{"id":"W4397013665","doi":"10.1007/s12559-024-10283-3","title":"Generative Model-Driven Synthetic Training Image Generation: An Approach to Cognition in Railway Defect Detection","year":2024,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; King Saud University","keywords":"Computer science; Artificial intelligence; Autoencoder; Scarcity; Convolutional neural network; Deep learning; Machine learning; Generative grammar; Synthetic data; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0001572383,0.0001971233,0.0001571985,0.0003245499,0.00009304502,0.0001706487,0.0000360064,0.00008455451,0.000003746866],"category_scores_gemma":[0.00003902029,0.0002115261,0.00005647692,0.0003453828,0.00002548182,0.0005036743,0.00001278574,0.0002176597,0.00002648692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602808,"about_ca_system_score_gemma":0.00003048451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002749176,"about_ca_topic_score_gemma":0.0000188833,"domain_scores_codex":[0.9989722,0.00006863561,0.0002235373,0.0003536924,0.0001413458,0.0002406071],"domain_scores_gemma":[0.999674,0.00005262065,0.00001834498,0.00003744025,0.0001467386,0.00007085981],"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":[0.00001193372,0.00001360551,0.000003830374,0.00005364614,0.00003068773,0.00000860369,0.00495254,0.66265,0.09634186,0.00006541986,0.0000204491,0.2358474],"study_design_scores_gemma":[0.0002483162,0.0000560125,0.0002746572,0.000159441,0.00003998573,0.0000178981,0.0008306038,0.9600988,0.03751487,0.0005072127,0.000007838462,0.0002443636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.326174,0.00006538586,0.6706459,0.00000635383,0.0004115216,0.000303819,0.00001501757,0.0002512743,0.002126778],"genre_scores_gemma":[0.9846994,0.000007893967,0.01426519,0.0000458305,0.0005310425,0.0001834154,0.00020827,0.00005092036,0.00000809441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6585254,"threshold_uncertainty_score":0.8625785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03478185166390813,"score_gpt":0.2697508636475864,"score_spread":0.2349690119836783,"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."}}