{"id":"W4417288161","doi":"10.1016/j.engappai.2025.113488","title":"Spatio-temporal traffic accidents detection via graph based generative adversarial network","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Research Grants Council, University Grants Committee; City University of Hong Kong","keywords":"Discriminator; Adversarial system; Anomaly detection; Generative grammar; Field (mathematics); Context (archaeology); Graph; Deep learning; Scarcity","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002283354,0.0001589414,0.0001667953,0.0002920314,0.0002245023,0.00006644234,0.0006587484,0.0001009652,0.00001155715],"category_scores_gemma":[0.00002467783,0.0001840558,0.0001097723,0.001932293,0.00005235509,0.0001787296,0.00008109454,0.000165255,0.00001997206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006476138,"about_ca_system_score_gemma":0.00006368294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005864192,"about_ca_topic_score_gemma":0.00005253444,"domain_scores_codex":[0.9987273,0.00002387492,0.0004944313,0.000381683,0.0001620168,0.0002107199],"domain_scores_gemma":[0.9989065,0.0001044983,0.0001485512,0.0006060145,0.0001770258,0.00005742737],"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":[0.00001057373,0.0001032187,0.00004511024,0.00001754366,0.00002330857,2.21549e-7,0.00004753145,0.614009,0.004588726,0.1005003,0.00006385134,0.2805906],"study_design_scores_gemma":[0.00002159178,0.00003609275,0.0001499844,0.0000160978,0.00001137023,7.38591e-7,0.000009161773,0.786105,0.1996628,0.01146869,0.002372797,0.0001456063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003609206,0.0000534766,0.9947956,0.0002147693,0.0002186623,0.0005749557,0.000003387593,0.0004499897,0.00007999541],"genre_scores_gemma":[0.8272341,0.000006580461,0.1720183,0.00003977258,0.0001003707,0.0005596023,0.000009011327,0.000008669303,0.00002357022],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8236249,"threshold_uncertainty_score":0.7505577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01080713229286026,"score_gpt":0.252006326730256,"score_spread":0.2411991944373958,"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."}}