{"id":"W4387514048","doi":"10.1080/13658816.2023.2264921","title":"Predicting households’ residential mobility trajectories with geographically localized interpretable model-agnostic explanation (GLIME)","year":2023,"lang":"en","type":"article","venue":"International Journal of Geographical Information Systems","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Western University; National Research Foundation of Korea; National Science Foundation","keywords":"Leverage (statistics); Computer science; Data science; Artificial intelligence; Deep learning; Individual mobility; Analytics; Deep neural networks; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002623303,0.0001741845,0.0003297811,0.0007634325,0.0003191583,0.000632082,0.0007308552,0.0001926306,0.0000388903],"category_scores_gemma":[0.0005213367,0.0001411868,0.0002345458,0.001091034,0.0003626608,0.003887375,0.00004232414,0.0003773232,0.00001132114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186344,"about_ca_system_score_gemma":0.000334103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002264617,"about_ca_topic_score_gemma":0.0007567502,"domain_scores_codex":[0.995698,0.0001960021,0.001393897,0.0001608665,0.002220906,0.0003302729],"domain_scores_gemma":[0.9963423,0.0003221136,0.0009163879,0.0001630476,0.0020351,0.00022105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008123161,0.0001330647,0.930043,0.00006995613,0.0003757802,0.00002851083,0.007606025,0.05426949,0.00003903464,0.005381796,0.0005331926,0.000707878],"study_design_scores_gemma":[0.006990612,0.0007838368,0.7795468,0.001690933,0.0004206424,0.00009339527,0.02046199,0.1601814,0.0001684475,0.007782861,0.0206054,0.001273622],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9561892,0.00006429289,0.03926574,0.0007463796,0.001715757,0.0003651289,0.00006994468,0.0002039394,0.001379616],"genre_scores_gemma":[0.9991032,0.0001269695,0.0001445984,0.00008020748,0.0004013632,0.00002497555,0.00006753922,0.00001037784,0.00004072894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1504961,"threshold_uncertainty_score":0.6095181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0163823910387454,"score_gpt":0.2804510053657107,"score_spread":0.2640686143269653,"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."}}