{"id":"W2921479043","doi":"10.1371/journal.pone.0212814","title":"Deep mapping gentrification in a large Canadian city using deep learning and Google Street View","year":2019,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Gentrification; Deep learning; Geography; Cartography; Computer science; Data science; Artificial intelligence; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001929895,0.00006273654,0.0001144603,0.00004117706,0.00008876636,0.00002706499,0.00006897171,0.0000462893,0.001173187],"category_scores_gemma":[0.000007393601,0.00006015696,0.000009754711,0.0001476456,0.000003463398,0.000169593,0.00004265676,0.00008361601,0.0002492352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221458,"about_ca_system_score_gemma":0.000007014727,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07723694,"about_ca_topic_score_gemma":0.6156771,"domain_scores_codex":[0.9993111,0.00003614342,0.0001147063,0.00017982,0.0001200641,0.0002381504],"domain_scores_gemma":[0.9997541,0.00001257094,0.00004386423,0.00009003278,0.000003512489,0.00009592679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001362684,0.0000481148,0.9970304,0.00005808704,0.000008208341,0.000001878123,0.0004102833,0.0002530839,0.00168387,0.00000313382,4.297853e-7,0.0005011352],"study_design_scores_gemma":[0.0003634306,0.00002139843,0.6952956,0.0001978547,0.00001811258,0.000001202394,0.000436633,0.3020599,0.0004021323,0.00002947485,0.0009915775,0.0001825976],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980461,0.0002524824,0.00003074779,0.0000582475,0.00001210328,0.0001968468,0.000001870717,0.00001123486,0.001390342],"genre_scores_gemma":[0.9993839,0.00008995333,0.0003801396,0.00008382825,0.00001609566,0.000004622559,0.000009473751,0.000006395117,0.0000255438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5384402,"threshold_uncertainty_score":0.9997399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02734098583359209,"score_gpt":0.2049513456866731,"score_spread":0.177610359853081,"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."}}