{"id":"W6912291614","doi":"10.5281/zenodo.15485472","title":"Reproduction Package for CAV 2025 Article `Btor2-Select: Machine Learning Based Algorithm Selection for Hardware Model Checking'","year":2025,"lang":"en","type":"other","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":"Artifact (error); Selection (genetic algorithm); Login; Set (abstract data type); Selection algorithm; Test data","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001327594,0.0003581778,0.0003603381,0.0006574602,0.002336297,0.00090768,0.001515187,0.0002576988,0.001597417],"category_scores_gemma":[0.002352202,0.0004146037,0.0001592995,0.0009872204,0.00007709115,0.0003091098,0.0008501164,0.0007017679,0.0003546652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003582275,"about_ca_system_score_gemma":0.00004650965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008194391,"about_ca_topic_score_gemma":0.000002728555,"domain_scores_codex":[0.9968506,0.0003972602,0.0003782475,0.00131623,0.0004448674,0.0006128273],"domain_scores_gemma":[0.9977455,0.00008126839,0.0003833472,0.0007949896,0.0008573415,0.0001375812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009786832,0.0001542453,0.000003275727,0.0004409811,0.0001320607,0.000002495784,0.0003607539,0.04515981,0.0009306238,0.004943338,0.5296514,0.4181231],"study_design_scores_gemma":[0.000544299,0.0001352217,0.000002455631,0.00006910964,0.0000280524,0.000005879653,0.00001156735,0.5041687,0.0005012086,0.0002157248,0.4940995,0.0002183216],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000003187558,0.0001812552,0.9555376,0.0007902995,0.0003570764,0.00143067,0.0002388795,0.002674028,0.03878696],"genre_scores_gemma":[0.003356253,0.0001355966,0.4486555,0.0003245518,0.001782833,0.000005240334,0.006150738,0.009561182,0.5300282],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5068822,"threshold_uncertainty_score":0.9998306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02541640956097876,"score_gpt":0.2612174019710267,"score_spread":0.235800992410048,"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."}}