SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_25978 · AAAI · 2023

Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs

Yang Liu, Yu Rong, Wenbing Huang, Jiaqi Han, Rui Jiao

Open in the Atlas

Code that ran

6 of 6 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, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/aaai_25978.json · badge: /api/ran/aaai_25978.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
jiaor17/3D-EMGP canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
binarize Ran
ran, honoured the contract we drafted
jiaor17/3D-EMGP/script/finetune_md17.py
code served (permissive licence) · get_code("6d5f9e03fb5171ad")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create a small tensor with values between 0 and 1
x = torch.rand(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
get_edges Ran
ran, honoured the contract we drafted
jiaor17/3D-EMGP/mgp/layers/egnn_clean.py
code served (permissive licence) · get_code("c2f9c401f5379aac")
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 2, dtype family int; 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

torch.manual_seed(0)

def get_edges(n_nodes):
    rows, cols = ([], [])
    for i in range(n_nodes):
        for j in range(n_nodes):
            if i != j:
                rows.append(i)
                cols.append(j)
    edges = [rows, cols]
    return edges

ARGS = {
    "n_nodes": 5
}
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 list, ndim 2, dtype family int — 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
process_input Ran
ran; our contract draft was wrong, not the code
jiaor17/3D-EMGP/script/finetune_qm9.py
code served (permissive licence) · get_code("255d015f7e8d573c")
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) and returned Tensor, ndim 2, dtype family float, shape (4, 300) 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
from torch import nn

torch.manual_seed(0)

# Create a small tensor of atom types
# Values should be in range [0, max_atom_type)
atom_type = torch.tensor([0, 5, 3, 2], dtype=torch.long)

ARGS = {
    "atom_type": atom_type,
    "max_atom_type": 100,
    "charge_power": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 300) — shape (4, 300) 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
process_input Ran
ran; our contract draft was wrong, not the code
jiaor17/3D-EMGP/script/finetune_md17.py
code served (permissive licence) · get_code("654a4b9e4afe14f4")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 30) 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
from torch import nn

torch.manual_seed(0)

# Create a small atom_type tensor with values in range [0, max_atom_type)
# Shape: (2, 3) - batch of 2, with 3 atoms each
atom_type = torch.tensor([[0, 1, 2], [3, 4, 1]], dtype=torch.long)

ARGS = {
    "atom_type": atom_type,
    "max_atom_type": 10,
    "charge_power": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 30) — shape (2, 3, 30) 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
unsorted_segment_mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiaor17/3D-EMGP/mgp/layers/egnn_clean.py
code served (permissive licence) · get_code("bc66f19be57720e7")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create sample data tensor with shape (batch_size, feature_dim)
# Using distinct sizes: 2 for batch, 4 for features
data = torch.randn(2, 4)

# Create segment_ids tensor that maps each data point to a segment
# Values should be in range [0, num_segments)
segment_ids = torch.tensor([0, 1])

# Number of segments to aggregate into
num_segments = 2

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
jiaor17/3D-EMGP/mgp/layers/egnn_clean.py
pointer only (licence: MIT); the stored copy get_code serves, from ZhangGroup-MITChemistry/Schake_GNN, is pointer only (licence: NONE) · get_code("5fb62a78eb65d3d7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ZhangGroup-MITChemistry/Schake_GNN, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 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
unsorted_segment_mean 20 other papers
8 dated earlier, 10 later, 2 same year, order not determinable · 1 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
2110.14811 (2021-10)
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
and 17 more not named here
unsorted_segment_sum 19 other papers
8 dated earlier, 7 later, 4 same year, order not determinable · 2 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.02547 (2019-06)
Combining Generative and Discriminative Models for Hybrid Inference
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
and 16 more not named here
get_edges 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2207.08824 (2022-07)
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
2309.16342 (2023-09)
LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
and 2 more not named here
binarize 1 other paper
1 dated earlier
2207.08824 (2022-07)
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
process_input 1 other paper
1 dated earlier
2207.08824 (2022-07)
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
process_input 1 other paper
1 dated earlier
2207.08824 (2022-07)
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs

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

Pretraining molecular representation models without labels is fundamental to various applications. Conventional methods mainly process 2D molecular graphs and focus solely on 2D tasks, making their pretrained models incapable of characterizing 3D geometry and thus defective for downstream 3D tasks. In this work, we tackle 3D molecular pretraining in a complete and novel sense. In particular, we first propose to adopt an equivariant energy-based model as the backbone for pretraining, which enjoys the merits of fulfilling the symmetry of 3D space. Then we develop a node-level pretraining loss for force prediction, where we further exploit the Riemann-Gaussian distribution to ensure the loss to be E(3)invariant, enabling more robustness. Moreover, a graph-level noise scale prediction task is also leveraged to further promote the eventual performance. We evaluate our model pretrained from a large-scale 3D dataset GEOM-QM9 on two challenging 3D benchmarks: MD17 and QM9. Experimental results demonstrate the efficacy of our method against current state-of-the-art pretraining approaches, and verify the validity of our design for each proposed component. Code is available at https://github.com/jiaor17/3D-EMGP.

For agents

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

get_harvested_code_for_paper("aaai_25978")
get_code_for_paper("aaai_25978")
have("aaai_25978")

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

curl https://syntology.ai/api/ran/aaai_25978.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_25978.svg)](https://syntology.ai/paper/aaai_25978)

Connect an agent — have() is free.