{"id":"W4362696576","doi":"10.36227/techrxiv.22486372.v1","title":"Artificial intelligence to detect buried objects","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Sliding window protocol; Pattern recognition (psychology); Segmentation; Support vector machine; Artificial neural network; Computer vision; Radar; Process (computing); Window (computing)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001021328,0.00017027,0.0001949703,0.0000751925,0.00002972128,0.00005498164,0.0002627676,0.0001283066,0.00006168505],"category_scores_gemma":[0.00006845656,0.0001685513,0.00008533714,0.0002586395,0.00001145596,0.000009753227,0.0002769471,0.0003289226,0.002252318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002859144,"about_ca_system_score_gemma":0.0000134861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007010331,"about_ca_topic_score_gemma":0.00004345978,"domain_scores_codex":[0.9991673,0.00001295787,0.0002206255,0.0002830808,0.000106213,0.0002098374],"domain_scores_gemma":[0.9992862,0.0001180821,0.00001384707,0.0004413544,0.00002798367,0.0001125571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003607509,0.00001882983,0.00000117818,0.0002189818,0.00006767271,0.000004433097,0.0002858555,0.2811463,0.02813552,0.02432796,0.001738796,0.6640508],"study_design_scores_gemma":[0.000004237458,0.00001835367,0.0004031844,0.00005846591,0.00002199531,2.92713e-7,0.00006784617,0.0412779,0.1529314,0.8031711,0.001571904,0.0004732986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0150821,0.00001292958,0.9775732,0.0004001845,0.0007211151,0.0004304371,0.000020708,0.001442179,0.004317113],"genre_scores_gemma":[0.7723677,0.00001545679,0.225883,0.00005884959,0.0006330322,0.0005183748,0.00001238595,0.00007063192,0.000440644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7788431,"threshold_uncertainty_score":0.9985245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08939993669612924,"score_gpt":0.3328547212598194,"score_spread":0.2434547845636902,"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."}}