{"id":"W4324357141","doi":"10.1016/j.jag.2023.103248","title":"SCL-GCN: Stratified Contrastive Learning Graph Convolution Network for pavement crack detection from mobile LiDAR point clouds","year":2023,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Jiangsu Province; Central University of Finance and Economics; National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Graph; Artificial intelligence; Deep learning; Lidar; Feature (linguistics); Adjacency list; Pattern recognition (psychology); Algorithm; Computer vision; Remote sensing; Theoretical computer science; Geography","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":[0.0003477013,0.0006470865,0.0004876128,0.0004594138,0.0002410109,0.0003983122,0.001229659,0.0007029671,0.0009321461],"category_scores_gemma":[0.001055108,0.0003216704,0.000573351,0.0005182709,0.0004609032,0.0008507433,0.0006975802,0.0009359631,0.0003264429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008185924,"about_ca_system_score_gemma":0.0008036845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01726169,"about_ca_topic_score_gemma":0.01681241,"domain_scores_codex":[0.9998078,0.00002398829,0.000008068303,0.00006700283,0.00005768596,0.0000354142],"domain_scores_gemma":[0.9997563,0.000072749,0.00002507838,0.00003410353,0.0000936582,0.00001812244],"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":[0.0002025233,0.0001243355,0.003058981,0.00007443244,0.00008236398,0.000151864,0.00009149534,0.6519644,0.02262421,0.004097964,0.00391859,0.3136089],"study_design_scores_gemma":[0.000002184881,0.0000126595,0.0002176747,0.000002009224,0.000004012102,0.0000115697,0.000002945558,0.9976071,0.001223115,0.0007138246,0.000199601,0.000003308218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08977892,0.0005303061,0.9043074,0.0002337664,0.00006723337,0.00007754433,0.0002623751,0.002715183,0.002027182],"genre_scores_gemma":[0.8094947,0.000308204,0.1840425,0.0002702005,0.00003801783,0.0001285224,0.001018938,0.0001153288,0.004583511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01726169,"threshold_uncertainty_score":0.03432244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008349877106050337,"score_gpt":0.2111578094879037,"score_spread":0.2028079323818534,"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."}}