SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.14865 · 2022

Accurate global machine learning force fields for molecules with hundreds of atoms

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2209.14865.json · badge: /api/ran/2209.14865.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
stefanch/sGDML community (classifier label)
classifier basis not recorded on the link
6 ran · 3 no recorded run
FunctionStatusWhere it lives
blink_str Ran
ran on a synthesized input
stefanch/sGDML/sgdml/utils/ui.py
code served (permissive licence) · get_code("2cfa5a93757e4895")
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 str. 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 sys

ENABLE_COLORED_OUTPUT = sys.stdout.isatty()

def blink_str(str):
    return '\x1b[5m' + str + '\x1b[0m' if ENABLE_COLORED_OUTPUT else str

ARGS = {
    'str': 'Hello World'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
share_array Ran
ran on a synthesized input
stefanch/sGDML/sgdml/predict.py
code served (permissive licence) · get_code("34dc51f900ba49a8")
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 tuple. 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 multiprocessing as mp
import numpy as np

# Create a small NumPy array of floats
arr_np = np.array([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0],
                   [9.0, 10.0, 11.0, 12.0]], dtype=float)

ARGS = {
    'arr_np': arr_np
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
share_array Ran
ran on a synthesized input
stefanch/sGDML/sgdml/utils/perm.py
code served (permissive licence) · get_code("a8698b7e1d029bf1")
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 tuple. 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 multiprocessing as mp
import numpy as np

# Create a small numpy array with distinct dimensions
arr_np = np.array([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

# Define typecode for float32
typecode = 'f'

ARGS = {
    'arr_np': arr_np,
    'typecode': typecode
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
train_dir_name Ran
ran on a synthesized input
stefanch/sGDML/sgdml/utils/io.py
code served (permissive licence) · get_code("685236f9f95cd7ac")
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 str. 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 numpy as np
import torch

# The function uses dataset as a dict with 'theory' and 'name' keys
# dataset['name'] needs to support .astype(str) which suggests it's a numpy array
# dataset['theory'] is converted to string and processed with regex

dataset = {
    'theory': 'B3LYP/6-31G*',
    'name': np.array(['ethanol'])
}

n_train = 100
use_sym = True
use_E = False
use_E_cstr = True

ARGS = {
    'dataset': dataset,
    'n_train': n_train,
    'use_sym': use_sym,
    'use_E': use_E,
    'use_E_cstr': use_E_cstr
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
z_str_to_z Ran
ran on a synthesized input
stefanch/sGDML/sgdml/utils/io.py
code served (permissive licence) · get_code("28fcc6ec2e16db2a")
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 ndarray, ndim 1, dtype family int, shape (4,) 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 numpy as np

_z_str_to_z_dict = {'H': 1, 'He': 2, 'Li': 3, 'Be': 4, 'B': 5, 'C': 6, 'N': 7, 'O': 8, 'F': 9, 'Ne': 10, 'Na': 11, 'Mg': 12, 'Al': 13, 'Si': 14, 'P': 15, 'S': 16, 'Cl': 17, 'Ar': 18, 'K': 19, 'Ca': 20, 'Sc': 21, 'Ti': 22, 'V': 23, 'Cr': 24, 'Mn': 25, 'Fe': 26, 'Co': 27, 'Ni': 28, 'Cu': 29, 'Zn': 30, 'Ga': 31, 'Ge': 32, 'As': 33, 'Se': 34, 'Br': 35, 'Kr': 36, 'Rb': 37, 'Sr': 38, 'Y': 39, 'Zr': 40, 'Nb': 41, 'Mo': 42, 'Tc': 43, 'Ru': 44, 'Rh': 45, 'Pd': 46, 'Ag': 47, 'Cd': 48, 'In': 49, 'Sn': 50, 'Sb': 51, 'Te': 52, 'I': 53, 'Xe': 54, 'Cs': 55, 'Ba': 56, 'La': 57, 'Ce': 58, 'Pr': 59, 'Nd': 60, 'Pm': 61, 'Sm': 62, 'Eu': 63, 'Gd': 64, 'Tb': 65, 'Dy': 66, 'Ho': 67, 'Er': 68, 'Tm': 69, 'Yb': 70, 'Lu': 71, 'Hf': 72, 'Ta': 73, 'W': 74, 'Re': 75, 'Os': 76, 'Ir': 77, 'Pt': 78, 'Au': 79, 'Hg': 80, 'Tl': 81, 'Pb': 82, 'Bi': 83, 'Po': 84, 'At': 85, 'Rn': 86, 'Fr': 87, 'Ra': 88, 'Ac': 89, 'Th': 90, 'Pa': 91, 'U': 92, 'Np': 93, 'Pu': 94, 'Am': 95, 'Cm': 96, 'Bk': 97, 'Cf': 98, 'Es': 99, 'Fm': 100, 'Md': 101, 'No': 102, 'Lr': 103, 'Rf': 104, 'Db': 105, 'Sg': 106, 'Bh': 107, 'Hs': 108, 'Mt': 109, 'Ds': 110, 'Rg': 111, 'Cn': 112, 'Uuq': 114, 'Uuh': 116}

def z_str_to_z(z_str):
    return np.array([_z_str_to_z_dict[x] for x in z_str])

ARGS = {
    'z_str': ['H', 'C', 'N', 'O']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (4,) — shape (4,) 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
z_to_z_str Ran
ran on a synthesized input
stefanch/sGDML/sgdml/utils/io.py
code served (permissive licence) · get_code("64712ad0eaaf05a4")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

# The function z_to_z_str takes a parameter 'z' which should be an iterable
# of atomic numbers (integers) and converts them to element symbol strings.
# Looking at the function body:
#   - z is iterated over with: [_z_to_z_str_dict[int(x)] for x in z]
#   - each element x is converted to int
#   - each int is used as a key to look up in _z_to_z_str_dict

# Create a valid z argument: a list/array of atomic numbers
z = [1, 6, 8, 2]  # H, C, O, He

ARGS = {
    'z': z
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
bipartite_match Not yet run
unverified (harvested, no recorded run)
stefanch/sGDML/sgdml/utils/perm.py
code served (permissive licence) · get_code("3f545f92ab893e68")
How it ran

no invocation recorded.

sync_perm_mat Not yet run
unverified (harvested, no recorded run)
stefanch/sGDML/sgdml/utils/perm.py
code served (permissive licence) · get_code("5208b6914556dcd9")
How it ran

no invocation recorded.

yes_or_no Not yet run
unverified (harvested, no recorded run)
stefanch/sGDML/sgdml/utils/ui.py
code served (permissive licence) · get_code("627ff9e87c4c8a82")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Global machine learning force fields (MLFFs), that have the capacity to capture collective many-atom interactions in molecular systems, currently only scale up to a few dozen atoms due a considerable growth of the model complexity with system size. For larger molecules, locality assumptions are typically introduced, with the consequence that non-local interactions are poorly or not at all described, even if those interactions are contained within the reference ab initio data. Here, we approach this challenge and develop an exact iterative parameter-free approach to train global symmetric gradient domain machine learning (sGDML) force fields for systems with up to several hundred atoms, without resorting to any localization of atomic interactions or other potentially uncontrolled approximations. This means that all atomic degrees of freedom remain fully correlated in the global sGDML FF, allowing the accurate description of complex molecules and materials that present phenomena with far-reaching characteristic correlation lengths. We assess the accuracy and efficiency of our MLFFs on a newly developed MD22 benchmark dataset containing molecules from 42 to 370 atoms. The robustness of our approach is demonstrated in nanosecond long path-integral molecular dynamics simulations for the supramolecular complexes in the MD22 dataset.

For agents

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

get_harvested_code_for_paper("2209.14865")
get_code_for_paper("2209.14865")
have("2209.14865")

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

curl https://syntology.ai/api/ran/2209.14865.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.14865.svg)](https://syntology.ai/paper/2209.14865)

Connect an agent — have() is free.