{"id":"W2884233295","doi":"10.21611/qirt.2018.107","title":"Rail inspection using active thermography to detect rolled-in material","year":2018,"lang":"en","type":"article","venue":"Proceedings of the 2018 International Conference on Quantitative InfraRed Thermography","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Thermography; Computer science; Computer vision; Artificial intelligence; Optics; Infrared; Physics","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":[0.0002778563,0.000385677,0.0002269648,0.0005183801,0.0001092449,0.0004220999,0.0004236262,0.0004492501,0.001286098],"category_scores_gemma":[0.000482434,0.0002258992,0.0001542954,0.0002656276,0.0003385297,0.0005045107,0.0002758774,0.000247595,0.0003791172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001584731,"about_ca_system_score_gemma":0.0001263708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003099836,"about_ca_topic_score_gemma":0.0005780791,"domain_scores_codex":[0.9997229,0.00004106447,0.000008136137,0.0000691478,0.0001393046,0.000019497],"domain_scores_gemma":[0.9996589,0.0001251521,0.00007835105,0.00003885122,0.00008741208,0.00001132097],"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":[0.00009546123,0.00002645968,0.0007070114,0.00008690519,0.000005893164,0.00004015331,0.00005983402,0.0005483326,0.983301,0.0001274067,0.00008404332,0.01491751],"study_design_scores_gemma":[0.00001458475,0.0004854593,0.007787959,0.000022918,0.00003975047,0.0003270276,0.00006919797,0.02420061,0.9649612,0.0001196691,0.001947329,0.00002431015],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7478124,0.001961237,0.2439734,0.00008367317,0.0001023032,0.00009467534,0.000101957,0.001152996,0.004717131],"genre_scores_gemma":[0.9611914,0.0004402264,0.03627804,0.00003647108,0.0000184163,0.00001746111,0.00004788902,0.00004724365,0.001922784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001286098,"threshold_uncertainty_score":0.004302382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03266786299376405,"score_gpt":0.2817150833475895,"score_spread":0.2490472203538254,"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."}}