{"id":"W3187845984","doi":"10.1109/tits.2021.3097240","title":"Short-Term Forecast of Bicycle Usage in Bike Sharing Systems: A Spatial-Temporal Memory Network","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Hong Kong Polytechnic University; National Natural Science Foundation of China","keywords":"Bike sharing; Computer science; Robustness (evolution); Task (project management); Feature engineering; Machine learning; Data mining; Real-time computing; Deep learning; Transport engineering; Engineering","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"],"consensus_categories":[],"category_scores_codex":[0.001061304,0.0002985656,0.0006338195,0.0002782109,0.0003454685,0.0001282493,0.0003525883,0.0002787023,0.0002585979],"category_scores_gemma":[0.000005529518,0.0003231058,0.0003168297,0.001162823,0.0001911143,0.000446814,5.68561e-7,0.0003501334,0.00001739324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002189611,"about_ca_system_score_gemma":0.0002720029,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02293918,"about_ca_topic_score_gemma":0.1089105,"domain_scores_codex":[0.9961602,0.000273488,0.001548999,0.0006682667,0.0007998808,0.0005491805],"domain_scores_gemma":[0.998601,0.0001699086,0.000254911,0.0004501909,0.0003128143,0.0002111466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002745823,0.001088665,0.6367399,0.001080892,0.0002405522,0.0001931821,0.02232654,0.327143,0.0007654264,0.0008716244,0.00003978323,0.009235901],"study_design_scores_gemma":[0.004699586,0.0007265647,0.7709793,0.01043886,0.001298945,0.00002126899,0.1067904,0.03587782,0.05623958,0.0007455545,0.007291082,0.004891024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6590778,0.0005464081,0.3356007,0.00003250046,0.002686251,0.0008548984,0.0001580284,0.0001130748,0.0009303199],"genre_scores_gemma":[0.9981526,0.0001643638,0.00006583767,0.0000130579,0.0002164348,0.0001876039,0.00008795106,0.00004012241,0.001072073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3390748,"threshold_uncertainty_score":0.9999221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0511023960503229,"score_gpt":0.3070827852640103,"score_spread":0.2559803892136874,"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."}}