{"id":"W2884473836","doi":"10.21611/qirt.2018.p27","title":"Application of Deep Learning in Infrared Non-Destructive Testing","year":2018,"lang":"en","type":"article","venue":"Proceedings of the 2018 International Conference on Quantitative InfraRed Thermography","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Universidad de Oviedo; Université Laval","keywords":"Computer science; Infrared; Deep learning; Artificial intelligence; Optics; Physics","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":[0.0003102409,0.0001605211,0.0002224198,0.0004637994,0.00006499144,0.00003339161,0.0003759566,0.0001110431,0.00002840915],"category_scores_gemma":[0.0003184017,0.0001315851,0.00009428593,0.0008858619,0.0002130352,0.0002481838,0.00005185053,0.0002729635,0.000008265873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005114084,"about_ca_system_score_gemma":0.00001625393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005361541,"about_ca_topic_score_gemma":0.00000538704,"domain_scores_codex":[0.9988623,0.00001724133,0.0004567115,0.0001925678,0.0003248591,0.0001463112],"domain_scores_gemma":[0.9983739,0.0001092852,0.0003840092,0.00008845189,0.001016838,0.00002746958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005036444,0.0001018312,0.08107189,0.0001359576,0.0002829754,2.54906e-7,0.005582711,0.001005155,0.7575409,0.1235076,0.0001253862,0.03014173],"study_design_scores_gemma":[0.002023732,0.001681471,0.2860289,0.001545956,0.00004141918,0.000007783465,0.007663646,0.3065004,0.2916876,0.1014772,0.0006458248,0.0006959797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8820733,0.00001560202,0.002109792,0.00001677182,0.0004448523,0.0003484807,0.00001341659,0.00006343983,0.1149143],"genre_scores_gemma":[0.9985249,0.000006879733,0.001270076,0.000008481934,0.00008118316,0.00004449993,0.00000191025,0.00002029463,0.00004174181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4658532,"threshold_uncertainty_score":0.5365885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03236050638024989,"score_gpt":0.2732233282198822,"score_spread":0.2408628218396323,"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."}}