We lifted 16 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| bytedance/deepsolid | canonical | 11 of 16 |
| Function | Status | Where it lives |
|---|---|---|
| enforce_pbc | Ran | bytedance/deepsolid/DeepSolid/network.py code served (permissive licence) · get_code("aca630458a5d37c0") |
| get_restore_path | Ran | bytedance/deepsolid/DeepSolid/checkpoint.py code served (permissive licence) · get_code("46014595574a2588") |
| init_solid_fermi_net_params | Ran | bytedance/deepsolid/DeepSolid/network.py code served (permissive licence) · get_code("564925745b0dbab8") |
| local_kinetic_energy | Ran | bytedance/deepsolid/DeepSolid/hamiltonian.py code served (permissive licence) · get_code("c8ab9823d4a04e02") |
| local_kinetic_energy_real_imag | Ran | bytedance/deepsolid/DeepSolid/hamiltonian.py code served (permissive licence) · get_code("9a2f5254b9004fff") |
| local_kinetic_energy_real_imag_dim_batch | Ran | bytedance/deepsolid/DeepSolid/hamiltonian.py code served (permissive licence) · get_code("85201fb3f5113d38") |
| make_different_rng_key_on_all_devices | Ran | bytedance/deepsolid/DeepSolid/constants.py code served (permissive licence) · get_code("044f4db035ee4c04") |
| np_enforce_pbc | Ran | bytedance/deepsolid/DeepSolid/distance.py code served (permissive licence) · get_code("e5219d5df83dd3c4") |
| resolve | Ran | bytedance/deepsolid/DeepSolid/base_config.py code served (permissive licence) · get_code("bf41787fb763d98d") |
| scaled_f | Ran | bytedance/deepsolid/DeepSolid/network.py code served (permissive licence) · get_code("bdb782a698bde89d") |
| wrap_if_pmap | Ran | bytedance/deepsolid/DeepSolid/constants.py code served (permissive licence) · get_code("7cca7b1b82215a77") |
| create_save_path | Not yet run | bytedance/deepsolid/DeepSolid/checkpoint.py code served (permissive licence) · get_code("75ce92be27f93323") |
| enforce_pbc | Not yet run | bytedance/deepsolid/DeepSolid/distance.py code served (permissive licence) · get_code("ae13781efdf47223") |
| find_last_checkpoint | Not yet run | bytedance/deepsolid/DeepSolid/checkpoint.py code served (permissive licence) · get_code("83cf365025dc973d") |
| replicate_all_local_devices | Not yet run | bytedance/deepsolid/DeepSolid/constants.py code served (permissive licence) · get_code("d169a08cfcf72de2") |
| select_big | Not yet run | bytedance/deepsolid/DeepSolid/ewaldsum.py code served (permissive licence) · get_code("b8423ac3becb0470") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Neural networks have been applied to tackle many-body electron correlations for small molecules and physical models in recent years. Here we propose a new architecture that extends molecular neural networks with the inclusion of periodic boundary conditions to enable ab initio calculation of real solids. The accuracy of our approach is demonstrated in four different types of systems, namely the one-dimensional periodic hydrogen chain, the two-dimensional graphene, the three-dimensional lithium hydride crystal, and the homogeneous electron gas, where the obtained results, e.g. total energies, dissociation curves, and cohesive energies, outperform many traditional ab initio methods and reach the level of the most accurate approaches. Moreover, electron densities of typical systems are also calculated to provide physical intuition of various solids. Our method of extending a molecular neural network to periodic systems can be easily integrated into other neural network structures, highlighting a promising future of ab initio solution of more complex solid systems using neural network ansatz, and more generally endorsing the application of machine learning in materials simulation and condensed matter physics.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.15472")
get_code_for_paper("2203.15472")
have("2203.15472")
Connect an agent — have() is free.