{"id":"W4311647946","doi":"10.1557/s43577-022-00440-0","title":"Beyond potentials: Integrated machine learning models for materials","year":2022,"lang":"en","type":"article","venue":"MRS Bulletin","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"HORIZON EUROPE European Research Council; École Polytechnique Fédérale de Lausanne; National Center of Competence in Research Materials’ Revolution: Computational Design and Discovery of Novel Materials; European Commission; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Closing (real estate); Realization (probability); Atomic units; Computer science; Statistical physics; Scale (ratio); Electronic structure; Sampling (signal processing); Physics; Quantum mechanics; Mathematics","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004206312,0.0003244316,0.0004829738,0.000165639,0.001347885,0.000377644,0.001029058,0.00007127093,0.05238647],"category_scores_gemma":[0.000488238,0.0003064717,0.0001044372,0.0002456113,0.0001457823,0.0001283237,0.0007087687,0.0003140151,0.0005660079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001384389,"about_ca_system_score_gemma":0.00008280235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007443724,"about_ca_topic_score_gemma":0.000006788307,"domain_scores_codex":[0.9961693,0.000982055,0.0006452046,0.0008048472,0.0006624078,0.000736128],"domain_scores_gemma":[0.9986882,0.0002370418,0.0003930039,0.0004346592,0.0001205323,0.0001265328],"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":[0.0002292346,0.0000713602,0.00002927902,0.00004166329,0.000006478958,0.00001175868,0.0003170205,0.126446,0.8610955,0.002784964,0.008656173,0.0003105738],"study_design_scores_gemma":[0.001752111,0.0008304573,0.00005588524,0.00003542084,0.0000610861,0.0001214414,0.0005506694,0.07500844,0.3769462,0.01060722,0.5329326,0.001098495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9250814,0.0003671423,0.05777434,0.005205373,0.004872743,0.001463621,0.001121946,0.001012193,0.003101229],"genre_scores_gemma":[0.9584569,0.00001002487,0.03164003,0.0009359379,0.0002314718,0.0006611932,0.0003019902,0.00009863944,0.007663826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5242764,"threshold_uncertainty_score":0.9999522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01714022399636814,"score_gpt":0.2406841777395913,"score_spread":0.2235439537432232,"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."}}