{"id":"W3144117020","doi":"10.1063/5.0026653","title":"Quantification of pitting corrosion from thermography using deep neural networks","year":2021,"lang":"en","type":"article","venue":"Review of Scientific Instruments","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Natural Science Foundation of China; Foundation of Science and Technology on Near-Surface Detection Laboratory","keywords":"Thermography; Corrosion; Pitting corrosion; Materials science; Pipeline transport; Nondestructive testing; Metallurgy; Environmental science; Infrared; Optics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000362256,0.0008972294,0.0003781399,0.0008092129,0.0001277856,0.0004531848,0.0004799858,0.0006200576,0.0005148211],"category_scores_gemma":[0.0008423004,0.0002972412,0.0004194691,0.0004721601,0.0002661483,0.0007431312,0.0004083634,0.0006571249,0.0002002829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005482822,"about_ca_system_score_gemma":0.0003339008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002830332,"about_ca_topic_score_gemma":0.004576331,"domain_scores_codex":[0.9998116,0.00002451639,0.00001153846,0.00004948661,0.00007702012,0.00002587487],"domain_scores_gemma":[0.9996572,0.00008349674,0.00007551753,0.00002341321,0.0001460932,0.00001431863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002467295,0.0001966903,0.007968739,0.0003297892,0.0001562319,0.000181583,0.0001185143,0.4901833,0.1289131,0.001216133,0.00143742,0.3690518],"study_design_scores_gemma":[0.000001943596,0.00003681331,0.002039594,0.000007595994,0.00001364485,0.00002437538,0.00001002084,0.9846447,0.01266338,0.0003461948,0.0002018418,0.000009783502],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2094957,0.001097925,0.7853062,0.0001845484,0.00007301618,0.0000535853,0.0002773768,0.001228185,0.002283498],"genre_scores_gemma":[0.9074451,0.0007351055,0.08895924,0.00007305808,0.00003149933,0.00005512368,0.0003443521,0.00004186975,0.002314645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002830332,"threshold_uncertainty_score":0.005627692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0191549543797194,"score_gpt":0.2492536771740978,"score_spread":0.2300987227943784,"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."}}