{"id":"W2883423620","doi":"10.1016/j.isprsjprs.2018.11.011","title":"TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildings","year":2018,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":136,"is_retracted":true,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Wuhan University; Japan Society for the Promotion of Science; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Segmentation; License; Aerial imagery; Roof; Scale (ratio); Computer science; Artificial intelligence; Computer vision; Aerial image; Orthophoto; Computer graphics (images); Remote sensing; Cartography; Image (mathematics); Geology; Geography; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":{"nature":"Retraction","reason":"Notice - Limited or No Information;Temporary Removal;Removed;","date":"1/1/2019 0:00","openalex_flagged":true},"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003007244,0.001430905,0.0008640083,0.002680792,0.0007914742,0.001063428,0.001334649,0.001157247,0.003603369],"category_scores_gemma":[0.0005548304,0.0005382993,0.00146147,0.002450586,0.0004790549,0.0006253399,0.001241783,0.0008460843,0.00656815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004207424,"about_ca_system_score_gemma":0.00121533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02069773,"about_ca_topic_score_gemma":0.0534784,"domain_scores_codex":[0.9994954,0.00003703462,0.00002179692,0.0001498868,0.0001656173,0.0001302362],"domain_scores_gemma":[0.9996954,0.00001904781,0.00002767521,0.0001128332,0.00009530102,0.00004977809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009272042,0.001537128,0.02492147,0.001528187,0.0006552871,0.00126995,0.0007195192,0.02140082,0.210435,0.001027027,0.3168577,0.4187206],"study_design_scores_gemma":[0.0006988908,0.0005655166,0.3640442,0.0003679126,0.0007365844,0.002930521,0.002147592,0.2125477,0.1418158,0.003103931,0.270656,0.0003852845],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.5088066,0.002314963,0.07585515,0.0006524818,0.0005431073,0.001051969,0.3561871,0.04168544,0.01290308],"genre_scores_gemma":[0.2818429,0.0006034054,0.1066961,0.0001921863,0.0001464471,0.0004495268,0.6034047,0.001577066,0.005087666],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.02069773,"threshold_uncertainty_score":0.0411545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01655117219334873,"score_gpt":0.2779389524151745,"score_spread":0.2613877802218258,"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."}}