SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.03789 · 2024

Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.03789.json · badge: /api/ran/2402.03789.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mdil-snu/sevennet canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
config_initialize Ran
ran, honoured the contract we drafted
mdil-snu/sevennet/sevenn/parse_input.py
code served (permissive licence) · get_code("5be11352a256938d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from typing import Any, Callable, Dict

torch.manual_seed(0)

# Test case 1: Simple key not in config, return default
ARGS_1 = {
    "key": "missing_key",
    "config": {"other_key": "value"},
    "default": 42,
    "conditions": {}
}

# Test case 2: Key in config, no condition, return user_input
ARGS_2 = {
    "key": "learning_rate",
    "config": {"learning_rate": 0.001},
    "default": 0.01,
    "conditions": {}
}

# Test case 3: Key with type condition (int)
ARGS_3 = {
    "key": "batch_size",
    "config": {"batch_size": "32"},
    "default": 16,
    "conditions": {"batch_size": int}
}

# Test case 4: Key with callable condition (lambda)
ARGS_4 = {
    "key": "threshold",
    "config": {"threshold": 0.5},
    "default": 0.1,
    "conditions": {"threshold": lambda x: isinstance(x, float) and 0.0 <= x <= 1.0}
}

# Test case 5: Nested dict with recursive config_initialize
ARGS_5 = {
    "key": "model_config",
    "config": {
        "model_config": {
            "hidden_dim": 128,
            "num_layers": 2
        }
    },
    "default": {
        "hidden_dim": 64,
        "num_layers": 1
    },
    "conditions": {
        "model_config": {
            "hidden_dim": int,
            "num_layers": int
        }
    }
}

# Use the simplest test case
ARGS = ARGS_1
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
copy_state_dict Ran
ran; our contract draft was wrong, not the code
mdil-snu/sevennet/sevenn/checkpoint.py
code served (permissive licence) · get_code("ad1feb9952020ba2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from typing import Any, Dict, List, Optional, Union
from torch import Tensor

torch.manual_seed(0)

# Create a complex nested state_dict with tensors, dicts, lists, and scalars
nested_state_dict = {
    "layer1": {
        "weight": torch.randn(4, 3),
        "bias": torch.randn(4),
    },
    "layer2": {
        "weight": torch.randn(5, 4),
        "bias": torch.randn(5),
        "nested_list": [
            torch.randn(2, 3),
            {"inner_weight": torch.randn(3, 2)},
        ],
    },
    "metadata": {
        "version": 1,
        "name": "test_model",
        "scalars": [1, 2.5, "string_value"],
    },
    "flat_list": [
        torch.randn(2, 4),
        torch.randn(3, 2),
        {"tensor": torch.randn(1, 5)},
    ],
}

ARGS = {
    "state_dict": nested_state_dict,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
error_record_condition Ran
ran, violated the contract we drafted
mdil-snu/sevennet/sevenn/_const.py
code served (permissive licence) · get_code("e0125c28e1884371")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

SUPPORTING_METRICS = ['RMSE', 'ComponentRMSE', 'MAE', 'Loss']
SUPPORTING_ERROR_TYPES = ['TotalEnergy', 'Energy', 'Force', 'Stress', 'Stress_GPa', 'TotalLoss', 'L2_modal', 'Modal_cos']

def error_record_condition(x):
    if type(x) is not list:
        return False
    for v in x:
        if type(v) is not list or len(v) != 2:
            return False
        if v[0] not in SUPPORTING_ERROR_TYPES:
            return False
        if v[0] == 'TotalLoss':
            continue
        if v[1] not in SUPPORTING_METRICS:
            return False
    return True

# Valid case: list of [error_type, metric] pairs
valid_x = [
    ['Energy', 'RMSE'],
    ['Force', 'MAE'],
    ['Stress', 'Loss'],
    ['TotalLoss'],
]

ARGS = {
    'x': valid_x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
config_initialize 1 other paper
1 later
2412.11569 (2024-12)
The dark side of the forces: assessing non-conservative force models for atomistic machine learning
copy_state_dict 1 other paper
1 later
2412.11569 (2024-12)
The dark side of the forces: assessing non-conservative force models for atomistic machine learning
error_record_condition 1 other paper
1 later
2412.11569 (2024-12)
The dark side of the forces: assessing non-conservative force models for atomistic machine learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Message-passing graph neural network interatomic potentials (GNN-IPs), particularly those with equivariant representations such as NequIP, are attracting significant attention due to their data efficiency and high accuracy. However, parallelizing GNN-IPs poses challenges because multiple message-passing layers complicate data communication within the spatial decomposition method, which is preferred by many molecular dynamics (MD) packages. In this article, we propose an efficient parallelization scheme compatible with GNN-IPs and develop a package, SevenNet (Scalable EquiVariance-Enabled Neural NETwork), based on the NequIP architecture. For MD simulations, SevenNet interfaces with the LAMMPS package. Through benchmark tests on a 32-GPU cluster with examples of SiO$_2$, SevenNet achieves over 80% parallel efficiency in weak-scaling scenarios and exhibits nearly ideal strong-scaling performance as long as GPUs are fully utilized. However, the strong-scaling performance significantly declines with suboptimal GPU utilization, particularly affecting parallel efficiency in cases involving lightweight models or simulations with small numbers of atoms. We also pre-train SevenNet with a vast dataset from the Materials Project (dubbed `SevenNet-0') and assess its performance on generating amorphous Si$_3$N$_4$ containing more than 100,000 atoms. By developing scalable GNN-IPs, this work aims to bridge the gap between advanced machine learning models and large-scale MD simulations, offering researchers a powerful tool to explore complex material systems with high accuracy and efficiency.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.03789")
get_code_for_paper("2402.03789")
have("2402.03789")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.03789.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.03789.svg)](https://syntology.ai/paper/2402.03789)

Connect an agent — have() is free.