{"id":"W4323266611","doi":"10.1016/j.artint.2023.103897","title":"Temporal logic explanations for dynamic decision systems using anchors and Monte Carlo Tree Search","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Black box; Monte Carlo tree search; Artificial intelligence; Decision tree; Machine learning; Monte Carlo method; State (computer science); Artificial neural network; Tree (set theory); Perception; Control (management); Complex system; Theoretical computer science; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002838751,0.00075756,0.001234455,0.001661756,0.0008892945,0.002057065,0.001783558,0.002041883,0.01075146],"category_scores_gemma":[0.02266157,0.0006574838,0.001490775,0.00110511,0.001819688,0.004367589,0.002224086,0.003103541,0.0006756361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001795305,"about_ca_system_score_gemma":0.001669989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005740299,"about_ca_topic_score_gemma":0.007044167,"domain_scores_codex":[0.9984799,0.0006479784,0.00009819316,0.0002760595,0.0003515001,0.0001463728],"domain_scores_gemma":[0.9851452,0.01263953,0.0006604468,0.0006555059,0.0006265281,0.0002727197],"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":[0.0001490849,0.00007923383,0.0008186585,0.0001097031,0.00006693418,0.0001815169,0.0002098608,0.5707392,0.0004354419,0.3909638,0.00269985,0.03354674],"study_design_scores_gemma":[0.00001019982,0.000007776661,0.00004324079,0.00001185267,0.000006524138,0.000009501414,0.00001066297,0.8459181,0.00009213958,0.1535998,0.0002840853,0.000006099973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01598907,0.0001877727,0.9792867,0.0007565477,0.00007140854,0.00004447523,0.0002086976,0.00037913,0.003076141],"genre_scores_gemma":[0.790867,0.0002950147,0.2030075,0.0003067993,0.0001577793,0.0001814891,0.0006505211,0.0001863312,0.004347588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01075146,"threshold_uncertainty_score":0.03596723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1235831946043025,"score_gpt":0.3831200242106715,"score_spread":0.259536829606369,"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."}}