{"id":"W3194683814","doi":"10.1139/cjce-2020-0808","title":"Classification of surface pavement cracks as top-down, bottom-up, and cement-treated reflective cracking based on deep learning methods","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Louisiana Transportation Research Center","keywords":"Cracking; Pavement management; Asphalt; Road surface; Fatigue cracking; Cement; Artificial neural network; Asphalt concrete; Convolutional neural network; Geotechnical engineering; Structural engineering; Engineering; Civil engineering; Computer science; Materials science; Artificial intelligence; Composite material","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003889476,0.0001896847,0.0002874306,0.0002856985,0.00007525914,0.00005620803,0.00009709383,0.00009651274,0.00007621025],"category_scores_gemma":[0.0002704152,0.0002021449,0.00007547458,0.0002904446,0.00001908724,0.0001367932,0.000008020708,0.0005165024,8.226909e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003913857,"about_ca_system_score_gemma":0.0001966118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779056,"about_ca_topic_score_gemma":0.002034237,"domain_scores_codex":[0.9989153,0.00005331781,0.0003914938,0.0001372688,0.0001647358,0.0003378473],"domain_scores_gemma":[0.9990613,0.0001233555,0.0001213355,0.0001405267,0.0002727699,0.000280741],"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":[0.000007131879,0.000003348785,0.004753769,0.00009832043,0.00009484374,0.00007961097,0.0006188515,0.8785712,0.1100635,0.0001606692,0.00004463603,0.005504202],"study_design_scores_gemma":[0.001357407,0.0003174942,0.03785291,0.001442203,0.0001609006,0.0001552599,0.001683725,0.612882,0.3339441,0.0001797536,0.009327728,0.0006965418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6844244,0.002501657,0.3062937,0.0001331533,0.002198112,0.0001672441,0.000006160573,0.00007474924,0.004200833],"genre_scores_gemma":[0.9903509,0.00005396157,0.009358562,0.00002302974,0.0001240396,0.000002017346,0.000003937137,0.00004271624,0.00004081642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3059266,"threshold_uncertainty_score":0.8243232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01016261003697802,"score_gpt":0.2525592174534015,"score_spread":0.2423966074164235,"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."}}