{"id":"W3168797207","doi":"10.1016/j.neunet.2021.05.035","title":"IGAGCN: Information geometry and attention-based spatiotemporal graph convolutional networks for traffic flow prediction","year":2021,"lang":"en","type":"article","venue":"Neural Networks","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Traffic flow (computer networking); Data mining; Graph; Dynamic data; Artificial intelligence; Algorithm; Theoretical computer science","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":[0.0004784076,0.001014138,0.0008419168,0.0008542532,0.0004013056,0.0006652314,0.002045851,0.001039104,0.002224159],"category_scores_gemma":[0.001595583,0.0004372048,0.0006131578,0.001217816,0.0004868669,0.001346135,0.001190428,0.001663049,0.0006529354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605706,"about_ca_system_score_gemma":0.001529934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06248909,"about_ca_topic_score_gemma":0.07253317,"domain_scores_codex":[0.9998142,0.00002346956,0.000007085447,0.00007658372,0.00004122935,0.00003748016],"domain_scores_gemma":[0.9996095,0.0001308864,0.00003386005,0.00007906309,0.0001136299,0.00003302548],"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":[0.0002729104,0.0002035283,0.002096795,0.0001098831,0.0001358067,0.0001279768,0.00006458754,0.5768202,0.006906283,0.01357968,0.0235063,0.3761761],"study_design_scores_gemma":[0.000003711177,0.000009114501,0.000152525,0.00000340546,0.00000563771,0.000005638135,0.000003144065,0.9956155,0.0006768679,0.00309278,0.0004288326,0.000002745209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07799357,0.001936519,0.9009709,0.0008522373,0.000349329,0.0001196867,0.002792374,0.01138285,0.003602465],"genre_scores_gemma":[0.727275,0.0009974125,0.2552222,0.0005052507,0.0001687147,0.0001713985,0.005891958,0.0004621793,0.009305883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06248909,"threshold_uncertainty_score":0.1242507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006599637297802789,"score_gpt":0.1899184373335769,"score_spread":0.1833188000357741,"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."}}