{"id":"W4414807644","doi":"10.1101/2025.09.29.679411","title":"Correcting Non-Uniform Milling in FIB-SEM Images with Unsupervised Cross-Plane Image-to-Image Translation","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"LGL (Canada)","funders":"National Institutes of Health; National Science Foundation","keywords":"Translation (biology); Image (mathematics); Image translation; Image quality; Quality (philosophy); Unsupervised learning; Pattern recognition (psychology); Ground truth","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003047105,0.0005244795,0.0004214137,0.0002265856,0.0001818832,0.000184709,0.0004977899,0.0004651406,0.000009883971],"category_scores_gemma":[0.00005260515,0.0005683551,0.0001039051,0.0004962784,0.0001072771,0.00002180779,0.0002337983,0.0006191807,0.000008109028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338035,"about_ca_system_score_gemma":0.0004039972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006815639,"about_ca_topic_score_gemma":0.00002492153,"domain_scores_codex":[0.9975947,0.0000415102,0.000493368,0.001117652,0.0001662709,0.0005865055],"domain_scores_gemma":[0.9982571,0.00002517752,0.0002198005,0.0009747545,0.0003785988,0.0001445449],"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":[0.0001022487,0.00006957447,0.00224324,0.0002097378,0.00003794505,0.00000778251,0.000009094276,0.0007714754,0.9963924,0.000008328589,0.0001200247,0.00002812964],"study_design_scores_gemma":[0.0005199913,0.0001335518,0.003788162,0.0003825464,0.00003660138,7.957645e-8,0.000005111651,0.0003964241,0.9918225,0.000002012253,0.002266941,0.0006460877],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6926385,0.0004406066,0.3048103,0.0001286576,0.0001204765,0.00122464,0.0004269188,0.0001545896,0.00005535171],"genre_scores_gemma":[0.7921906,0.0003086201,0.2065421,0.0001831772,0.0001684375,0.0004683998,0.00001489582,0.00009435219,0.00002947384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09955206,"threshold_uncertainty_score":0.9996768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007157940102278432,"score_gpt":0.2748731882087694,"score_spread":0.2677152481064909,"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."}}