{"id":"W4286461694","doi":"10.1017/s1431927622011710","title":"Comparison Between Deep Learning and Iterative Bayesian Statistics Deconvolution Methods in Energy Electron Loss Spectroscopy","year":2022,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Light Source (Canada); McMaster University","funders":"","keywords":"Deconvolution; Bayesian probability; Spectroscopy; Energy (signal processing); Electron; Bayesian statistics; Statistical physics; Statistics; Computer science; Computational physics; Physics; Bayesian inference; Materials science; Artificial intelligence; Algorithm; Mathematics; Nuclear physics; Astronomy","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":[0.0009622472,0.0001979953,0.0004402675,0.0004683172,0.0004570925,0.0002491823,0.0002679041,0.00006307844,0.00003601011],"category_scores_gemma":[0.00002376192,0.0002245,0.00004913406,0.0007675253,0.00006855423,0.0002409892,0.0003229411,0.0004355952,8.881352e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001662162,"about_ca_system_score_gemma":0.00004847086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002352946,"about_ca_topic_score_gemma":0.0002210829,"domain_scores_codex":[0.9974732,0.001084808,0.0004270068,0.0005458355,0.0001452835,0.000323911],"domain_scores_gemma":[0.999227,0.0002303161,0.000218631,0.0002000501,0.00004573934,0.00007829887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007254876,0.0002253708,0.1999291,0.00003741723,0.000317602,0.00002220958,0.01259499,0.001096209,0.6878675,0.02582913,0.0005540183,0.07145399],"study_design_scores_gemma":[0.0007494997,0.0006388661,0.007576247,0.00001501868,0.0001568702,0.00003158201,0.0006003061,0.2073074,0.7517011,0.0105636,0.01995903,0.0007004109],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04771284,0.002228823,0.9496,0.000184581,0.00002267086,0.00008547251,0.00001178728,0.00007718823,0.00007657419],"genre_scores_gemma":[0.5368231,0.0002262055,0.4625725,0.0001436552,0.00001149797,0.00002446018,0.00005571272,0.00001047654,0.0001323449],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4891103,"threshold_uncertainty_score":0.9154844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01172668865008721,"score_gpt":0.3542914914673325,"score_spread":0.3425648028172453,"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."}}