{"id":"W4387503046","doi":"10.1190/geo2022-0741.1","title":"A deep learning benchmark for first break detection from hardrock seismic reflection data","year":2023,"lang":"en","type":"article","venue":"Geophysics","topic":"Seismology and Earthquake Studies","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Deep learning; Overfitting; Computer science; Machine learning; Benchmarking; Benchmark (surveying); Artificial intelligence; Data set; Baseline (sea); Reflection (computer programming); Set (abstract data type); Generalization; Data mining; Artificial neural network; Geology","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":[0.0001895965,0.0001202952,0.0001471634,0.00005978281,0.0006842903,0.0000656138,0.0005099839,0.00007244049,0.000002918231],"category_scores_gemma":[0.00009904201,0.0001217979,0.00005116121,0.0005084221,0.00002776008,0.0004447412,0.0004422661,0.000163973,0.0002805384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001985208,"about_ca_system_score_gemma":0.00001559729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002738853,"about_ca_topic_score_gemma":0.0002046363,"domain_scores_codex":[0.9989417,0.00004669563,0.0001251536,0.0004868681,0.0001196714,0.0002798984],"domain_scores_gemma":[0.9989836,0.0003029332,0.00007109901,0.0005610011,0.00004933923,0.00003203166],"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":[0.00009576734,0.00005040027,0.002278885,0.00006225942,0.0002724915,0.00001537769,0.00374211,0.02367272,0.001137253,0.0007340375,0.00753543,0.9604033],"study_design_scores_gemma":[0.0004040361,0.0002200053,0.02660028,0.00001372049,0.00003178889,0.000004599141,0.000100619,0.9035401,0.0007544928,0.02355365,0.04456038,0.0002163586],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2737509,0.0001002705,0.7229737,0.0007619875,0.001454253,0.0001842002,0.00001494955,0.000548634,0.0002110915],"genre_scores_gemma":[0.9969941,0.0000552066,0.001735212,0.0001655787,0.0004238578,0.00004303892,0.0001951437,0.00001130601,0.0003765767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9601869,"threshold_uncertainty_score":0.5263077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03617926290698817,"score_gpt":0.2657023791032034,"score_spread":0.2295231161962152,"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."}}