{"id":"W3096684504","doi":"10.1109/tits.2020.3030259","title":"Understanding and Modeling Urban Mobility Dynamics via Disentangled Representation Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Representation (politics); Generative grammar; Feature learning; Computer science; Generative model; Feature vector; Feature (linguistics); Artificial intelligence; Traffic flow (computer networking); Machine learning; Domain (mathematical analysis); Dynamics (music); Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004969709,0.0006669736,0.000459694,0.0004634137,0.0001702856,0.0005225206,0.0008719903,0.0006256149,0.0008917758],"category_scores_gemma":[0.00171521,0.0003726436,0.0007201226,0.0005865907,0.0006829102,0.00123197,0.0009122473,0.001365981,0.0001715053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006897713,"about_ca_system_score_gemma":0.0004974687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008746165,"about_ca_topic_score_gemma":0.008682209,"domain_scores_codex":[0.9997461,0.00009002996,0.00000825316,0.00007999722,0.00003424724,0.0000413602],"domain_scores_gemma":[0.999529,0.0002754198,0.00006937281,0.00005600617,0.00004631245,0.00002383681],"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":[0.00001697963,0.00001746059,0.0009858233,0.00001021884,0.00001667732,0.00002645248,0.00002372239,0.9815063,0.0004443612,0.006882392,0.0004119291,0.009657679],"study_design_scores_gemma":[8.131983e-7,0.000002493691,0.0000979818,8.722464e-7,0.000001380524,0.000003051339,0.000002033084,0.9972461,0.00003952338,0.002541604,0.00006312308,0.000001084189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08864135,0.0002705574,0.9084794,0.0004412107,0.00003599503,0.00002393356,0.0003251912,0.0003404937,0.001441892],"genre_scores_gemma":[0.9607071,0.0003003525,0.03585665,0.00009487485,0.0000429924,0.00005801022,0.0007264889,0.00004242645,0.002171184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008746165,"threshold_uncertainty_score":0.01739055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07772835440766876,"score_gpt":0.2511281552030318,"score_spread":0.1733998007953631,"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."}}