{"id":"W4399513380","doi":"10.1038/s41467-024-48768-2","title":"Using scalable computer vision to automate high-throughput semiconductor characterization","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Materials Research; Office of Energy Efficiency; Materials Research Science and Engineering Center, Harvard University; Finnish Center for Artificial Intelligence; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Simons Foundation; University of Toronto; Office of Energy Efficiency and Renewable Energy; U.S. Department of Energy; National Science Foundation","keywords":"Throughput; Computer science; Scalability; Characterization (materials science); Computer architecture; Nanotechnology; Materials science; Database; Operating system","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":[],"consensus_categories":[],"category_scores_codex":[0.00020281,0.0001397244,0.0001546566,0.0002848677,0.0001905503,0.0002430012,0.0003300262,0.0002993896,0.00002675001],"category_scores_gemma":[0.00002140046,0.0001359782,0.00004908476,0.0009242241,0.00001146673,0.0002769113,0.0001704911,0.000426149,0.0003460363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001937796,"about_ca_system_score_gemma":0.00002476669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003054287,"about_ca_topic_score_gemma":0.00002009474,"domain_scores_codex":[0.9991627,0.00006312293,0.0002600376,0.0001936318,0.0001482852,0.000172192],"domain_scores_gemma":[0.9988678,0.00007169633,0.00001945169,0.0008503377,0.00009381004,0.00009697305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007898782,0.0000277749,0.00002800663,0.00007021301,0.00006144773,0.000002794925,0.0005575517,0.01486258,0.9253908,0.003148033,0.02147398,0.03436889],"study_design_scores_gemma":[0.0001067339,0.00005578248,0.001012139,0.0003903686,0.00002211944,0.00002244194,0.00001441123,0.4488734,0.01151444,0.00002489677,0.537693,0.0002702619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8470657,0.001072222,0.1373321,0.001612393,0.008446635,0.00098905,0.0001489182,0.002538542,0.0007944371],"genre_scores_gemma":[0.9834249,0.00003152648,0.01557275,0.0002233443,0.0004600137,0.00002901512,0.0001047197,0.00004825043,0.0001054651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9138764,"threshold_uncertainty_score":0.5545031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.031511524377865,"score_gpt":0.3140093047158236,"score_spread":0.2824977803379586,"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."}}