{"id":"W4386960109","doi":"10.3389/fmats.2023.1233961","title":"An evolutionary variational autoencoder for perovskite discovery","year":2023,"lang":"en","type":"article","venue":"Frontiers in Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Autoencoder; Algorithm; Artificial intelligence; Computer science; Machine learning; Materials science; Deep learning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002715241,0.000245176,0.0004207867,0.0003503695,0.00027416,0.0005159591,0.0007376039,0.0001383785,0.0009626488],"category_scores_gemma":[0.0004367092,0.0002323506,0.00005388135,0.0004124035,0.0001738163,0.001376609,0.0001335118,0.00006765758,0.0003084926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000146749,"about_ca_system_score_gemma":0.0001293923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009691441,"about_ca_topic_score_gemma":0.000004450962,"domain_scores_codex":[0.997142,0.0003962036,0.0005979137,0.0007202317,0.0004580125,0.0006856432],"domain_scores_gemma":[0.9990062,0.0001306945,0.0002081583,0.0004799819,0.00007885119,0.00009611164],"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":[0.0001821438,0.00006666347,0.005379915,0.00008463187,0.000005249139,0.000008588778,0.0003659824,0.03463754,0.9307576,0.003823517,0.0245875,0.0001006623],"study_design_scores_gemma":[0.002732239,0.0005283317,0.3380583,0.0001951199,0.00005039402,0.0000285896,0.0006870556,0.3629543,0.1776997,0.1023709,0.01289566,0.001799376],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7933446,0.0000382375,0.1924542,0.0004714723,0.01166645,0.0006786998,0.0007347934,0.0004847337,0.0001267897],"genre_scores_gemma":[0.5041612,0.00002174937,0.4913551,0.0003225102,0.001033472,0.0006007117,0.0006469131,0.00008367575,0.001774712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7530578,"threshold_uncertainty_score":0.9999506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01058961792493477,"score_gpt":0.2743541203689939,"score_spread":0.2637645024440591,"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."}}