{"id":"W4200200473","doi":"10.5194/ica-abs-3-105-2021","title":"Waterloo Building Dataset: A large-scale very-high-spatial-resolution image dataset for building rooftop extraction","year":2021,"lang":"en","type":"article","venue":"Abstracts of the ICA","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Scale (ratio); Extraction (chemistry); Computer science; Remote sensing; Geography; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003324642,0.00264202,0.001573628,0.004143398,0.001182495,0.001160373,0.003347409,0.001822462,0.01837314],"category_scores_gemma":[0.001350839,0.0008918717,0.001845887,0.005865959,0.0006664183,0.0009608371,0.001844549,0.001360084,0.01863695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002057318,"about_ca_system_score_gemma":0.003723599,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2997738,"about_ca_topic_score_gemma":0.5980974,"domain_scores_codex":[0.9991434,0.00004749771,0.00004465317,0.0002330793,0.000330253,0.0002010974],"domain_scores_gemma":[0.9993938,0.00005860291,0.00004518681,0.0001505723,0.0002681921,0.00008365566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001991348,0.0002870485,0.004599651,0.001076068,0.0002171957,0.0002903914,0.0001341324,0.003735678,0.007128772,0.0008242022,0.9236533,0.05785441],"study_design_scores_gemma":[0.0007694368,0.0001422192,0.07853729,0.0004950788,0.0003260942,0.0006811974,0.0008295245,0.04751829,0.01588464,0.002615846,0.8518881,0.0003124185],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01028487,0.0005079164,0.004892725,0.0001240763,0.00006796047,0.0002278503,0.973411,0.006610157,0.003873386],"genre_scores_gemma":[0.007919597,0.0001588013,0.006118794,0.00005023072,0.0000153123,0.0001808364,0.983712,0.0002458863,0.001598594],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7002262,"threshold_uncertainty_score":0.5960579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01336690295962198,"score_gpt":0.2523278698896337,"score_spread":0.2389609669300117,"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."}}