{"id":"W4408097917","doi":"10.1190/tle44030187.1","title":"Ground-truth-calibrated onshore and offshore subsurface infrastructure image from deep-learning-based 3D inversion of magnetic data","year":2025,"lang":"en","type":"article","venue":"The Leading Edge","topic":"Geophysical and Geoelectrical Methods","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Newfoundland and Labrador Centre for Applied Health Research","funders":"","keywords":"Submarine pipeline; Inversion (geology); Ground truth; Geology; Geophysics; Artificial intelligence; Remote sensing; Seismology; Computer science; Oceanography; Tectonics","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":[0.0002828143,0.0001492361,0.0002482472,0.00005966774,0.0001715411,0.00006548068,0.0005414365,0.00009319789,0.000463001],"category_scores_gemma":[0.0003249757,0.00009627776,0.00003256278,0.0006047208,0.0002313313,0.0001404484,0.00008184021,0.0003819881,0.00005282474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003392965,"about_ca_system_score_gemma":0.00003945147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009878036,"about_ca_topic_score_gemma":0.0001991654,"domain_scores_codex":[0.9987338,0.0003531685,0.0001809786,0.0003289047,0.0001611549,0.0002420028],"domain_scores_gemma":[0.9981148,0.00130538,0.00007097158,0.0004003416,0.00003273886,0.00007572769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003447895,0.00004491247,0.2640254,0.0001434582,0.0000783923,0.00001170968,0.0004663393,0.005070923,0.00421237,0.0001685674,0.00404635,0.7213867],"study_design_scores_gemma":[0.0002749596,0.0001220581,0.643741,0.00004007517,0.00007460145,6.50872e-7,0.00007050719,0.3468916,0.0008009382,0.005120003,0.002736613,0.0001270052],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930813,0.001580435,0.002114762,0.0008427743,0.0002446869,0.0001382895,0.00008860432,0.00005378829,0.001855315],"genre_scores_gemma":[0.9952655,0.00003355054,0.003760897,0.0002512129,0.00005369761,3.366111e-7,0.0002847867,0.000003774227,0.0003462393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7212597,"threshold_uncertainty_score":0.5069537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499351367822272,"score_gpt":0.2424896218933468,"score_spread":0.2274961082151241,"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."}}