{"id":"W4391786243","doi":"10.1063/5.0181037","title":"GradDFT. A software library for machine learning enhanced density functional theory","year":2024,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Xanadu Quantum Technologies (Canada)","funders":"Office of Science; National Energy Research Scientific Computing Center; U.S. Department of Energy","keywords":"Density functional theory; Computer science; Scalability; Differentiable function; Artificial intelligence; Machine learning; Software; Artificial neural network; Benchmarking; Parametrization (atmospheric modeling); Theoretical computer science; Computational chemistry; Chemistry; Quantum mechanics; Mathematics; Physics; Programming language; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.001484414,0.0001471653,0.0002331307,0.0000284689,0.000145766,0.0001745677,0.0004837848,0.00004867382,0.0004523391],"category_scores_gemma":[0.0005928957,0.00008897591,0.0001495874,0.0001709841,0.0002032657,0.0004978032,0.0001445589,0.0004383695,0.00005969159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003102613,"about_ca_system_score_gemma":0.0001174456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001381879,"about_ca_topic_score_gemma":4.971275e-8,"domain_scores_codex":[0.9986396,0.0002301595,0.0003389833,0.0001605417,0.0003968265,0.0002338836],"domain_scores_gemma":[0.9979386,0.001506707,0.00022887,0.0001538962,0.00009408246,0.00007780788],"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":[0.0003128022,0.0000267547,0.00002180092,0.00007266356,0.00001474434,0.000002851893,0.0003103054,0.002403875,0.9908924,0.002490062,0.001555183,0.001896578],"study_design_scores_gemma":[0.0001722798,0.00008687296,0.00002999811,0.00009095928,0.00005693734,0.00006430725,0.00001795281,0.003782703,0.8869499,0.1073858,0.001247516,0.0001148414],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7074395,0.0003466862,0.2905531,0.0004637649,0.0008789761,0.00008643606,0.00001583265,0.0001252162,0.00009046886],"genre_scores_gemma":[0.9881827,0.00001616075,0.009892155,0.0002303878,0.001296609,0.000003479265,0.0000084667,0.00003392794,0.0003360686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2807432,"threshold_uncertainty_score":0.4952796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01203709043409784,"score_gpt":0.2405277956290867,"score_spread":0.2284907051949889,"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."}}