{"id":"W3096106171","doi":"10.1109/hccai49649.2020.00008","title":"Extending the learning shout-ahead architecture with user-defined exception rules – a case study for traffic light controls","year":2020,"lang":"en","type":"article","venue":"","topic":"Traffic control and management","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Architecture; Computer science; Artificial intelligence; Human–computer interaction; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009996464,0.0006717482,0.0003913273,0.000247757,0.0003877385,0.000827598,0.001656338,0.001024773,0.002458737],"category_scores_gemma":[0.002747706,0.0003008365,0.0004271218,0.0001579145,0.0008526248,0.001257752,0.001060292,0.001562724,0.0004812222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004584086,"about_ca_system_score_gemma":0.001079055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00762991,"about_ca_topic_score_gemma":0.008918133,"domain_scores_codex":[0.999371,0.000145397,0.00004374497,0.0001440342,0.0001969309,0.00009892125],"domain_scores_gemma":[0.9986919,0.0005042634,0.00006679389,0.0003478753,0.0002936415,0.00009561388],"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":[0.0008826522,0.00109158,0.009610974,0.0003368513,0.0001305841,0.001350218,0.0009654748,0.7171093,0.03282651,0.009249578,0.002363517,0.2240828],"study_design_scores_gemma":[0.00005040822,0.0003051621,0.001063778,0.00002173307,0.00003483643,0.0001859236,0.00009117457,0.966538,0.0222614,0.004141421,0.005273656,0.00003251147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5314699,0.0002828954,0.4484063,0.0004338007,0.0001294286,0.0004036594,0.0001727093,0.006136263,0.01256501],"genre_scores_gemma":[0.8929191,0.00009109679,0.1012917,0.000128054,0.00001279338,0.00008289626,0.0001528751,0.0001277667,0.00519375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00762991,"threshold_uncertainty_score":0.01517099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.015380023823975,"score_gpt":0.2248456350153688,"score_spread":0.2094656111913938,"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."}}