SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1712.06113 · 2017

SchNet - a deep learning architecture for molecules and materials

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 2 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/1712.06113.json · badge: /api/ran/1712.06113.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
peterbjorgensen/msgnet reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
float_or_string Ran
ran, honoured the contract we drafted
peterbjorgensen/msgnet/src/scripts/runner.py
code served (permissive licence) · get_code("f6861553018d2738")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float, 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.

ARGS = {
    "string": "3.14"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 float, 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
get_arguments Ran
ran; our contract draft was wrong, not the code
peterbjorgensen/msgnet/src/scripts/runner.py
code served (permissive licence) · get_code("c3c3392a3d0f7172")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Namespace. 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 argparse

def list_of_lists(string):
    """list_of_list
    Parse a string of the form "1,2,3 4,3,2 ..."

    :param string:
    """
    if string:
        return [float(x) for x in string.strip().split(',')]
    else:
        return string

def float_or_string(string):
    try:
        return float(string)
    except ValueError:
        return string

def get_arguments(arg_list=None):
    parser = argparse.ArgumentParser(description='Train graph convolution network', fromfile_prefix_chars='@')
    parser.add_argument('--load_model', type=str, default=None)
    parser.add_argument('--fold', type=int, default=-1)
    parser.add_argument('--cutoff', type=float_or_string, nargs='+', default=['voronoi'], help='Cutoff method (voronoi, const or coval) followed by float for const and coval')
    parser.add_argument('--edge_idx', nargs='*', default=[], type=int, help='Space separated list of edge feature indices to use')
    parser.add_argument('--dataset', type=str, default='oqmd')
    parser.add_argument('--edge_expand', nargs='*', type=list_of_lists, default=None, help='Space separated list of comma separated triplets start,step,stop for edge feature expansion')
    parser.add_argument('--msg_share_weights', action='store_true')
    parser.add_argument('--num_passes', type=int, default=3)
    parser.add_argument('--node_embedding_size', type=int, default=256)
    parser.add_argument('--update_edges', action='store_true')
    parser.add_argument('--avg_msg', action='store_true', help='Average messages instead of sum')
    parser.add_argument('--readout', type=str, default='set2set')
    parser.add_argument('--target', type=str, default=None)
    parser.add_argument('--learning_rate', type=float, default=0.001)
    return parser.parse_args(arg_list)

ARGS = {
    'arg_list': [
        '--load_model', 'model.pt',
        '--fold', '2',
        '--cutoff', 'const', '5.0',
        '--edge_idx', '0', '1', '2',
        '--dataset', 'test_dataset',
        '--edge_expand', '0.0,0.5,5.0', '1.0,0.2,3.0',
        '--msg_share_weights',
        '--num_passes', '5',
        '--node_embedding_size', '128',
        '--update_edges',
        '--avg_msg',
        '--readout', 'mean',
        '--target', 'energy',
        '--learning_rate', '0.0005'
    ]
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
list_of_lists Ran
ran, honoured the contract we drafted
peterbjorgensen/msgnet/src/scripts/runner.py
code served (permissive licence) · get_code("61dc9fc0e2272217")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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.

ARGS = {
    "string": "1.5,2.3,4.7"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 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
species_count_filter Ran
ran, violated the contract we drafted
peterbjorgensen/msgnet/src/scripts/predict_with_model.py
code served (permissive licence) · get_code("6664fee3d8969be5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 numpy as np

class MockAtoms:
    def __init__(self, atomic_numbers):
        self.atomic_numbers = atomic_numbers
    
    def get_atomic_numbers(self):
        return np.array(self.atomic_numbers)

class MockX:
    def __init__(self, atomic_numbers):
        self.atoms = MockAtoms(atomic_numbers)

x = MockX([1, 1, 6, 8, 8])
count = 3

ARGS = {
    'x': x,
    'count': count
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 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
float_or_string 1 other paper
1 later
1806.03146 (2018-06)
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
get_arguments 1 other paper
1 later
1806.03146 (2018-06)
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
list_of_lists 1 other paper
1 later
1806.03146 (2018-06)
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
species_count_filter 1 other paper
1 later
1806.03146 (2018-06)
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials

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

Deep learning has led to a paradigm shift in artificial intelligence, including web, text and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning in general and deep learning in particular is ideally suited for representing quantum-mechanical interactions, enabling to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for \emph{molecules and materials} where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study of the quantum-mechanical properties of C$_{20}$-fullerene that would have been infeasible with regular ab initio molecular dynamics.

For agents

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

get_harvested_code_for_paper("1712.06113")
get_code_for_paper("1712.06113")
have("1712.06113")

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

curl https://syntology.ai/api/ran/1712.06113.json

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

[![Syntology run record](https://syntology.ai/api/ran/1712.06113.svg)](https://syntology.ai/paper/1712.06113)

Connect an agent — have() is free.