{"id":"W4408094703","doi":"10.1016/j.scs.2025.106267","title":"Perceiving the fine-scale urban poverty using street view images through a vision-language model","year":2025,"lang":"en","type":"article","venue":"Sustainable Cities and Society","topic":"Impact of Light on Environment and Health","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute on Governance","funders":"Social Science Foundation of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Scale (ratio); Poverty; Urban poverty; Computer vision; Computer science; Artificial intelligence; Geography; Cartography; Economics; Economic growth","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":[0.0004026976,0.0001753877,0.0001861138,0.000009653315,0.001125512,0.0001139028,0.0001824144,0.00008077808,0.0003475023],"category_scores_gemma":[0.00001430631,0.0001210711,0.0001188544,0.0001533891,0.000384573,0.000474234,0.0004003795,0.0001859083,0.000003206276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004040064,"about_ca_system_score_gemma":0.00005550559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00262684,"about_ca_topic_score_gemma":0.00005860322,"domain_scores_codex":[0.9986646,0.00004485616,0.0001787244,0.0002665235,0.000226167,0.0006191492],"domain_scores_gemma":[0.9995568,0.0000574816,0.00005429457,0.0002557798,0.000007556739,0.00006802717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.00006069709,0.0003873962,0.2029146,0.001665878,0.0001585358,0.00002863416,0.3527871,0.01090563,0.003523351,0.007061257,0.4141953,0.006311651],"study_design_scores_gemma":[0.001446241,0.0001750728,0.2502744,0.0002071827,0.0001732437,0.00000673859,0.5784276,0.1167928,0.00052486,0.01067598,0.04035291,0.0009430025],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9753497,0.001843601,0.003641513,0.002359714,0.00004148689,0.0003513438,0.00001263731,0.00004083321,0.01635919],"genre_scores_gemma":[0.9654688,0.0009873429,0.001970611,0.003995953,0.00004178315,0.00001064352,0.000004446294,0.00001471121,0.02750575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3738424,"threshold_uncertainty_score":0.8656639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007300970329415799,"score_gpt":0.2640467857790999,"score_spread":0.2567458154496841,"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."}}