{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003963375,0.001408332,0.001430913,0.001338441,0.000761795,0.001783001,0.002077904,0.002084796,0.0039291],"category_scores_gemma":[0.02288067,0.0007291641,0.001190551,0.0006200378,0.003001287,0.002473329,0.003114452,0.001899112,0.0004544114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123736,"about_ca_system_score_gemma":0.001732754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002215152,"about_ca_topic_score_gemma":0.002380888,"domain_scores_codex":[0.9978305,0.0007836292,0.0001272202,0.0003530622,0.0006599873,0.0002456722],"domain_scores_gemma":[0.9810628,0.01533556,0.001243475,0.001154938,0.0008715194,0.0003317553],"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":[0.0002207259,0.00004104776,0.001816558,0.0001142102,0.00006369819,0.0001718667,0.0001237649,0.9338158,0.002261022,0.0250412,0.00051793,0.03581215],"study_design_scores_gemma":[0.00001603303,0.0000303436,0.00005579105,0.00001035899,0.000006133507,0.00002572373,0.00001303375,0.9857888,0.0008708348,0.01301198,0.0001646735,0.000006288991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04980948,0.0001590395,0.9463061,0.0002326595,0.00002551148,0.00008284843,0.00005244495,0.001287285,0.002044609],"genre_scores_gemma":[0.7960973,0.00005967931,0.2021963,0.0001277492,0.00001888276,0.0001457739,0.0001140933,0.0001916251,0.00104864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003963375,"threshold_uncertainty_score":0.02096063,"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."}}