{"id":"W4414464116","doi":"10.1109/acdsa65407.2025.11166555","title":"Integrating Knowledge and Data Driven Methods to Generate Synthetic Mobility Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sheridan College","funders":"Research and Development","keywords":"Data-driven; Representativeness heuristic; Geospatial analysis; Data integration; Scalability; Data collection; Synthetic data; Data quality","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":[0.00573204,0.00008908095,0.0001854256,0.00009551159,0.0006256769,0.0001723982,0.001360927,0.00006053717,0.0004253646],"category_scores_gemma":[0.003447966,0.00007675076,0.00002093974,0.0006464074,0.0002352077,0.0002573562,0.001012703,0.0001065454,0.00002761992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006322857,"about_ca_system_score_gemma":0.0004001941,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01347767,"about_ca_topic_score_gemma":0.1455022,"domain_scores_codex":[0.9977448,0.001014104,0.0002457479,0.0006966694,0.0001108227,0.0001878482],"domain_scores_gemma":[0.9970158,0.0008849716,0.00003252854,0.001828631,0.0001215888,0.0001164985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006876981,0.0002162687,0.004525322,0.00005718981,0.0001041068,4.373544e-7,0.009178803,0.00008324275,0.0004959372,0.0481163,0.009098586,0.9281169],"study_design_scores_gemma":[0.0002048129,0.00002751745,0.003400649,0.0001143018,0.0003172977,1.497746e-7,0.02256911,0.5359392,0.0005781805,0.006872972,0.4295287,0.0004471456],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04084212,0.0008591501,0.8662822,0.007423434,0.0002748505,0.0006260431,0.0001313528,0.0001730967,0.0833877],"genre_scores_gemma":[0.8997656,0.00006040704,0.09281474,0.0004890728,0.000117847,0.00002111929,0.0001661954,0.000005587578,0.006559431],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9276698,"threshold_uncertainty_score":0.9930916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1107881882325228,"score_gpt":0.4800432641990845,"score_spread":0.3692550759665617,"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."}}