{"id":"W4283317747","doi":"10.1021/acsaem.2c00493","title":"Automatically Capturing Key Features for Predicting Superionic Conductivity of Solid-State Electrolytes Using a Neural Network","year":2022,"lang":"en","type":"article","venue":"ACS Applied Energy Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Toronto","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canada Foundation for Innovation","keywords":"Computer science; Artificial neural network; Artificial intelligence; Feature (linguistics); Process (computing); Machine learning; Property (philosophy); Intuition; Feature selection; Obstacle","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002565839,0.0003790949,0.0008099056,0.0001125754,0.000931236,0.0002404055,0.0008382971,0.00008765092,0.0007383524],"category_scores_gemma":[0.0001786965,0.0003664731,0.00007648109,0.0002859811,0.0002284306,0.0002333679,0.0007620774,0.0001501428,0.000003150836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001408095,"about_ca_system_score_gemma":0.0001720812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006682504,"about_ca_topic_score_gemma":0.00002939207,"domain_scores_codex":[0.9962845,0.0004552774,0.000903849,0.000730616,0.0006200967,0.001005633],"domain_scores_gemma":[0.9982598,0.0003509151,0.0006798121,0.0005155682,0.00008789111,0.0001060599],"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":[0.0001938675,0.00003130151,0.00003184616,0.00007131579,0.00001399309,0.000002217661,0.0003071857,0.3373325,0.6579948,0.003902518,0.00006495147,0.00005348405],"study_design_scores_gemma":[0.0005096877,0.0001748003,0.0003500865,0.00002262762,0.00004618975,0.0000590805,0.0000930997,0.01226678,0.9817176,0.00421733,0.0001552677,0.0003874199],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952974,0.00007090602,0.002072887,0.00006917609,0.001397472,0.0004571031,0.000275191,0.0002836866,0.00007614326],"genre_scores_gemma":[0.9878479,0.000003804313,0.01093993,0.0001948588,0.000405736,0.0004031183,0.00004458868,0.00007961991,0.00008050878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3250657,"threshold_uncertainty_score":0.9998787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01242793424242447,"score_gpt":0.2539140114769148,"score_spread":0.2414860772344903,"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."}}