{"id":"W4318604490","doi":"10.1109/ssci51031.2022.10022181","title":"Simpler is better: Multilevel Abstraction with Graph Convolutional Recurrent Neural Network Cells for Traffic Prediction","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Benchmark (surveying); Abstraction; Encoder; Graph; Recurrent neural network; Convolutional neural network; Data mining; Sequence (biology); Artificial intelligence; Machine learning; Theoretical computer science; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002323564,0.0003069473,0.0002116562,0.0002441542,0.0005925662,0.00007893907,0.000255086,0.0000673228,0.0001940686],"category_scores_gemma":[0.000002767276,0.000337254,0.0001400409,0.0003771712,0.00009329132,0.0003488725,0.00004211744,0.0003949753,0.00001522651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002658119,"about_ca_system_score_gemma":0.00003972238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004543791,"about_ca_topic_score_gemma":0.000008920043,"domain_scores_codex":[0.9979824,0.00005348328,0.0004819718,0.0004664169,0.0006285063,0.0003872356],"domain_scores_gemma":[0.9993169,0.0001504612,0.0001247278,0.0001871072,0.000121714,0.00009914558],"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":[0.0002009886,0.0001094285,0.000024569,0.00004918544,0.00009735617,0.000002975173,0.0002370543,0.9012971,0.0003412874,0.001227653,0.08773541,0.008677001],"study_design_scores_gemma":[0.0002478917,0.0008282099,0.0006226599,0.00002329752,0.00004244093,0.00002799004,0.0002247274,0.9719487,0.001148701,0.0007048475,0.02383842,0.00034208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0958841,0.0001022813,0.8862799,0.001459479,0.007813151,0.001962314,0.001779823,0.004206628,0.0005123626],"genre_scores_gemma":[0.9925405,0.00009400307,0.00480933,0.0005026642,0.0003717526,0.0008137277,0.0006548008,0.00006037285,0.0001528272],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8966564,"threshold_uncertainty_score":0.999908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01676661914422996,"score_gpt":0.2330853682350549,"score_spread":0.216318749090825,"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."}}