{"id":"W4388361857","doi":"10.1016/j.commatsci.2023.112580","title":"Machine learning models for the discovery of direct band gap materials for light emission and photovoltaics","year":2023,"lang":"en","type":"article","venue":"Computational Materials Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; University of Toronto; Canada Foundation for Innovation; Ontario Research Foundation","keywords":"Band gap; Photovoltaics; Direct and indirect band gaps; Computer science; Wide-bandgap semiconductor; Materials science; Photovoltaic system; Computational physics; Optoelectronics; Physics; Engineering; Electrical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.007697758,0.0002781404,0.000484026,0.0002357633,0.001274377,0.0009603188,0.0009144766,0.00007084914,0.0001014694],"category_scores_gemma":[0.002030621,0.0001924771,0.00005777155,0.0005928744,0.000862779,0.001026973,0.0003929817,0.00005679318,0.00001639855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000600544,"about_ca_system_score_gemma":0.0002836713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009651831,"about_ca_topic_score_gemma":0.000002253877,"domain_scores_codex":[0.9967592,0.0001808188,0.0007171651,0.0007907285,0.0009384478,0.0006136663],"domain_scores_gemma":[0.9968376,0.001686587,0.000523999,0.0003196938,0.0005269033,0.0001052418],"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":[0.000155918,0.00001797836,0.00003817401,0.0001984107,0.000004035504,5.745511e-7,0.0003852908,0.08404274,0.9105067,0.00437956,0.0001997965,0.00007077298],"study_design_scores_gemma":[0.0004188753,0.000147211,0.0005727976,0.00008856706,0.00001750745,0.000009324303,0.00006966444,0.1434361,0.8346152,0.0200003,0.0003981531,0.0002263344],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624055,0.0001190857,0.03273099,0.000571613,0.001968386,0.001193666,0.0007020748,0.0001852444,0.0001234448],"genre_scores_gemma":[0.9912781,0.00004549514,0.007700658,0.00008095949,0.0001846761,0.0002400432,0.00006708773,0.00003607614,0.0003668835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07589154,"threshold_uncertainty_score":0.9801604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03530613113269843,"score_gpt":0.2954086929149833,"score_spread":0.2601025617822849,"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."}}