{"id":"W2151553160","doi":"10.1117/12.718272","title":"Defect quantification with reference-free thermal contrast and artificial neural networks","year":2007,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Universidad del Valle; Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Contrast (vision); Artificial neural network; Thermal; Computer science; Point (geometry); Sample (material); Fourier transform; Materials science; Artificial intelligence; Mathematics; Physics; Mathematical analysis; Geometry; Thermodynamics","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":[0.000568674,0.0002853896,0.0003020136,0.00009928839,0.00007571619,0.0000927537,0.0005443905,0.0001875267,0.000004893513],"category_scores_gemma":[0.0001043575,0.0002260315,0.0002665428,0.0002775086,0.000241557,0.0003096714,0.00005985859,0.0003636177,9.821044e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004375262,"about_ca_system_score_gemma":0.000007464363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008517548,"about_ca_topic_score_gemma":8.250909e-7,"domain_scores_codex":[0.9984796,1.317451e-8,0.0004999087,0.0002692538,0.0003711866,0.0003800275],"domain_scores_gemma":[0.9990277,0.00016148,0.0001685502,0.00006900746,0.0004672291,0.0001060351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000204634,0.00004691845,0.0004749192,0.000204121,0.0003242501,1.546345e-7,0.0001260118,0.00134687,0.7705615,0.2245926,0.0005014932,0.001616559],"study_design_scores_gemma":[0.001810126,0.0009207164,0.01590143,0.0005205256,0.0004868056,0.00006240603,0.001743195,0.3940528,0.5798227,0.002115931,0.001445322,0.001118081],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995302,0.000176707,0.001666823,0.0002937454,0.0001247446,0.0004658369,0.00006794816,0.0002634737,0.001638763],"genre_scores_gemma":[0.9807807,0.00006374437,0.01878795,0.00004578985,0.0001840329,0.00006600395,0.000008362444,0.00005627152,0.000007191915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3927059,"threshold_uncertainty_score":0.9217297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01233313370467458,"score_gpt":0.2163922359589784,"score_spread":0.2040591022543038,"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."}}