Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 375

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Pushing the frontiers of density functionals by solving the fractional electron problem

Open access
Kirkpatrick, James, McMorrow, Brendan, Turban, David H. P., Gaunt, Alexander L., Spencer, James S., Matthews, Alexander G. D. G., Obika, Annette, Thiry, Louis, Fortunato, Meire, Pfau, David, Castellanos, Lara Román, Petersen, Stig, Nelson, Alexander W. R., Kohli, Pushmeet, Mori-Sánchez, Paula, Hassabis, Demis, Cohen, Aron J.·2021·Science
DOI 10.1126/science.abj6511
Open this paper in CoChat — free account

Abstract

Improving DFT with deep learning: In the past 30 years, density functional theory (DFT) has emerged as the most widely used electronic structure method to predict the properties of various systems in chemistry, biology, and materials science. Despite a long history of successes, state-of-the-art DFT functionals have crucial limitations. In particular, significant systematic errors are observed for charge densities involving mobile charges and spins. Kirkpatrick et al . developed a framework to train a deep neural network on accurate chemical data and fractional electron constraints (see the Perspective by Perdew). The resulting functional outperforms traditional functionals on thorough benchmarks for main-group atoms and molecules. The present work offers a solution to a long-standing critical problem in DFT and demonstrates the success of combining DFT with the modern machine-learning methodology. —YS

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1126/science.abj6511

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 6 references

Research works printed but not linked: 66

  1. 10.1103/PhysRev.136.B864 · DOI · Paper page
  2. 10.1038/514550a · DOI
  3. 10.1126/science.1158722 · DOI · Paper page
  4. 10.1103/PhysRevLett.115.036402 · DOI
  5. 10.1093/nsr/nwx111 · DOI
  6. 10.1073/pnas.1807095115 · DOI
  7. 10.1021/acs.chemrev.0c01111 · DOI · Paper page
  8. 10.1103/PhysRevLett.108.253002 · DOI
  9. 10.1002/qua.25040 · DOI
  10. 10.1038/s41524-020-0310-0 · DOI
  11. A. V. Sinitskiy V. S. Pande Physical machine learning outperforms “human learning” in quantum chemistry. arXiv:1908.00971 [physics.chem-ph] (2019). · arXiv
  12. 10.1103/PhysRevA.100.022512 · DOI
  13. 10.1021/acs.jctc.0c00872 · DOI
  14. 10.1038/s41467-020-17265-7 · DOI
  15. 10.1103/PhysRevLett.49.1691 · DOI
  16. 10.1063/1.2987202 · DOI · Paper page
  17. 10.1002/wcms.1340 · DOI · Paper page
  18. 10.1002/jcc.24854 · DOI
  19. 10.1016/j.cplett.2011.05.007 · DOI
  20. 10.1080/00268970802708959 · DOI
  21. 10.1021/acs.jpca.7b10958 · DOI
  22. L. Li S. Hoyer R. Pederson R. Sun E. D. Cubuk P. Riley K. Burke Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics. arXiv:2009.08551 [physics.comp-ph] (2020). · DOI
  23. 10.1007/s00214-007-0310-x · DOI · Paper page
  24. 10.1063/1.2834918 · DOI
  25. 10.1021/cr200107z · DOI
  26. 10.1063/1.1858371 · DOI
  27. A. D. Becke Density Functionals E. R. Johnson Ed. (Springer 2014) vol. 365 pp. 175–186. · DOI
  28. 10.1021/cr900228f · DOI · Paper page
  29. 10.1103/PhysRevX.7.031059 · DOI
  30. 10.1080/00268976.2017.1350291 · DOI
  31. 10.1021/jo502041f · DOI
  32. 10.1021/ct900489g · DOI · Paper page
  33. 10.1038/s41597-019-0121-7 · DOI
  34. 10.1073/pnas.1910411116 · DOI
  35. 10.1103/PhysRevLett.77.3865 · DOI · Paper page
  36. 10.1021/jp108605g · DOI
  37. 10.1039/C7CP04913G · DOI · Paper page
  38. 10.1103/PhysRevLett.80.890 · DOI
  39. 10.1021/jp050536c · DOI
  40. 10.1039/c1cp22592h · DOI · Paper page
  41. 10.1039/c3cp54374a · DOI · Paper page
  42. 10.1063/1.4790598 · DOI
  43. 10.1103/PhysRevA.78.052513 · DOI
  44. 10.1021/acs.jctc.0c00498 · DOI
  45. 10.1021/jp904369h · DOI
  46. 10.1071/CH17588 · DOI
  47. 10.1063/1.481336 · DOI · Paper page
  48. 10.1007/s00214-005-0028-6 · DOI · Paper page
  49. 10.1063/1.1535422 · DOI · Paper page
  50. 10.1021/ct501137x · DOI
  51. 10.1039/C8CP05554H · DOI
  52. 10.1007/s10107-012-0584-1 · DOI · Paper page
  53. 10.1063/1.1688752 · DOI · Paper page
  54. 10.1021/ct800511q · DOI
  55. 10.1126/science.aah5975 · DOI
  56. 10.1021/acs.jctc.7b01252 · DOI · Paper page
  57. 10.1063/5.0005039 · DOI
  58. 10.1063/1.3700802 · DOI
  59. 10.1021/jo201567d · DOI
  60. 10.1038/s41597-020-0460-4 · DOI
  61. 10.1103/PhysRevResearch.2.033429 · DOI
  62. J. S. Spencer D. Pfau A. Botev W. Foulkes Better faster fermionic neural networks. arXiv:2011.07125 [physics.comp-ph] (2020). · arXiv
  63. J. Martens R. Grosse Optimizing neural networks with kronecker-factored approximate curvature in ICML Proceedings (ICML 2015) pp. 2408–2417.
  64. 10.1063/1.457480 · DOI · Paper page
  65. 10.1103/PhysRevLett.91.146401 · DOI
  66. 10.1063/1.1626543 · DOI

Cited by

Metadata

Authors
Kirkpatrick, J., McMorrow, B., Turban, D. H. P., Gaunt, A. L., Spencer, J. S., Matthews, A. G. D. G., Obika, A., Thiry, L., Fortunato, M., Pfau, D., Castellanos, L. R., Petersen, S., Nelson, A. W. R., Kohli, P., Mori-Sánchez, P., Hassabis, D., & Cohen, A. J.
Venue
Science
Publisher
American Association for the Advancement of Science (AAAS)
Published
2021-12-10
Volume
374
Issue
6573
Pages
1385-1389
ISSN
  • 0036-8075 (ISSN-L)
  • 1095-9203
DOI
10.1126/science.abj6511
OpenAlex
W4200371263
Cited by
375
References
6
FWCI
27.18
Type
journal article
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.