{"id":"W4400956229","doi":"10.1016/j.aei.2024.102717","title":"Defect detection on multi-type rail surfaces via IoU decoupling and multi-information alignment","year":2024,"lang":"en","type":"article","venue":"Advanced Engineering Informatics","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Basic Research Program of Shaanxi Province; Natural Science Foundation of Hunan Province; China Scholarship Council; University of Waterloo; National Natural Science Foundation of China","keywords":"Decoupling (probability); Computer science; Artificial intelligence; Engineering; Materials science; Control 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002363672,0.0002621233,0.0002025642,0.0003042567,0.00007747005,0.0001807734,0.00005999327,0.0001503354,0.000004288248],"category_scores_gemma":[0.00005381244,0.0002527836,0.00007015294,0.0003468524,0.000008946195,0.001157449,0.00002100935,0.0002968463,0.000133043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002153769,"about_ca_system_score_gemma":0.000007452004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006091792,"about_ca_topic_score_gemma":0.000004122663,"domain_scores_codex":[0.9988641,0.000005845074,0.000552887,0.00009361749,0.0002060352,0.0002775023],"domain_scores_gemma":[0.9995548,0.00008759148,0.00004882683,0.0001688695,0.00004737062,0.00009259158],"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":[0.00000842017,0.000004596691,0.000004444265,0.0003304359,0.00004376071,0.000001020554,0.0005529193,0.8714962,0.009822913,0.00002675472,0.00003046744,0.1176781],"study_design_scores_gemma":[0.0004585247,0.0001209462,0.0000847645,0.0002296002,0.00001612824,0.00002422099,0.0001302121,0.9311002,0.0317083,0.000001984188,0.03584966,0.0002753934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2252034,0.0003739921,0.7700776,0.000003548707,0.002737496,0.0003270344,0.000007378549,0.001150914,0.0001186542],"genre_scores_gemma":[0.9864205,0.0001629973,0.01323196,0.00002674962,0.00005461951,0.00003151235,0.00001441546,0.00004118221,0.0000160754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7612171,"threshold_uncertainty_score":0.9999924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01098477162487129,"score_gpt":0.2271057419252353,"score_spread":0.216120970300364,"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."}}