{"id":"W4405422801","doi":"10.1016/j.jag.2024.104259","title":"An enhanced network for extracting tunnel lining defects using transformer encoder and aggregate decoder","year":2024,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Shenzhen University; National Natural Science Foundation of China","keywords":"Encoder; Aggregate (composite); Transformer; Computer science; Engineering; Materials science; Electrical engineering; Composite material; Voltage","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":[0.0002954665,0.0001076748,0.0001135432,0.000132799,0.00007295122,0.0002278689,0.00005992581,0.00006474746,0.000006414206],"category_scores_gemma":[0.00001354497,0.00009870104,0.00003831437,0.00007073249,0.00001258339,0.001395456,0.000004374718,0.0001489513,7.493752e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003101689,"about_ca_system_score_gemma":0.00002688012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001667472,"about_ca_topic_score_gemma":0.000005633726,"domain_scores_codex":[0.9992148,0.000003680564,0.000406136,0.00006823711,0.0001679482,0.0001391426],"domain_scores_gemma":[0.9995602,0.00006492611,0.0001135986,0.00003391325,0.0001757425,0.00005160258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001349244,0.000004807146,0.0002924521,0.0001638238,0.0001393908,0.000002538488,0.00465135,0.5888508,0.05919557,0.002822647,0.00005510921,0.3436866],"study_design_scores_gemma":[0.0007077184,0.0000512763,0.006132,0.0003661964,0.0000413588,0.00006830461,0.0006316713,0.9636996,0.0209421,0.002666692,0.004499269,0.0001937522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6450315,0.0001480011,0.3534968,0.00002539963,0.0009167912,0.00008894539,0.000003325905,0.00003491348,0.0002543054],"genre_scores_gemma":[0.9662166,0.0001951966,0.03270563,0.0001037423,0.0007337929,0.000004547961,0.00002047295,0.00001476648,0.000005219732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3748489,"threshold_uncertainty_score":0.4024912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01345336327699552,"score_gpt":0.256277374726171,"score_spread":0.2428240114491755,"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."}}