{"id":"W3035952341","doi":"10.1061/(asce)cp.1943-5487.0000915","title":"Automated Defect Quantification in Concrete Bridges Using Robotics and Deep Learning","year":2020,"lang":"en","type":"article","venue":"Journal of Computing in Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Robotics; Artificial intelligence; Engineering; Deep learning; Computer science; Construction engineering; Civil engineering; Forensic engineering; Robot","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003201221,0.0001427451,0.0002892004,0.0002203311,0.00002357379,0.00004718044,0.00009173167,0.00006778543,6.363256e-7],"category_scores_gemma":[0.0002008941,0.0001551815,0.00004767908,0.0002888754,0.000009699558,0.0001495122,0.00002792678,0.0005543624,3.407068e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001169202,"about_ca_system_score_gemma":0.00001289594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005423327,"about_ca_topic_score_gemma":0.000003629331,"domain_scores_codex":[0.9990337,0.00002276059,0.0004829096,0.00009534334,0.0001228336,0.0002424138],"domain_scores_gemma":[0.9996197,0.0001140367,0.0001064867,0.0000457192,0.00004435192,0.00006967377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004104359,7.392743e-7,0.01355612,0.0001292583,0.0000154681,0.00004144283,0.0008835316,0.9633215,0.0213163,0.00003047949,0.000002189637,0.0006988338],"study_design_scores_gemma":[0.0003455725,0.00002787107,0.0300412,0.0004374117,0.00001033204,0.00007936875,0.0001369515,0.9675015,0.001232936,0.000002551554,0.00004183151,0.0001425202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8101371,0.0007685184,0.1885169,0.00001878615,0.000344446,0.00004209259,1.315925e-7,0.0001452045,0.00002676661],"genre_scores_gemma":[0.985819,0.00006983717,0.01385429,0.000008252114,0.0002149773,1.813705e-7,4.203314e-7,0.00003290624,1.567167e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1756819,"threshold_uncertainty_score":0.6328117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01160609960968598,"score_gpt":0.2255442682857138,"score_spread":0.2139381686760279,"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."}}