{"id":"W3087953136","doi":"10.1177/2399808320959079","title":"Using deep learning to examine the correlation between transportation planning and perceived safety of the built environment","year":2020,"lang":"en","type":"article","venue":"Environment and Planning B Urban Analytics and City Science","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perception; Probit model; Convolutional neural network; Ordered probit; Variables; Logit; Ordinary least squares; Set (abstract data type); Regression analysis; Transportation planning; Transport engineering; Logistic regression; Geography; Probit; Computer science; Engineering; Psychology; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007161176,0.0001035575,0.0001417708,0.00003177223,0.001218891,0.00007427645,0.0001576473,0.00004482554,0.00002370273],"category_scores_gemma":[0.00005504983,0.00007326246,0.00002573956,0.0002001009,0.0009361265,0.0001923986,0.00004004512,0.0001710729,3.802048e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003171128,"about_ca_system_score_gemma":0.0000225505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001966256,"about_ca_topic_score_gemma":0.00002150859,"domain_scores_codex":[0.9988111,0.00006121228,0.000215646,0.0003031001,0.0004147477,0.0001941872],"domain_scores_gemma":[0.9995048,0.0001107885,0.0001243821,0.00009250231,0.000008275956,0.0001592364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001037496,0.00000480892,0.9536206,0.00000581202,0.000006483093,5.961597e-7,0.03509891,0.009794708,0.0008250475,0.00004072481,0.000002320864,0.0005896213],"study_design_scores_gemma":[0.0001112824,0.00003555933,0.9802925,0.00002505947,0.00006925978,1.052579e-7,0.004406519,0.01388024,0.00005691499,0.00004836553,0.0009758021,0.0000983975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913373,0.0003278575,0.00733579,0.0006118504,0.00002364989,0.0001881385,0.000007583229,0.000007451777,0.0001603944],"genre_scores_gemma":[0.9994456,0.0000621268,0.000277659,0.00008473055,0.00006187674,9.013524e-7,0.000004505785,0.000003881892,0.00005872475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03069239,"threshold_uncertainty_score":0.9374851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05504780798520448,"score_gpt":0.2772891670892123,"score_spread":0.2222413591040078,"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."}}