{"id":"W4401274005","doi":"10.1002/nsg.12316","title":"A fine‐tuning workflow for automatic first‐break picking with deep learning","year":2024,"lang":"en","type":"article","venue":"Near Surface Geophysics","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Institut National de la Recherche Scientifique; Centre de Géomatique du Québec","funders":"Mitacs","keywords":"Overfitting; Computer science; Initialization; Artificial intelligence; Workflow; Artificial neural network; Set (abstract data type); Deep learning; Machine learning; Unavailability; Data mining; Pattern recognition (psychology); Database; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002096594,0.0001682254,0.0001713768,0.00002988371,0.0004048405,0.0003221933,0.0001537265,0.00005365989,0.0002536302],"category_scores_gemma":[0.00002671279,0.0001349699,0.00007500417,0.0003321236,0.00007745002,0.0002953362,0.00001276424,0.0002540417,0.0002543354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009415395,"about_ca_system_score_gemma":0.00006198783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001138568,"about_ca_topic_score_gemma":0.00009949555,"domain_scores_codex":[0.9989792,0.00003167344,0.0001374387,0.0002936414,0.0002110862,0.0003469244],"domain_scores_gemma":[0.9993436,0.0003468433,0.00004506432,0.0001552445,0.00003918665,0.00007004082],"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":[0.00003113757,0.00001700084,0.05059713,0.0004192335,0.00008574249,0.000039817,0.002749011,0.08003839,0.00005135883,0.0001365657,0.005022898,0.8608117],"study_design_scores_gemma":[0.0001197172,0.0001640463,0.002723368,0.0002824051,0.00002984396,0.000009384518,0.000144893,0.9428385,0.0001830848,0.0007336068,0.05255823,0.0002129106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9691831,0.001212604,0.02430764,0.0007324507,0.0004236029,0.0003049332,0.00001629018,0.001245186,0.002574138],"genre_scores_gemma":[0.9539754,0.00002097778,0.04477027,0.0002070036,0.0001042434,0.000002450432,0.00006596316,0.00001693925,0.0008367943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8628001,"threshold_uncertainty_score":0.5503913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009551043609012573,"score_gpt":0.2063269680376111,"score_spread":0.1967759244285985,"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."}}