{"id":"W4416809247","doi":"10.1016/j.ssci.2025.107063","title":"A traffic flow forecasting model based on dynamic graph learning and temporally adaptive attention","year":2025,"lang":"en","type":"article","venue":"Safety Science","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Technology Program of Gansu Province; National Natural Science Foundation of China","keywords":"Attention network; Graph; Intelligent transportation system; Traffic congestion; Traffic flow (computer networking); Adjacency list; Feature 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003768199,0.00009150222,0.00007420559,0.0003334366,0.0002505527,0.00004089021,0.0001157896,0.00002875492,0.000001318392],"category_scores_gemma":[0.00002585329,0.00009274863,0.00002686193,0.0005728556,0.0001149354,0.000191014,0.00003006663,0.0001358946,0.000001245366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007900497,"about_ca_system_score_gemma":0.0000313164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001162895,"about_ca_topic_score_gemma":0.000009553777,"domain_scores_codex":[0.9993101,0.00001034921,0.0001210563,0.000216354,0.0001650529,0.0001771065],"domain_scores_gemma":[0.9998053,0.00002164919,0.00001851877,0.0000890371,0.00002671558,0.00003876687],"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":[0.000009959238,0.000006644459,0.00004930601,0.00001703135,0.000002755319,7.131484e-7,0.00003669685,0.8989875,0.0005307327,0.0007596951,0.00008264722,0.09951636],"study_design_scores_gemma":[0.0001653669,0.00003750483,0.00162199,0.0001007218,0.000005993928,4.202925e-7,0.00006583569,0.9976559,0.00002601291,0.0001353683,0.0001020462,0.00008283333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02824951,0.00002500913,0.9557582,0.00009975945,0.0001287273,0.0001772403,0.000002789505,0.002014565,0.01354425],"genre_scores_gemma":[0.9858915,0.00002627265,0.01391987,0.00005015255,0.00000315787,0.000012334,0.000003020412,0.000006476751,0.00008724152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.957642,"threshold_uncertainty_score":0.3782179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007954237058243368,"score_gpt":0.2196894459620968,"score_spread":0.2117352089038534,"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."}}