{"id":"W4417257707","doi":"10.48550/arxiv.2506.08740","title":"Urban Incident Prediction with Graph Neural Networks: Integrating Government Ratings and Crowdsourced Reports","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Alfred P. Sloan Foundation; National Aeronautics and Space Administration; Open Philanthropy Project; National Science Foundation","keywords":"Government (linguistics); Crowdsourcing; Incident report; Graph; Set (abstract data type); Data set; Predictive modelling","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001672516,0.001088345,0.0007083248,0.001243652,0.0003421846,0.0009389056,0.001646753,0.00107992,0.0009667759],"category_scores_gemma":[0.00742799,0.0005024677,0.0006672029,0.001648999,0.0005113025,0.00156659,0.001032081,0.001586847,0.0003381791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001535229,"about_ca_system_score_gemma":0.0006658581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04813086,"about_ca_topic_score_gemma":0.06053197,"domain_scores_codex":[0.9992322,0.0003136905,0.00003625715,0.0002638993,0.00007839741,0.00007564216],"domain_scores_gemma":[0.996996,0.00177834,0.0004321684,0.000278516,0.0003948591,0.000120149],"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":[0.0001659991,0.0001592885,0.01945441,0.00007324242,0.0001165023,0.0001002662,0.0001311252,0.9228624,0.0002359697,0.002254674,0.00416321,0.05028294],"study_design_scores_gemma":[0.000004341401,0.000006716287,0.0008474523,0.000007178624,0.000007133187,0.000003615861,0.00001312084,0.9971445,0.00005795495,0.001689907,0.0002136545,0.000004494016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4908617,0.002670761,0.4847424,0.004861814,0.0005227969,0.0002960573,0.005936985,0.002367938,0.007739642],"genre_scores_gemma":[0.9660425,0.0003222039,0.02853635,0.0003149001,0.0001263109,0.00009046457,0.002650285,0.00004878671,0.001868312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04813086,"threshold_uncertainty_score":0.09570146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007464980062877606,"score_gpt":0.1950977281359613,"score_spread":0.1876327480730837,"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."}}