{"id":"W4401836478","doi":"10.1016/j.aiig.2024.100087","title":"Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface data","year":2024,"lang":"en","type":"article","venue":"Artificial Intelligence in Geosciences","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Geoscience BC","funders":"","keywords":"Surface (topology); Invertible matrix; Scale (ratio); Artificial neural network; Segmentation; Mathematics; Market segmentation; Artificial intelligence; Computer science; Geometry; Geology; Pattern recognition (psychology); Geography; Cartography; Pure mathematics; Economics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001824148,0.0001793985,0.0001873249,0.0001707529,0.0003050657,0.001247357,0.001630833,0.00007463233,0.000003469222],"category_scores_gemma":[0.00006393083,0.0001654742,0.00004377078,0.001819802,0.0001815051,0.001470537,0.0009700202,0.0001663425,0.000003261795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001763959,"about_ca_system_score_gemma":0.00007876778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002885204,"about_ca_topic_score_gemma":0.0006397623,"domain_scores_codex":[0.9976691,0.00007172852,0.0004684137,0.0009705813,0.0002832302,0.0005369746],"domain_scores_gemma":[0.9988585,0.000332639,0.00006802482,0.0005620754,0.0000797017,0.00009904696],"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":[0.00001183276,0.0001487223,0.004237041,0.0001027354,0.0000131819,0.00001816731,0.004037588,0.02575742,0.003145048,0.4795348,0.0006081758,0.4823853],"study_design_scores_gemma":[0.00001197468,0.0000782861,0.000119303,0.00005824897,0.000003585947,0.000005791544,0.000241062,0.9611252,0.005346678,0.03191749,0.0008869289,0.0002054577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2084113,0.001176687,0.7885424,0.00055915,0.0007677851,0.0002653364,0.00001126816,0.0002425406,0.00002347794],"genre_scores_gemma":[0.9695132,0.0003039594,0.02981789,0.000202748,0.0001093278,0.000009372846,0.00001095681,0.00001064699,0.00002192518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9353678,"threshold_uncertainty_score":0.9997894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07135544442361007,"score_gpt":0.3448330432967888,"score_spread":0.2734775988731787,"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."}}