{"id":"W4385859418","doi":"10.1007/978-3-031-34593-7_14","title":"Semantic Segmentation of Synthetic Images into Building Components for Automated Quality Assurance","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in civil engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Building information modeling; Computer science; Segmentation; Schedule; Convolutional neural network; Artificial intelligence; Intersection (aeronautics); Component (thermodynamics); Quality assurance; Building model; Testbed; Machine learning; Engineering; Simulation; Scheduling (production processes)","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":[0.0004340298,0.001119762,0.0007640357,0.002196803,0.0003488045,0.001741136,0.001044213,0.0009361401,0.004284073],"category_scores_gemma":[0.000825514,0.0006591885,0.001305413,0.001937345,0.0007400858,0.00104762,0.00075949,0.0006865472,0.001594768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006773169,"about_ca_system_score_gemma":0.0007221127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003220984,"about_ca_topic_score_gemma":0.004349852,"domain_scores_codex":[0.9996368,0.00004970435,0.00001759567,0.00009673207,0.0001402823,0.00005883222],"domain_scores_gemma":[0.9996108,0.0001017524,0.00004290065,0.0001185248,0.0001103904,0.00001566772],"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":[0.0004061675,0.0001756455,0.001471562,0.0006050118,0.0001341263,0.0002356995,0.0002874275,0.09122504,0.233965,0.0138622,0.012318,0.645314],"study_design_scores_gemma":[0.0000301017,0.0001269218,0.003150324,0.00008898626,0.00009623388,0.0004287195,0.0002210853,0.8321943,0.1269834,0.01839243,0.01824926,0.00003816368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02735969,0.0006570425,0.9628469,0.0001480734,0.00007997382,0.0001247036,0.0007304306,0.004577005,0.003476189],"genre_scores_gemma":[0.2407013,0.0009878301,0.749135,0.0001092669,0.00005845602,0.00009131767,0.004527337,0.001350331,0.003039197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004284073,"threshold_uncertainty_score":0.0143317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01257191104973945,"score_gpt":0.255790175394559,"score_spread":0.2432182643448196,"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."}}