{"id":"W4410639425","doi":"10.1109/tgrs.2025.3573023","title":"Point-SCT: A Multiscale Spatial Convolution-Swin Transformer Network for Point Cloud Ground Filtering in Complex Mountainous Terrains","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Shanxi Province; National Natural Science Foundation of China","keywords":"Terrain; Computer science; Point cloud; Convolution (computer science); Scale (ratio); Remote sensing; Cloud computing; Artificial intelligence; Geology; Cartography; Geography; Artificial neural network","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":[0.0004006361,0.0002236032,0.000242241,0.0001348342,0.0009259342,0.00009399292,0.0001305043,0.0001226527,0.00002585908],"category_scores_gemma":[0.000008650661,0.0002174356,0.000106877,0.0005874604,0.0005141963,0.0001930589,0.000004618798,0.000265381,0.00001439793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002340339,"about_ca_system_score_gemma":0.00003532557,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01034581,"about_ca_topic_score_gemma":0.0101406,"domain_scores_codex":[0.9982296,0.00006197106,0.0003682413,0.0005860971,0.000203772,0.000550339],"domain_scores_gemma":[0.9993887,0.0001503999,0.00006125323,0.0002723434,0.00001796154,0.0001093372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008938181,0.00008748727,0.00002078576,0.00002631233,0.00001369632,0.000005481489,0.001595081,0.02090251,0.04029669,0.00003073002,0.0001862232,0.9367456],"study_design_scores_gemma":[0.001060363,0.0001206602,0.009388603,0.0001776666,0.00004049425,0.00007230261,0.0007230242,0.9775645,0.004397524,0.001468721,0.004594778,0.0003914252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1808284,0.000009971322,0.8160613,0.0009921762,0.0004002345,0.0005481167,0.00001544117,0.00005811702,0.00108622],"genre_scores_gemma":[0.9258022,0.00003299298,0.07274864,0.0006359629,0.00005933823,0.000001023759,0.000005738592,0.00001589518,0.0006981912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9566619,"threshold_uncertainty_score":0.9962444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445399672323465,"score_gpt":0.2506958205243624,"score_spread":0.2362418238011278,"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."}}