{"id":"W3089524077","doi":"10.3390/app10196819","title":"A Method of Defect Depth Estimation for Simulated Infrared Thermography Data with Deep Learning","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Thermography; Finite element method; Materials science; Infrared; Nondestructive testing; Structural engineering; Acoustics; Composite material; Optics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003450598,0.0001013224,0.0001458825,0.00008361635,0.00009135828,0.00002727009,0.000378302,0.00004175047,0.000007610194],"category_scores_gemma":[0.00002542964,0.00007891502,0.000036111,0.0007795998,0.0001088752,0.000108234,0.00003072022,0.00008353459,2.157453e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002454478,"about_ca_system_score_gemma":0.00001136623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005783692,"about_ca_topic_score_gemma":0.000003644489,"domain_scores_codex":[0.9993467,0.00001673317,0.0001363852,0.0002158579,0.0001378911,0.0001463751],"domain_scores_gemma":[0.9994791,0.0002569851,0.00005246209,0.0001509138,0.00001802653,0.00004255091],"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":[0.0000699586,0.00001229474,0.0005359899,0.0001461517,0.00009334151,4.206269e-7,0.001745863,0.8081256,0.07582821,0.001423319,0.00005448095,0.1119644],"study_design_scores_gemma":[0.000203381,0.0001672731,0.0004323933,0.00001584074,0.00004976147,7.727922e-7,0.0002553827,0.9667838,0.03011061,0.001566898,0.0002724178,0.0001414424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03890784,0.0001074695,0.9577445,0.000008852649,0.00001051676,0.000341742,0.00003603019,0.0004192599,0.00242375],"genre_scores_gemma":[0.7968565,0.00000478721,0.2030565,0.00002422114,0.000009190805,0.00001720327,0.00002053515,0.00001062253,4.217071e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7579487,"threshold_uncertainty_score":0.3218061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03046937053437041,"score_gpt":0.2780274842734792,"score_spread":0.2475581137391088,"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."}}