{"id":"W3041899234","doi":"10.1109/itsc45102.2020.9294213","title":"Explainability of Intelligent Transportation Systems using Knowledge Compilation: a Traffic Light Controller Case","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Air Force Office of Scientific Research; Office of Naval Research; Division of Electrical, Communications and Cyber Systems; Advanced Research Projects Agency; National Institutes of Health; National Science Foundation","keywords":"Controller (irrigation); Computer science; State (computer science); Black box; Representation (politics); Control (management); Traffic signal; Intelligent transportation system; Action (physics); Real-time computing; Control engineering; Artificial intelligence; Transport engineering; Engineering; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008711906,0.0005039041,0.001020538,0.0002890473,0.0001922782,0.00028409,0.001158506,0.000374688,0.00003857732],"category_scores_gemma":[0.0001041018,0.0004904964,0.0003861187,0.0007112019,0.0001130271,0.0004473513,0.000289903,0.0005613106,0.00004617546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003635513,"about_ca_system_score_gemma":0.0005181269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007333294,"about_ca_topic_score_gemma":0.0004569647,"domain_scores_codex":[0.9957435,0.0004092595,0.001730898,0.001211478,0.0004717745,0.00043307],"domain_scores_gemma":[0.9966881,0.0003060394,0.0006985666,0.001071324,0.0009739923,0.0002619549],"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":[0.0001038715,0.0006851102,0.0001715843,0.002237811,0.0002301011,0.0008853805,0.03519128,0.8376321,0.001451696,0.1118747,0.0003486019,0.009187759],"study_design_scores_gemma":[0.0001716104,0.00009435979,0.00003126763,0.0002312599,0.00007072571,0.00009990989,0.001934184,0.9853899,0.008608337,0.002115696,0.0007656452,0.000487039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1389931,0.000998291,0.8551108,0.0005033057,0.001468344,0.001782966,0.00004812621,0.0003396448,0.0007554502],"genre_scores_gemma":[0.9889423,0.0000207104,0.01058579,0.00003592658,0.0001763253,0.0001031986,0.0000293123,0.000030425,0.00007602823],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8499492,"threshold_uncertainty_score":0.9997547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1011619418833305,"score_gpt":0.3258268616807003,"score_spread":0.2246649197973697,"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."}}