{"id":"W3095998817","doi":"10.1061/(asce)cf.1943-5509.0001541","title":"Semantic Segmentation of Defects in Infrared Thermographic Images of Highly Damaged Concrete Structures","year":2020,"lang":"en","type":"article","venue":"Journal of Performance of Constructed Facilities","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Spall; Nondestructive testing; Delamination (geology); Thermography; Computer science; Segmentation; Artificial intelligence; Artificial neural network; Structural engineering; Pattern recognition (psychology); Computer vision; Forensic engineering; Engineering; Geology; Infrared","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":[0.0001594191,0.000167154,0.0005514307,0.0003278288,0.00001905556,0.000009093489,0.000184618,0.00008249652,0.00003855491],"category_scores_gemma":[0.00008389327,0.0001448176,0.0001199926,0.0003142845,0.0002716973,0.0003932605,0.00002132918,0.0002851964,1.7395e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003420981,"about_ca_system_score_gemma":0.00007849235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001090007,"about_ca_topic_score_gemma":0.000001290467,"domain_scores_codex":[0.998504,0.00003860912,0.00089352,0.00007271249,0.0002916718,0.0001994877],"domain_scores_gemma":[0.9990266,0.00007150241,0.000443246,0.0001069499,0.0002948373,0.00005684263],"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":[0.0002614261,0.000002694817,0.157249,0.00210678,0.0001655469,0.000007074561,0.005340626,0.01532551,0.8165701,0.0002032736,0.00003983915,0.002728184],"study_design_scores_gemma":[0.001359491,0.0003718448,0.1108079,0.0004413705,0.00004975192,0.00002829956,0.005611459,0.001705673,0.8792171,0.0002111593,0.00003460046,0.0001613907],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983948,0.0005421634,0.00029151,0.000007852352,0.0002741484,0.0001029847,0.0000508084,0.00001549103,0.0003202097],"genre_scores_gemma":[0.9976642,0.0003620657,0.001893794,0.000005812249,0.00005437591,0.000001092615,0.000003165543,0.00001239285,0.000003152964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06264701,"threshold_uncertainty_score":0.5905489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006882111097027214,"score_gpt":0.1925183726733702,"score_spread":0.1856362615763429,"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."}}