{"id":"W4393146415","doi":"10.1609/aaai.v38i20.30594","title":"Temporal Logic Explanations for Dynamic Decision Systems Using Anchors and Monte Carlo Tree Search (Abstract Reprint)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reprint; Computer science; Monte Carlo method; Tree (set theory); Computation tree logic; Decision tree; Theoretical computer science; Artificial intelligence; Temporal logic; Mathematics; Statistics; Combinatorics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009155541,0.0002177926,0.0002631763,0.0002216504,0.0002813794,0.0008081595,0.001103251,0.0001109032,0.000007681231],"category_scores_gemma":[0.0004117347,0.0001548703,0.0001216315,0.0005488036,0.0001836926,0.0005289827,0.0003172806,0.000266191,0.00001854721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001051374,"about_ca_system_score_gemma":0.0001643897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00014962,"about_ca_topic_score_gemma":0.00005250372,"domain_scores_codex":[0.9980758,0.00001503829,0.0005108211,0.0006724769,0.0003834292,0.0003423961],"domain_scores_gemma":[0.9985783,0.0002984042,0.0001676777,0.0002683716,0.000584559,0.0001026556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004859023,0.00007914067,0.0002833565,0.0002206551,0.00002699197,0.000002462419,0.002298998,0.0007772033,0.01460191,0.8651713,0.00009545704,0.116394],"study_design_scores_gemma":[0.00002829854,0.0001505225,0.000361606,0.0006622075,0.00001686897,0.00002008973,0.0009391513,0.9109674,0.01375286,0.07276878,0.0001199625,0.0002123209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7081295,0.0007386495,0.2837266,0.001109842,0.001500754,0.00119678,0.00001869813,0.0002272392,0.00335189],"genre_scores_gemma":[0.9930973,0.00008581369,0.006481476,0.00001660809,0.00007012852,0.00003802757,5.009225e-7,0.00001380363,0.0001963087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9101901,"threshold_uncertainty_score":0.77931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1264871103022022,"score_gpt":0.3503657921298592,"score_spread":0.223878681827657,"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."}}