{"id":"W3184919107","doi":"10.1007/978-3-030-81685-8_29","title":"Effective Hybrid System Falsification Using Monte Carlo Tree Search Guided by QB-Robustness","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Exploratory Research for Advanced Technology; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Robustness (evolution); Computer science; Tree traversal; Scalability; Computation; Theoretical computer science; Mathematical optimization; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":"high","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002883406,0.0006942523,0.0008043412,0.0008411841,0.0004805565,0.0009494227,0.003996236,0.000380312,0.00000468417],"category_scores_gemma":[0.0002281107,0.0006933527,0.0001932704,0.001160373,0.0006588476,0.001119639,0.001433813,0.001026739,0.00001680027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001748572,"about_ca_system_score_gemma":0.0007135888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001232559,"about_ca_topic_score_gemma":0.00001538113,"domain_scores_codex":[0.9938552,0.0003693073,0.0008690912,0.002388818,0.001661695,0.0008558977],"domain_scores_gemma":[0.9952198,0.0005771227,0.0005137742,0.002518785,0.000939573,0.0002309638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001047141,0.00006103582,0.0000212886,0.0003012038,0.00003473471,0.0001197307,0.0006748031,0.3195237,0.005328625,0.01777147,0.00004668213,0.6561062],"study_design_scores_gemma":[0.0002830347,0.0001102029,0.00005712952,0.0007276792,0.00001761056,0.0002805852,0.000001266983,0.9671872,0.02961255,0.0008327576,0.0001993942,0.0006906271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002450614,0.000897541,0.9914581,0.000135786,0.002623054,0.001087857,0.00001704826,0.0002863217,0.00104367],"genre_scores_gemma":[0.164584,0.00002514875,0.8345094,0.0001553647,0.0003843918,0.00004106267,0.0000124703,0.00005979725,0.0002283572],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6554156,"threshold_uncertainty_score":0.9995518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04106848967663938,"score_gpt":0.3003669894834916,"score_spread":0.2592984998068522,"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."}}