{"id":"W3197439341","doi":"10.1038/s41524-022-00767-x","title":"A deep learned nanowire segmentation model using synthetic data augmentation","year":2022,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Electron and X-Ray Spectroscopy Techniques","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Materials Research; Hessisches Ministerium für Wissenschaft und Kunst; National Research Council Canada; National Science Foundation; Canadian Institutes of Health Research; Western Economic Diversification Canada; Technische Universität Darmstadt; Canadian Light Source; Natural Sciences and Engineering Research Council of Canada; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; University of Saskatchewan","keywords":"Artificial intelligence; Segmentation; Computer science; Convolutional neural network; Pentoxide; Image segmentation; Pattern recognition (psychology); Computer vision; Feature (linguistics); Nanowire; Materials science; Vanadium; Nanotechnology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001056277,0.0001750492,0.0002219309,0.0001262703,0.0005716241,0.0002261207,0.0005215377,0.00003674024,0.003351605],"category_scores_gemma":[0.00003781845,0.0001916042,0.00002758924,0.0001609825,0.0000533811,0.000535334,0.0004216113,0.00007843159,0.00004989492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003035118,"about_ca_system_score_gemma":0.0001840595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007588427,"about_ca_topic_score_gemma":0.000004641955,"domain_scores_codex":[0.9977269,0.0003911174,0.0004317894,0.0005442397,0.0006169842,0.0002890365],"domain_scores_gemma":[0.9991662,0.00007729464,0.0002607245,0.0003666401,0.00007875287,0.00005036941],"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":[0.00007595345,0.00006616952,0.00000577177,0.00001601876,0.000007121394,0.000002512299,0.0001777984,0.2220472,0.7748178,0.002227102,0.0002961045,0.0002604968],"study_design_scores_gemma":[0.0003203965,0.00008869942,0.00002427397,0.000009980685,0.00002870122,0.00003074575,0.0001145133,0.4762734,0.497833,0.0250303,0.00004753743,0.0001983821],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7272347,0.00004828161,0.2710568,0.0002306485,0.0003622814,0.0004052202,0.0002921543,0.0002393063,0.0001305848],"genre_scores_gemma":[0.8774014,0.000004451417,0.1208402,0.0003585758,0.00006910689,0.00009801551,0.001125651,0.00003238278,0.00007032663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2769847,"threshold_uncertainty_score":0.9975595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05503411256117948,"score_gpt":0.3393624068284181,"score_spread":0.2843282942672387,"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."}}