{"id":"W4410069780","doi":"10.1007/s13349-025-00957-3","title":"Automated structural integrity assessment of bridges: a hybrid machine learning and feature-based framework","year":2025,"lang":"en","type":"article","venue":"Journal of Civil Structural Health Monitoring","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"National Research Foundation of Korea","keywords":"Structural integrity; Feature (linguistics); Computer science; Artificial intelligence; Engineering; Machine learning; Structural engineering","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":[0.0007761794,0.000838915,0.001475879,0.002268524,0.0004518758,0.0009783757,0.001602343,0.001452926,0.001306013],"category_scores_gemma":[0.00168763,0.000321039,0.001223128,0.001087899,0.0003760875,0.00122991,0.0009673905,0.0007956063,0.0005335364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004503858,"about_ca_system_score_gemma":0.0009054706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006630423,"about_ca_topic_score_gemma":0.007616876,"domain_scores_codex":[0.9994085,0.0001030547,0.00003421884,0.000176095,0.0001903997,0.0000878104],"domain_scores_gemma":[0.9992114,0.0003018971,0.0001028915,0.00009928006,0.0002384666,0.0000459342],"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":[0.0002142335,0.0005321557,0.007728063,0.0001025635,0.0001936928,0.0002140095,0.00005863083,0.3996618,0.01924915,0.002685938,0.002694204,0.5666655],"study_design_scores_gemma":[0.000003509533,0.00004009712,0.0009073201,0.000004213247,0.00001449663,0.00002588243,0.000005962412,0.9965448,0.001048493,0.001230778,0.0001689595,0.000005476476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05369153,0.0002794055,0.9427489,0.0001417392,0.00002119952,0.00006920305,0.0002965898,0.001876042,0.0008754545],"genre_scores_gemma":[0.7534517,0.0001761546,0.2433015,0.0001014862,0.00007996926,0.0001111519,0.001053215,0.0001095809,0.001615333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006630423,"threshold_uncertainty_score":0.01318365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009340066837307386,"score_gpt":0.3239583966056592,"score_spread":0.3146183297683518,"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."}}