{"id":"W4402474673","doi":"10.5194/isprs-archives-xlviii-m-4-2024-55-2024","title":"Reconstruction of Building LoD2 Wireframe Models Using Semantic Segmentation","year":2024,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Power Systems and Technologies","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Segmentation; Computer science; Computer vision; Artificial intelligence; Natural language processing; Computer graphics (images)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010044,0.0003498144,0.0003863904,0.001137197,0.0006459338,0.0006297554,0.001028831,0.0001025731,0.000003985793],"category_scores_gemma":[0.000242694,0.0002295497,0.0003060595,0.0009921157,0.002013873,0.00075771,0.0004968946,0.0003846168,0.000001041556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006516013,"about_ca_system_score_gemma":0.0001478171,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5794184,"about_ca_topic_score_gemma":0.05207042,"domain_scores_codex":[0.9965476,0.0001376162,0.001363588,0.0002998528,0.001262374,0.0003889482],"domain_scores_gemma":[0.9979254,0.0005874587,0.0008588698,0.0003521844,0.0001929601,0.00008313209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000036237,0.0000066395,0.00007042704,0.0001292989,0.0001167648,2.62842e-7,0.002173444,0.03604902,0.01379655,0.00002839714,0.00001499954,0.947578],"study_design_scores_gemma":[0.0003170366,0.0000678607,0.0002866859,0.0008795507,0.00004937199,0.0002137344,0.002002438,0.9566813,0.02833189,0.010349,0.0005816654,0.0002394832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04155988,0.0001152032,0.9504304,0.0007770229,0.002932188,0.0004887764,0.00008345219,0.0001136524,0.003499446],"genre_scores_gemma":[0.9924973,0.0002547515,0.006966253,0.0001265624,0.00009946436,3.146664e-7,0.00001498019,0.00001367695,0.00002667079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9509374,"threshold_uncertainty_score":0.9652268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01971818335203979,"score_gpt":0.25240779386968,"score_spread":0.2326896105176402,"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."}}