{"id":"W4405800596","doi":"10.1190/geo2024-0242.1","title":"Filling the gap: Enhancing borehole imaging with a tensor neural network","year":2024,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Borehole; Geology; Tensor (intrinsic definition); Artificial neural network; Seismology; Computer science; Artificial intelligence; Geometry; Mathematics; Geotechnical engineering","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":[0.0001835491,0.0001157409,0.00009048139,0.00002527529,0.0002634187,0.0002062789,0.0001676162,0.00001600769,0.0001680781],"category_scores_gemma":[0.0000066198,0.00006592781,0.00005003028,0.0003034399,0.00008643491,0.0002316206,0.00001246387,0.0002249452,0.0001774062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002762667,"about_ca_system_score_gemma":0.00003431491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001437184,"about_ca_topic_score_gemma":0.00002941316,"domain_scores_codex":[0.9991728,0.00003272463,0.0001017929,0.0002092368,0.0001742198,0.0003092347],"domain_scores_gemma":[0.9995861,0.0001472359,0.00002649309,0.0001753602,0.00002309946,0.00004168912],"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":[0.0000363108,0.0000102912,0.03179448,0.0000859677,0.00005989458,0.0002225943,0.001485314,0.02848303,0.0001975525,0.000755592,0.129712,0.807157],"study_design_scores_gemma":[0.00007682067,0.0000647206,0.007190535,0.0001967578,0.00003930944,0.00007418863,0.0004663145,0.8993623,0.0007359789,0.006353645,0.08516177,0.0002776942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8937681,0.01234774,0.01971196,0.01226551,0.003239151,0.0006603427,0.00008442219,0.002537278,0.05538554],"genre_scores_gemma":[0.994348,0.00002971457,0.001363632,0.003165643,0.0006308123,0.000001422886,0.00002871107,0.000007211603,0.0004247839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8708792,"threshold_uncertainty_score":0.2688458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009651655124649565,"score_gpt":0.1996677375491552,"score_spread":0.1900160824245057,"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."}}