{"id":"W4313567559","doi":"10.1016/j.iintel.2022.100024","title":"Automated multiclass structural damage detection and quantification using augmented reality","year":2023,"lang":"en","type":"article","venue":"Journal of Infrastructure Intelligence and Resilience","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Colleges and Universities","keywords":"Computer science; Structural health monitoring; Visualization; Visual inspection; Identification (biology); Segmentation; Augmented reality; Artificial intelligence; Scale (ratio); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005206207,0.0008934443,0.0007624991,0.001442824,0.0002214379,0.0009108229,0.0008220103,0.000848992,0.001251031],"category_scores_gemma":[0.000844712,0.0004173379,0.0009112157,0.0005682086,0.0003469708,0.0007872393,0.00106463,0.0007006544,0.0004510618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003633191,"about_ca_system_score_gemma":0.0003245021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002852769,"about_ca_topic_score_gemma":0.003240299,"domain_scores_codex":[0.9993075,0.0001056927,0.00003035741,0.0002301336,0.0002513248,0.00007493243],"domain_scores_gemma":[0.9994906,0.0001192343,0.0001184826,0.0001300601,0.0001160778,0.00002561467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003611576,0.0003397791,0.00384906,0.0001441867,0.0001396601,0.00018167,0.0003621384,0.1936194,0.1207791,0.00167504,0.00185634,0.6766925],"study_design_scores_gemma":[0.00000662403,0.00009863439,0.003833245,0.000008456845,0.00001802703,0.00009829455,0.00003449888,0.9843923,0.01024544,0.0005815562,0.0006645528,0.00001845245],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1721501,0.0003692769,0.8215445,0.0001060611,0.00004922959,0.00006958938,0.0001896655,0.003969485,0.001552086],"genre_scores_gemma":[0.7893739,0.0002331739,0.2082379,0.00005534502,0.00002493889,0.00005348194,0.0003095135,0.00005711841,0.001654627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002852769,"threshold_uncertainty_score":0.005672395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0173491025739185,"score_gpt":0.2880728412194207,"score_spread":0.2707237386455022,"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."}}