{"id":"W4285604412","doi":"10.24963/ijcai.2022/545","title":"FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Traffic flow (computer networking); Data mining; Deep learning; Artificial intelligence; 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":[0.0008085812,0.001528781,0.001376506,0.0010456,0.0004821911,0.000706576,0.002137799,0.001185123,0.002156276],"category_scores_gemma":[0.003346455,0.0006282054,0.0008780584,0.0009867775,0.0007078464,0.001758056,0.001051463,0.002148711,0.0006256955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009197942,"about_ca_system_score_gemma":0.001808956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02290151,"about_ca_topic_score_gemma":0.0237339,"domain_scores_codex":[0.9996177,0.00008473035,0.00001663641,0.0001257006,0.00009737525,0.000057866],"domain_scores_gemma":[0.9991659,0.000338211,0.00009108411,0.0001398291,0.0001893745,0.00007560203],"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":[0.0001911328,0.0002150948,0.002726149,0.0001376804,0.00009093108,0.0001199071,0.00009441568,0.7730879,0.002749228,0.007573829,0.01552941,0.1974843],"study_design_scores_gemma":[0.000004128958,0.000007632595,0.00007829958,0.000002320039,0.000002575216,0.000004570405,0.00000229169,0.997598,0.0001886076,0.001899201,0.0002098261,0.00000252324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02922795,0.0006640311,0.9610003,0.0003511351,0.0001700423,0.00009676205,0.0004881737,0.006020634,0.001981048],"genre_scores_gemma":[0.74075,0.0005104627,0.2517262,0.0004692368,0.0001938607,0.0001687931,0.002336013,0.0005155407,0.003329937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02290151,"threshold_uncertainty_score":0.0455364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04697044092855063,"score_gpt":0.2364344383597053,"score_spread":0.1894639974311547,"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."}}