{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003169328,0.002100318,0.001271159,0.002331486,0.0005730172,0.003297266,0.003698394,0.002088943,0.6008426],"category_scores_gemma":[0.02885018,0.001264961,0.001826858,0.001796887,0.0009448085,0.002904476,0.002931447,0.002514649,0.3450574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121492,"about_ca_system_score_gemma":0.001625351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002012512,"about_ca_topic_score_gemma":0.001975225,"domain_scores_codex":[0.996267,0.0005821381,0.0003442431,0.0005712797,0.001986106,0.0002492377],"domain_scores_gemma":[0.9858807,0.005675558,0.0005312989,0.004081156,0.003494425,0.0003368614],"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":[0.0003329899,0.00007658445,0.0002984307,0.0004804337,0.00003455186,0.0001400182,0.00006088297,0.002258028,0.003341002,0.009511549,0.878449,0.1050165],"study_design_scores_gemma":[0.0003815584,0.000234904,0.001204424,0.0003576682,0.00003359414,0.0004141949,0.00003666081,0.02498258,0.01551631,0.01551923,0.9411996,0.000119185],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"other","genre_scores_codex":[0.001095606,0.0002170754,0.28498,0.001004978,0.001662265,0.0005536075,0.03622823,0.6046115,0.06964675],"genre_scores_gemma":[0.02462003,0.0003867059,0.1514272,0.001570889,0.0009885499,0.001506262,0.1056345,0.52144,0.192426],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9968307,"threshold_uncertainty_score":0.5693496,"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."}}