{"id":"W4408836404","doi":"10.1016/j.trc.2025.105107","title":"TMS-GNN: Traffic-aware Multistep Graph Neural Network for bus passenger flow prediction","year":2025,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Mitacs","keywords":"Artificial neural network; Computer science; Traffic flow (computer networking); Transport engineering; Graph; Engineering; Real-time computing; Simulation; Computer network; Artificial intelligence; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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":[0.0002994227,0.0008759642,0.0004889141,0.0005899458,0.0002289448,0.0003566327,0.001352489,0.0006907449,0.001373289],"category_scores_gemma":[0.001097835,0.0003225503,0.0006468919,0.0006635648,0.0002929687,0.0008049645,0.0005365671,0.001226784,0.0002694203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001120013,"about_ca_system_score_gemma":0.001132189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0577726,"about_ca_topic_score_gemma":0.06243067,"domain_scores_codex":[0.9998636,0.00002131867,0.000006964143,0.00004846727,0.00003001118,0.0000296666],"domain_scores_gemma":[0.9997739,0.00007124621,0.00002908453,0.00001874757,0.00008703506,0.00002004122],"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":[0.0000553413,0.00004473668,0.001937053,0.00003339932,0.00003970195,0.00004392754,0.00001519071,0.9488233,0.0007372341,0.001612894,0.002439799,0.0442173],"study_design_scores_gemma":[0.000001878963,0.000005500355,0.0001645995,0.000001589323,0.000002886776,0.00000285346,0.000001535672,0.9990076,0.0001142293,0.0005746972,0.0001210017,0.000001662643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1871881,0.001886771,0.796611,0.0009805206,0.0004328685,0.000121718,0.002720469,0.004386663,0.005671826],"genre_scores_gemma":[0.9309728,0.0006462692,0.06042387,0.0002194463,0.00006692766,0.00009864438,0.003162223,0.00008082108,0.00432902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0577726,"threshold_uncertainty_score":0.1148727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03213255960766891,"score_gpt":0.3129369431168603,"score_spread":0.2808043835091914,"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."}}