{"id":"W4394817068","doi":"10.3997/2214-4609.202332088","title":"A Deep Learning Seismic Processing Framework Based on Pre-Training: Giving the Dataset the Attention It Needs","year":2023,"lang":"en","type":"article","venue":"","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Extrapolation; Data processing; Task (project management); Noise (video); Machine learning; Transfer of learning; Deep learning; Property (philosophy); Task analysis; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007960538,0.0009665323,0.0005456359,0.0003899884,0.0003759203,0.0006438528,0.001503983,0.001190531,0.002016829],"category_scores_gemma":[0.002032963,0.0005141642,0.0004945827,0.0005644802,0.0007876742,0.001647554,0.001429813,0.002355997,0.0006372759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006249356,"about_ca_system_score_gemma":0.001245541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00513558,"about_ca_topic_score_gemma":0.009605274,"domain_scores_codex":[0.9997786,0.00004517688,0.00001139778,0.00007045356,0.00006050947,0.00003377566],"domain_scores_gemma":[0.9994392,0.0001814587,0.00004638431,0.0001419032,0.0001577696,0.00003330346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001688635,0.0001458482,0.001109404,0.00008128565,0.00004484112,0.0001020263,0.00007855031,0.7504795,0.02949448,0.01241724,0.003414353,0.2024637],"study_design_scores_gemma":[0.000004514623,0.00002881103,0.0001453984,0.000004516794,0.00000428027,0.00001379305,0.000006906369,0.9907652,0.004371942,0.003889643,0.0007599379,0.00000498801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0115835,0.00007934056,0.9862829,0.0002146543,0.00001976326,0.00002397938,0.0001128643,0.0008760797,0.0008069628],"genre_scores_gemma":[0.3644317,0.0002812513,0.6285681,0.0003812401,0.00008938959,0.000183506,0.001308319,0.0002138632,0.004542718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00513558,"threshold_uncertainty_score":0.01021135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02811423267223532,"score_gpt":0.2613363762969315,"score_spread":0.2332221436246962,"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."}}