{"id":"W4413132051","doi":"10.5194/ecss2025-86","title":"Automated Hailpad Dent Detection and Segmentation Using Machine Learning","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Pipeline (software); Segmentation; Convolutional neural network; Thresholding; Intersection (aeronautics); Process (computing); Deep learning; Pattern recognition (psychology); Binary number; False positive paradox; Data mining; Machine learning; Computer vision; Image (mathematics); 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":[0.0004923464,0.001329788,0.0008772183,0.001722468,0.0003829654,0.001375475,0.001818111,0.00123546,0.002194598],"category_scores_gemma":[0.001112504,0.0007908744,0.001439572,0.0006503797,0.0005151721,0.0008259986,0.001068988,0.0009426856,0.001379916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000771859,"about_ca_system_score_gemma":0.0009846466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007217099,"about_ca_topic_score_gemma":0.01600233,"domain_scores_codex":[0.9995018,0.00002561518,0.00002766686,0.000171639,0.0001858817,0.00008737576],"domain_scores_gemma":[0.9994253,0.0001588623,0.00009824312,0.0001137573,0.0001689599,0.00003489612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004685312,0.0002767252,0.01833716,0.000325602,0.0001351108,0.0003712153,0.0002327716,0.2913042,0.08190092,0.001565067,0.006904923,0.5981778],"study_design_scores_gemma":[0.000006678641,0.00004688749,0.003831735,0.00001878312,0.00001745781,0.000103591,0.0000466806,0.9781041,0.01570451,0.0007002187,0.001401459,0.00001791368],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2788638,0.0009079452,0.6967778,0.0002809218,0.0001215519,0.0003772601,0.00161365,0.01626369,0.004793295],"genre_scores_gemma":[0.6820145,0.0004541306,0.3076035,0.0001753954,0.00004320211,0.0001739283,0.0036948,0.0004941071,0.005346338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007217099,"threshold_uncertainty_score":0.01435018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01899568540644174,"score_gpt":0.2569140656494546,"score_spread":0.2379183802430128,"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."}}