{"id":"W3015337730","doi":"10.1016/j.cag.2020.03.005","title":"Predicting Crowd Egress and Environment Relationships to Support Building Design Optimization","year":2020,"lang":"en","type":"article","venue":"Computers & Graphics","topic":"Evacuation and Crowd Dynamics","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Rehabilitation Institute; York University; University Health Network","funders":"Ontario Research Foundation; National Science Foundation","keywords":"Computer science; Crowd simulation; Set (abstract data type); Range (aeronautics); Machine learning; Variety (cybernetics); Artificial neural network; Artificial intelligence; Network planning and design","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001622691,0.000119006,0.000101494,0.00008569838,0.0001246104,0.00006774501,0.00009640631,0.00006774898,0.000009163236],"category_scores_gemma":[0.00003107282,0.000141034,0.00002511725,0.0002123467,0.00002146351,0.0001212813,0.00004966962,0.0001787234,0.000006555042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002670933,"about_ca_system_score_gemma":0.000007180011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.256444e-7,"about_ca_topic_score_gemma":5.207075e-7,"domain_scores_codex":[0.9993178,0.00003818032,0.0001901008,0.0001775559,0.0001328893,0.0001435359],"domain_scores_gemma":[0.9995832,0.00009614741,0.00002685353,0.000103532,0.00001518358,0.0001751177],"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":[0.000003228997,0.000003924905,0.003874653,0.00002134435,0.00001626833,0.000002386845,0.0007812012,0.9922262,0.0001203402,0.00112013,0.000450029,0.00138026],"study_design_scores_gemma":[0.0001584336,0.00005212277,0.001819072,0.00001696698,0.00001545575,0.000003231117,0.00003657712,0.9970145,0.00008059732,0.0001041444,0.0005563345,0.0001425636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03587643,0.00006552981,0.9628929,0.0005008302,0.0001311142,0.0001852922,0.000004133142,0.0002755022,0.0000682084],"genre_scores_gemma":[0.7866318,0.0001154928,0.2127009,0.0004261609,0.00006456766,0.000009559249,0.00001789233,0.00003009885,0.000003626495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7507553,"threshold_uncertainty_score":0.5751199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03789344458040938,"score_gpt":0.2178261059410697,"score_spread":0.1799326613606604,"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."}}