{"id":"W3185643228","doi":"10.1145/3459605","title":"Falsification of Hybrid Systems Using Adaptive Probabilistic Search","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Modeling and Computer Simulation","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Japan Science and Technology Agency; Japan Society for the Promotion of Science","keywords":"Probabilistic logic; Computer science; Robustness (evolution); Discriminative model; Exploit; Baseline (sea); Discretization; Algorithm; Key (lock); Tree traversal; Tree (set theory); Mathematical optimization; Machine learning; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002098555,0.0001065609,0.0001509071,0.000116395,0.0001921454,0.0001077987,0.0001911131,0.00003381721,0.000001294241],"category_scores_gemma":[0.00001182945,0.0001087199,0.00004766035,0.0002370503,0.0000167353,0.0002191957,0.00001821484,0.0001615716,0.000001739093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002958483,"about_ca_system_score_gemma":0.00005945706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007582865,"about_ca_topic_score_gemma":7.204037e-7,"domain_scores_codex":[0.9988828,0.0001565713,0.0002540237,0.0003527371,0.0002250781,0.0001287598],"domain_scores_gemma":[0.9989777,0.00017951,0.00005729059,0.0004503606,0.0002855348,0.00004964295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000556017,0.00007712231,0.000005307033,0.00002575959,0.00001487507,0.000001824,0.0002444934,0.9309022,0.00007032356,0.0009619223,1.593185e-7,0.06769049],"study_design_scores_gemma":[0.0002492976,0.00009743077,0.00001762899,0.00007709061,0.00001348816,0.00001950418,0.00002776208,0.9977935,0.0002160243,0.001377781,0.000003514651,0.0001069943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1311788,0.00008031986,0.8682694,0.00006867898,0.0002133764,0.0001011489,0.000003038178,0.00007496605,0.00001024875],"genre_scores_gemma":[0.8446187,0.000007744777,0.1552845,0.00001614936,0.00004383307,0.000003268337,0.000004010358,0.000006993,0.00001472367],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7134399,"threshold_uncertainty_score":0.4433469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666532214771873,"score_gpt":0.298929233412535,"score_spread":0.2322760119353477,"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."}}