{"id":"W2904101382","doi":"10.1007/978-3-030-30281-8_10","title":"Fast Falsification of Hybrid Systems Using Probabilistically Adaptive Input","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Margin (machine learning); Computer science; Discretization; Key (lock); Tree (set theory); Feature (linguistics); Las vegas; Hybrid system; Artificial intelligence; Algorithm; Theoretical computer science; Mathematics; Machine learning","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":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","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":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002868182,0.0004235804,0.0006587257,0.0007555539,0.0001266311,0.0005276575,0.004734278,0.0002209548,0.000001430979],"category_scores_gemma":[0.0006638198,0.0004005067,0.0001112576,0.001634016,0.0007105326,0.000734551,0.003176907,0.0008586838,0.00001333194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006088398,"about_ca_system_score_gemma":0.001282767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001525447,"about_ca_topic_score_gemma":0.000003489071,"domain_scores_codex":[0.9951538,0.0004023256,0.0009612185,0.001724303,0.001173124,0.0005851949],"domain_scores_gemma":[0.9951096,0.0004690435,0.0008713001,0.002572729,0.000857126,0.0001202082],"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":[0.000008603268,0.00009449077,0.0002119974,0.0002295865,0.000007344802,0.000003975442,0.0006162429,0.9138051,0.002454162,0.009065997,8.91728e-7,0.07350157],"study_design_scores_gemma":[0.0001517612,0.0001502528,0.00066331,0.0005399568,0.000007981211,0.00004099985,0.000001012575,0.9638826,0.01669095,0.01747962,0.000005145663,0.0003864602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0297663,0.0001562979,0.9640003,0.00006893724,0.004614824,0.001222042,0.0000129153,0.0001228699,0.00003554951],"genre_scores_gemma":[0.4943238,0.000004154042,0.505505,0.00004107203,0.00009467878,0.00001858179,0.000002486626,0.000009961524,3.246668e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4645575,"threshold_uncertainty_score":0.9998447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05059250578223105,"score_gpt":0.3049642944555652,"score_spread":0.2543717886733342,"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."}}