,0.0004140497,0.000441309],"domain_scores_gemma":[0.9981475,0.00007339117,0.0001635243,0.001156091,0.0003443678,0.0001150627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001228652,0.0001655983,0.00001721216,0.0001750578,0.00004768968,0.00005463251,0.0003416849,0.07877757,0.001082263,0.05614371,0.739562,0.1235097],"study_design_scores_gemma":[0.0003417988,0.0001000004,0.0001433531,0.00006366096,0.000009249973,0.00004963178,0.00001739194,0.39929,0.0001995949,0.000300669,0.599325,0.0001596271],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001302797,0.00002090536,0.9231526,0.002146031,0.0002650353,0.0005857843,0.000321399,0.0007526601,0.07145277],"genre_scores_gemma":[0.9085866,0.00005803195,0.06528392,0.001083923,0.0003110844,8.922036e-7,0.01823092,0.001079932,0.00536469],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9072838,"threshold_uncertainty_score":0.9990376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03964419333641551,"score_gpt":0.2992744602368088,"score_spread":0.2596302669003933,"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."}}