{"id":"W4401604229","doi":"10.1016/j.commatsci.2024.113255","title":"Optimizing SEM parameters for segmentation with AI – Part 1: Generating a training set","year":2024,"lang":"en","type":"article","venue":"Computational Materials Science","topic":"Electron and X-Ray Spectroscopy Techniques","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Object Research Systems (Canada)","funders":"","keywords":"Segmentation; Set (abstract data type); Training (meteorology); Training set; Artificial intelligence; Computer science; Pattern recognition (psychology); Materials science; Physics; Programming language","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001295452,0.0001788753,0.0001942739,0.0001732109,0.0004750307,0.001426066,0.0002769287,0.00003426264,0.0001205692],"category_scores_gemma":[0.00005035249,0.0001473123,0.00003082879,0.000388999,0.0003097611,0.0008793814,0.00004754288,0.00005867003,0.00002221532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000147766,"about_ca_system_score_gemma":0.0004952088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001157828,"about_ca_topic_score_gemma":0.000003369342,"domain_scores_codex":[0.9980969,0.00005125548,0.000320898,0.0005947238,0.0004712894,0.0004649427],"domain_scores_gemma":[0.9993676,0.0001649558,0.00009508844,0.0001236141,0.0001624697,0.00008628725],"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":[0.00002675486,0.000008613096,0.000002724871,0.00004864385,0.000004331058,0.000003687903,0.001075239,0.0283607,0.9618392,0.007835058,0.0002501751,0.0005448489],"study_design_scores_gemma":[0.0001511528,0.0002561559,0.0000126294,0.0001450707,0.00001372682,0.00003603699,0.0001658686,0.05669903,0.9374532,0.004682634,0.00016908,0.0002154685],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6426948,0.00005209454,0.3555858,0.0003330112,0.0005355972,0.000360793,0.00006110121,0.0003263927,0.00005030911],"genre_scores_gemma":[0.6194111,0.000002046129,0.3798793,0.0003623812,0.0001160591,0.0001451676,0.00004218152,0.00001709803,0.00002473198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02833834,"threshold_uncertainty_score":0.9996105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03971351801274419,"score_gpt":0.3293942931680933,"score_spread":0.2896807751553491,"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."}}