SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.08264 · 2020

Molecule Attention Transformer

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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, 2 violated it and 1 has no contract verdict; 3 failures of our instrument; 2 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/2002.08264.json · badge: /api/ran/2002.08264.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
gmum/MAT canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
ardigen/MAT community (classifier label)
classifier basis: plan_row
2 ran · 0 no recorded run
lucidrains/molecule-attention-transformer reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
clones Ran
ran; our contract draft was wrong, not the code
gmum/MAT/src/transformer.py
code served (permissive licence) · get_code("a22016a532513520")
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 ModuleList. 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
import copy
import math

torch.manual_seed(0)

# The clones function takes a module and N, and produces N identical deep copies
# We need to provide:
# 1. module: an nn.Module instance
# 2. N: an integer for the number of copies

# Create a simple nn.Module for testing
simple_module = nn.Linear(4, 3)

# Number of clones to create
N = 5

ARGS = {
    "module": simple_module,
    "N": N
}
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 ModuleList — a ModuleList output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModuleList output the recorded ndim 1 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
default Ran
ran, violated the contract we drafted
lucidrains/molecule-attention-transformer/molecule_attention_transformer/molecule_attention_transformer.py
code served (permissive licence) · get_code("3b2866ad3b081f76")
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 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 torch
import numpy as np

def exists(val):
    return val is not None

def default(val, d):
    return d if not exists(val) else val

# Test case 1: val is None, should return d
val_1 = None
d_1 = "default_value"

# Test case 2: val is not None, should return val
val_2 = "provided_value"
d_2 = "default_value"

# Test case 3: val is 0 (falsy but not None), should return val
val_3 = 0
d_3 = 42

# Test case 4: val is empty list (falsy but not None), should return val
val_4 = []
d_4 = [1, 2, 3]

# Test case 5: val is a tensor
torch.manual_seed(0)
val_5 = torch.tensor([1.0, 2.0])
d_5 = torch.tensor([0.0, 0.0])

ARGS = {
    "val": None,
    "d": "default_value"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
earily_stop Ran
ran on a synthesized input
gmum/MAT/src/utils.py
code served (permissive licence) · get_code("dbb58515a25d9f47")
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

torch.manual_seed(0)

# Analyze the function:
# - val_acc_history: list of validation accuracies (accessed by indexing)
# - tasks: list/collection (len() is called on it)
# - early_stop_step_single: integer (used in comparison)
# - early_stop_step_multi: integer (used in comparison)
# - required_progress: float/int (used in subtraction comparison)

# Create sample validation accuracy history
val_acc_history = [0.70, 0.72, 0.74, 0.75, 0.76, 0.765, 0.77, 0.771, 0.772]

# Create tasks list - can be any collection, just needs len()
tasks = ["task1"]  # Single task case

# Early stopping parameters
early_stop_step_single = 3
early_stop_step_multi = 5
required_progress = 0.01

ARGS = {
    "val_acc_history": val_acc_history,
    "tasks": tasks,
    "early_stop_step_single": early_stop_step_single,
    "early_stop_step_multi": early_stop_step_multi,
    "required_progress": required_progress
}
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
exists Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from ThomasMrY/VCT
pointer only; the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

xavier_normal_small_init_ Ran
ran; our contract draft was wrong, not the code
ardigen/MAT/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from YL-wang/GraphSAM, is pointer only (licence: NONE) · get_code("bcbec2ac208c5777")
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 YL-wang/GraphSAM, 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.

xavier_uniform_small_init_ Ran
ran; our contract draft was wrong, not the code
ardigen/MAT/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from YL-wang/GraphSAM, is pointer only (licence: NONE) · get_code("98dc6e3782d99038")
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 YL-wang/GraphSAM, 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.

attention Not yet run
unverified (harvested, no recorded run)
gmum/MAT/src/transformer.py
code served (permissive licence) · get_code("f30d2c34a90c3d8a")
How it ran

no invocation recorded.

featurize_mol Not yet run
unverified (harvested, no recorded run)
gmum/MAT/src/featurization/data_utils.py
code served (permissive licence) · get_code("081f1434ee84b91f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 4 later) and 4 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
exists 486 other papers
12 dated earlier, 2 the same month, 470 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
clones 79 other papers
19 dated earlier, 60 later · 11 only as an assembly brick
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1706.03762 (2017-06)
Attention Is All You Need
and 76 more not named here
xavier_normal_small_init_ 1 other paper
1 later
2406.13137 (2024-06)
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
xavier_uniform_small_init_ 1 other paper
1 later
2406.13137 (2024-06)
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models

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

Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry. To move towards this goal, we propose Molecule Attention Transformer (MAT). Our key innovation is to augment the attention mechanism in Transformer using inter-atomic distances and the molecular graph structure. Experiments show that MAT performs competitively on a diverse set of molecular prediction tasks. Most importantly, with a simple self-supervised pretraining, MAT requires tuning of only a few hyperparameter values to achieve state-of-the-art performance on downstream tasks. Finally, we show that attention weights learned by MAT are interpretable from the chemical point of view.

For agents

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

get_harvested_code_for_paper("2002.08264")
get_code_for_paper("2002.08264")
have("2002.08264")

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

curl https://syntology.ai/api/ran/2002.08264.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.08264.svg)](https://syntology.ai/paper/2002.08264)

Connect an agent — have() is free.