{"id":"W4206678087","doi":"10.1038/s41524-021-00685-4","title":"Machine learned interatomic potentials using random features","year":2022,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Compute Canada","keywords":"Density functional theory; Statistical physics; Interatomic potential; Computer science; Energy (signal processing); Molecular dynamics; Kernel (algebra); Physics; Mathematics; Quantum mechanics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002645702,0.000316792,0.0005427013,0.0002323895,0.00110726,0.0006298239,0.0008507167,0.00005719042,0.0292385],"category_scores_gemma":[0.0002402346,0.0003061292,0.00009413814,0.0002788009,0.000163426,0.0003171465,0.0008250407,0.0001932864,0.0003480357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001949931,"about_ca_system_score_gemma":0.0001833088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004053446,"about_ca_topic_score_gemma":0.000002547403,"domain_scores_codex":[0.9955279,0.00148059,0.0007565685,0.0007059323,0.001018162,0.0005108733],"domain_scores_gemma":[0.9986398,0.0002788467,0.0004991835,0.0003394526,0.0001285754,0.0001141776],"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":[0.0002770262,0.0000466633,0.00003761661,0.00002148326,0.000007900913,0.00001783306,0.0001638099,0.3586103,0.6387946,0.001548029,0.0004001876,0.00007456073],"study_design_scores_gemma":[0.007168018,0.0005181972,0.004795745,0.0001207033,0.0001179396,0.001746762,0.0003123404,0.1416461,0.7776336,0.05918572,0.004807568,0.001947298],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975427,0.0001172616,0.01893554,0.000531613,0.003421119,0.000468379,0.0005088068,0.0002869416,0.000303325],"genre_scores_gemma":[0.9746668,0.000001732504,0.02363248,0.0007172014,0.0002990867,0.00007804742,0.0002081491,0.0000521689,0.0003443621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2169642,"threshold_uncertainty_score":0.9999391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01686798247139903,"score_gpt":0.2870762360671166,"score_spread":0.2702082535957176,"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."}}