{"id":"W4391048039","doi":"10.2139/ssrn.4701536","title":"A Geographic-Semantic Context-Aware Urban Commuting Flow Prediction Model Using Graph Neural Network","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Leverage (statistics); Computer science; Artificial intelligence; Adjacency list; Dependency (UML); Graph; Machine learning; Spatial network; Artificial neural network; Context (archaeology); Gravity model of trade; Data mining; Data science; Geography; Theoretical computer science; Mathematics","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":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006851499,0.0004075787,0.0005628741,0.00049383,0.002733929,0.0006561015,0.0007919883,0.000519751,0.00005001559],"category_scores_gemma":[0.0001157557,0.000417509,0.0009059925,0.0008143209,0.0003892137,0.000175775,0.0002981533,0.008260469,0.000009696641],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001952545,"about_ca_system_score_gemma":0.007352218,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01431297,"about_ca_topic_score_gemma":0.1392208,"domain_scores_codex":[0.9938678,0.0009000072,0.0008298519,0.0006256522,0.0008496558,0.002927014],"domain_scores_gemma":[0.9983426,0.00014439,0.0004879266,0.0004380184,0.0003611469,0.000225954],"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":[0.0000297462,0.00007529323,0.007438539,0.00008633077,0.0009343322,0.000006174809,0.005138709,0.9453873,0.000004187205,0.02462141,0.0002184282,0.01605958],"study_design_scores_gemma":[0.0001281969,0.00003424529,0.00005882528,0.0002697011,0.0005681287,0.0000134976,0.004672795,0.6084379,3.204942e-7,0.3854724,0.00009875352,0.0002452751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7620032,0.02960762,0.2006688,0.003069278,0.002387155,0.0009521177,0.00006728387,0.0005106143,0.000733877],"genre_scores_gemma":[0.9934241,0.003167902,0.0001063303,0.0001447381,0.002652941,0.00002147061,0.00006108899,0.0000542015,0.000367233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.360851,"threshold_uncertainty_score":0.9998277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02101638659110272,"score_gpt":0.285528178253029,"score_spread":0.2645117916619263,"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."}}