{"id":"W4410733347","doi":"10.1139/cjce-2024-0503","title":"PNNs4: a parallel quadruple neural network model for urban intersection turning movement prediction","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Intersection (aeronautics); Artificial neural network; Flow (mathematics); Computer science; Mathematics; Engineering; Transport engineering; Artificial intelligence; Geometry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.0003952011,0.0008326264,0.0005982738,0.0005028385,0.0003331787,0.0005508059,0.001754481,0.000673817,0.001856245],"category_scores_gemma":[0.0008591339,0.0005010754,0.0006857034,0.000507006,0.0004512728,0.00076925,0.000959859,0.001232694,0.0003802931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009018763,"about_ca_system_score_gemma":0.001228383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04024085,"about_ca_topic_score_gemma":0.04090566,"domain_scores_codex":[0.9998493,0.00002124636,0.000008333661,0.00004763492,0.00004304598,0.00003045244],"domain_scores_gemma":[0.9998046,0.00005450195,0.00002576432,0.00001644557,0.00008281503,0.00001593932],"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":[0.00004569243,0.00003120565,0.001001474,0.00001435871,0.00003910435,0.00002921052,0.000009644721,0.9724953,0.0007394942,0.0006442983,0.0009924228,0.02395787],"study_design_scores_gemma":[0.000001665574,0.000007203384,0.0001029908,0.000001215274,0.000003167285,0.000002463701,0.000001669562,0.9992212,0.000158063,0.0003791852,0.0001195173,0.000001625305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1979221,0.000836598,0.788358,0.0006195506,0.0002973926,0.0001099486,0.001448984,0.002364003,0.00804338],"genre_scores_gemma":[0.9314256,0.0003034308,0.05945653,0.0001412386,0.0000469899,0.0001293257,0.001339723,0.00006894701,0.007088381],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04024085,"threshold_uncertainty_score":0.08001328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006812071026103224,"score_gpt":0.1843924197240523,"score_spread":0.1775803486979491,"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."}}