{"id":"W4400411299","doi":"10.1109/tgrs.2024.3424659","title":"A Test-Time Learning Approach to Reparameterize the Geophysical Inverse Problem With a Convolutional Neural Network","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada); University of British Columbia","funders":"","keywords":"Convolutional neural network; Inverse problem; Computer science; Artificial neural network; Geophysics; Test (biology); Artificial intelligence; 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":[0.0003335038,0.0001383156,0.0001172913,0.00009358657,0.0007335257,0.0002223931,0.00009942842,0.00004019941,0.00001512902],"category_scores_gemma":[0.00000841886,0.00008304984,0.0000492791,0.0006270041,0.0003528163,0.0002042917,0.000001482622,0.000368205,0.00005736851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008495394,"about_ca_system_score_gemma":0.00006125058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002127583,"about_ca_topic_score_gemma":0.000025697,"domain_scores_codex":[0.9988173,0.00007449856,0.000122807,0.0004003202,0.0002676916,0.0003174123],"domain_scores_gemma":[0.9994472,0.0002633603,0.00002404986,0.0001264146,0.00002835156,0.000110679],"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":[0.00006470304,0.00001304187,0.00001558584,0.00002006464,0.00001471248,0.00001984602,0.0007427686,0.0719093,0.0005943455,0.000005534772,0.0009058195,0.9256943],"study_design_scores_gemma":[0.00005523595,0.0002582622,0.0002883868,0.0001011629,0.00002045249,0.0002831623,0.0001200313,0.9952003,0.0002969125,0.0001401736,0.003095764,0.0001401992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2394764,0.00005528278,0.7537866,0.002716305,0.0003738634,0.0003934865,0.00001528219,0.000483714,0.002699148],"genre_scores_gemma":[0.891192,0.00002151942,0.104769,0.002107923,0.00008912658,1.986536e-7,0.000003338576,0.000006519086,0.001810393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9255541,"threshold_uncertainty_score":0.5641761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01101724822099591,"score_gpt":0.2020342264036272,"score_spread":0.1910169781826313,"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."}}