{"id":"W3200993033","doi":"10.48550/arxiv.2109.08357","title":"Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Missing data; Data mining; Imputation (statistics); Graph; Deep learning; Artificial intelligence; Convolutional neural network; Big data; Intelligent transportation system; Machine learning; 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":[0.001384543,0.0008725197,0.0007697594,0.0009767174,0.0004020762,0.0006277247,0.002149804,0.0009164673,0.001238217],"category_scores_gemma":[0.005089568,0.0005291972,0.0008525573,0.001859388,0.0005334174,0.002113884,0.001077211,0.002163223,0.0003447917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001571165,"about_ca_system_score_gemma":0.001624487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02605162,"about_ca_topic_score_gemma":0.03572312,"domain_scores_codex":[0.9995015,0.0001184284,0.00003072543,0.0001711032,0.00009458152,0.00008364169],"domain_scores_gemma":[0.9986631,0.0005686944,0.0001976538,0.0002569421,0.0002528684,0.00006085754],"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":[0.0001253851,0.00009778934,0.005951253,0.00008148055,0.0001166912,0.0001130521,0.000071002,0.8696205,0.0009544533,0.01233935,0.00376594,0.1067631],"study_design_scores_gemma":[0.000001485537,0.000004624379,0.0001907515,0.000003665288,0.000005450046,0.000006468189,0.000003891077,0.9953017,0.0001686355,0.004122907,0.0001880981,0.000002304158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04773671,0.0007657229,0.9470128,0.0007596887,0.00008592635,0.00003360377,0.0008470104,0.001522293,0.001236281],"genre_scores_gemma":[0.8584872,0.0008417475,0.133813,0.0003339568,0.00008623279,0.00009418444,0.003088315,0.0001376218,0.003117668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02605162,"threshold_uncertainty_score":0.05179995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06591026237124424,"score_gpt":0.2006809423428645,"score_spread":0.1347706799716202,"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."}}