{"id":"W4417508745","doi":"10.1109/tim.2025.3644563","title":"RMSDNet: A Lightweight Object Detection Network for Rail Surface Defect","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Advanced Metallurgy; Beijing Jiaotong University","keywords":"Object detection; Feature extraction; Convolution (computer science); Redundancy (engineering); Feature (linguistics); Block (permutation group theory); Process (computing); Surface (topology); Noise (video)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006344538,0.0004980014,0.0003928035,0.0002776845,0.0006157435,0.0001776637,0.0001070933,0.0002653519,0.00003437745],"category_scores_gemma":[0.0000103392,0.000567628,0.0003078635,0.0005828136,0.0000486327,0.000208626,0.000001269811,0.0003744892,0.00001333672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008545027,"about_ca_system_score_gemma":0.0001236472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005079854,"about_ca_topic_score_gemma":0.0004143071,"domain_scores_codex":[0.9977608,0.00007605611,0.0006362657,0.0005245939,0.000448663,0.0005536499],"domain_scores_gemma":[0.999145,0.0001061302,0.00008690493,0.0002992637,0.0001938086,0.0001689243],"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":[0.0002605306,0.0001241904,0.00001738739,0.0005180262,0.0007065675,7.235807e-7,0.0003347716,0.8154202,0.01225308,0.0001793682,0.0002399645,0.1699452],"study_design_scores_gemma":[0.00659676,0.0008944951,0.0007989943,0.001198456,0.00127924,0.00001523881,0.0004479293,0.7755733,0.198598,0.0004187635,0.0130548,0.00112397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04312486,0.001028703,0.9459837,0.0001691568,0.007138282,0.00135919,0.00009133788,0.0003087225,0.0007960604],"genre_scores_gemma":[0.9936721,0.00115635,0.004006488,0.000119292,0.0001129145,0.0002685667,0.00001065592,0.00006736813,0.0005863133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9505472,"threshold_uncertainty_score":0.9996775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01508889778103459,"score_gpt":0.2247886983003282,"score_spread":0.2096998005192936,"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."}}