{"id":"W4388044873","doi":"10.21203/rs.3.rs-3352833/v1","title":"Autocharacterization: Automated and Scalable Semiconductor Property Estimation from High-throughput Experiments using Computer Vision","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"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; University of Toronto; Office of Energy Efficiency and Renewable Energy; U.S. Department of Energy; National Science Foundation","keywords":"Bottleneck; Scalability; Throughput; Computer science; Workflow; Nanomanufacturing; Leverage (statistics); Parallelizable manifold; Algorithm; Artificial intelligence; Materials science; Nanotechnology; Embedded 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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002751038,0.0004349367,0.0006005017,0.0003818746,0.0007539208,0.002137791,0.0008898385,0.0004363436,0.001061797],"category_scores_gemma":[0.0004991132,0.0003326257,0.00005463112,0.0004846969,0.0004694872,0.0007251379,0.004102823,0.0007500825,0.00075162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004255928,"about_ca_system_score_gemma":0.0004305309,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007136552,"about_ca_topic_score_gemma":0.0000111756,"domain_scores_codex":[0.9934965,0.001498903,0.0006967345,0.001686093,0.001779985,0.0008418306],"domain_scores_gemma":[0.9974761,0.000313974,0.0003528128,0.0010407,0.0005680795,0.0002483232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005326728,0.00007673437,0.0004976821,0.0005696077,0.00001232949,0.00003272526,0.0008808728,0.04687143,0.949102,0.00003066467,0.001454534,0.0004181096],"study_design_scores_gemma":[0.0003074141,0.0001572722,0.01249867,0.001753413,0.00001129929,0.000006860394,0.00004780988,0.9165033,0.06740461,0.0007603327,0.0001398888,0.000409149],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822713,0.00007911807,0.01126008,0.0005914675,0.002383895,0.001467694,0.0003730399,0.001555126,0.00001825295],"genre_scores_gemma":[0.8459653,0.00004484503,0.1513372,0.00005452878,0.0007498313,0.0002007384,0.001012535,0.0001353385,0.0004997018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8816974,"threshold_uncertainty_score":0.9999126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1122236526028077,"score_gpt":0.4309323498243941,"score_spread":0.3187086972215864,"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."}}