{"id":"W4403295440","doi":"10.1109/tgrs.2024.3477423","title":"Self-Supervised Pretraining Framework for Extracting Global Structures From Building Point Clouds via Completion","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Point cloud; Point (geometry); Artificial intelligence; Completion (oil and gas wells); Machine learning; Geology; Mathematics","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":[0.0003860866,0.0001932627,0.0001775258,0.00005892325,0.0009037935,0.0003904466,0.00009989756,0.0001338022,0.00005529803],"category_scores_gemma":[0.00002061461,0.0001545539,0.00009811375,0.0003841064,0.0001032758,0.0003487035,8.691964e-7,0.000309795,0.00000901159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002138002,"about_ca_system_score_gemma":0.00004340401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002100755,"about_ca_topic_score_gemma":0.0006081342,"domain_scores_codex":[0.9985548,0.00007839223,0.000220624,0.0005121349,0.0002594933,0.0003745947],"domain_scores_gemma":[0.9991513,0.0005043329,0.00004170083,0.0001309949,0.00003776772,0.0001338492],"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":[0.00002653168,0.00000373027,0.00004200336,0.00003901814,0.00001994773,0.00001174313,0.0009790018,0.0009754265,0.001083857,0.00002935839,0.000002895136,0.9967865],"study_design_scores_gemma":[0.0001093018,0.00009682505,0.003501705,0.0002754003,0.00003968088,0.0000905644,0.0007012939,0.9840844,0.0008098795,0.009896207,0.000155808,0.000238975],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3396432,0.0002531358,0.6580873,0.000141338,0.001376848,0.0001255799,0.00009246024,0.00017919,0.0001009708],"genre_scores_gemma":[0.6206628,0.00003361047,0.3790668,0.00009635724,0.0001183853,4.204344e-8,0.000008060964,0.00000407985,0.000009851155],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9965475,"threshold_uncertainty_score":0.695134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02608840417167502,"score_gpt":0.2670768573024729,"score_spread":0.2409884531307979,"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."}}