{"id":"W4238498444","doi":"10.20944/preprints202008.0565.v1","title":"Defect Depth Estimation in Infrared Thermography with Deep Learning","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Université Laval","keywords":"Thermography; Immediacy; Finite element method; Infrared; Materials science; Nondestructive testing; Computer science; Structural engineering; Acoustics; Optics; Engineering; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003331405,0.000484907,0.0004862145,0.0004271878,0.00005497739,0.00003540741,0.0004803377,0.0003654298,0.0001656011],"category_scores_gemma":[0.00007662605,0.0004946548,0.0002609796,0.0005403035,0.00007255084,0.0001037884,0.0003355429,0.001918853,0.00003671643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000081987,"about_ca_system_score_gemma":0.00003319034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009002855,"about_ca_topic_score_gemma":0.00005248485,"domain_scores_codex":[0.9981361,0.000130805,0.000430061,0.0006670011,0.0002654897,0.0003705262],"domain_scores_gemma":[0.9989247,0.00009476289,0.0001373028,0.0006734285,0.0000446175,0.0001252158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001114728,0.00005763243,0.6026976,0.0006933309,0.0004102327,0.00005674018,0.00345144,0.3721783,0.01238909,0.00009096628,0.00002400974,0.00783912],"study_design_scores_gemma":[0.0005126908,0.00006631996,0.8761114,0.0007659797,0.0001475489,0.0000117113,0.0001354239,0.08916665,0.02457849,0.00658597,0.0008268913,0.001090889],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.925929,0.0004205728,0.05579136,0.00003358795,0.0001662454,0.0009074134,0.00002816132,0.002739856,0.01398384],"genre_scores_gemma":[0.9965127,0.0002349255,0.002519422,0.00005699922,0.00003372624,0.0004194673,0.00008642946,0.0001227546,0.00001357828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2830117,"threshold_uncertainty_score":0.9997505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04022311106985771,"score_gpt":0.2752249300701031,"score_spread":0.2350018190002454,"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."}}