{"id":"W4406095416","doi":"10.1007/s13349-024-00905-7","title":"Damage identification method of arch bridges using MobileViT and transfer learning","year":2025,"lang":"en","type":"article","venue":"Journal of Civil Structural Health Monitoring","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Arch; Identification (biology); Structural engineering; Engineering; Computer science; Biology","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":[0.001013687,0.0002265931,0.0005958446,0.000491197,0.0002053991,0.00004434344,0.0002374348,0.0001213597,0.000003674502],"category_scores_gemma":[0.00008299977,0.0002134505,0.0001010332,0.0003787531,0.00005293568,0.0003658017,0.00003896345,0.0007618926,8.105905e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004454764,"about_ca_system_score_gemma":0.0001301471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002147163,"about_ca_topic_score_gemma":0.000009871335,"domain_scores_codex":[0.997628,0.0001912362,0.00126374,0.0001723185,0.0003598607,0.000384884],"domain_scores_gemma":[0.9988531,0.0002555047,0.0003021998,0.0001774324,0.0002475276,0.0001641988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001358603,0.00001061952,0.1528423,0.005979627,0.0001783639,0.00001089811,0.002920697,0.07456228,0.09662612,0.0004098108,0.00004667994,0.6662768],"study_design_scores_gemma":[0.0006775221,0.0002436196,0.8344647,0.002334442,0.00007347538,0.0001877231,0.0007540908,0.02835649,0.1310204,0.001290807,0.0002873389,0.000309449],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708956,0.003643276,0.02278745,0.00007896088,0.002241825,0.0002210759,0.000003799974,0.0001002829,0.00002770281],"genre_scores_gemma":[0.9761533,0.001088679,0.02223999,0.000006730312,0.0004633824,0.000003401605,7.113405e-7,0.00003184714,0.00001196977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6816224,"threshold_uncertainty_score":0.8704261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03056840017812663,"score_gpt":0.3772613365309964,"score_spread":0.3466929363528698,"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."}}