SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.17656 · ICLR · 2025

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Arno Solin, Markus Heinonen, Vikas Garg, Najwa Laabid, Severi Rissanen

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 3 failures of our instrument; 8 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/2405.17656.json · badge: /api/ran/2405.17656.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
Aalto-QuML/DiffAlign canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
aalto-quml/diffalign canonical (classifier label)
classifier basis: classifier_2025
3 ran · 6 no recorded run
FunctionStatusWhere it lives
Etoy Ran
ran on a synthesized input · constructed an object; no result was computed
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("cfc16868035a3662")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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.

SinusoidalPosEmb Ran
ran on a synthesized input
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("e697b4752c97453b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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.

Xtoy Ran
ran on a synthesized input · constructed an object; no result was computed
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("863dcb9813616c11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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.

clamp Ran
ran, honoured the contract we drafted
Aalto-QuML/DiffAlign/diffalign/neuralnet/ema_pytorch.py
pointer only (licence: NONE) · get_code("e907f76525778206")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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.

compute_laplacian Ran
ran; our contract draft was wrong, not the code
Aalto-QuML/DiffAlign/diffalign/neuralnet/extra_features.py
pointer only (licence: NONE) · get_code("ccab2b12df8bd44a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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.

exists Ran
ran, violated the contract we drafted
Aalto-QuML/DiffAlign/diffalign/neuralnet/ema_pytorch.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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.

get_eigenvalues_features Ran
ran; our contract draft was wrong, not the code
Aalto-QuML/DiffAlign/diffalign/neuralnet/extra_features.py
pointer only (licence: NONE) · get_code("1a6187f72cb66c75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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.

laplacian_eigenvectors_gpu Ran
ran; our contract draft was wrong, not the code
Aalto-QuML/DiffAlign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("bff752d1e7ccc633")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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.

GraphTransformerWithYAtomMapPosEmb Not yet run
unverified (harvested, no recorded run)
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("938c82ec14c26496")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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. No invocation recorded.

NodeEdgeBlock Not yet run
unverified (harvested, no recorded run)
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("6e076146caba7dd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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. No invocation recorded.

NodeEdgeBlockImproved Not yet run
unverified (harvested, no recorded run)
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("d6759caff506f0c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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. No invocation recorded.

XEyTransformerLayer Not yet run
unverified (harvested, no recorded run)
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("a372a576e26cd124")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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. No invocation recorded.

assert_correctly_masked Not yet run
unverified (harvested, no recorded run)
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("a6d926d01c357eab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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. No invocation recorded.

get_X_prods_and_E_prods_aligned Not yet run
unverified (harvested, no recorded run)
aalto-quml/diffalign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("282326286ec069ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aalto-quml/diffalign 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. No invocation recorded.

get_eigenvectors_features Not yet run
unverified (harvested, no recorded run)
Aalto-QuML/DiffAlign/diffalign/neuralnet/extra_features.py
pointer only (licence: NONE) · get_code("f473a482524e385f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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. No invocation recorded.

laplacian_eigenvectors_scipy Not yet run
unverified (harvested, no recorded run)
Aalto-QuML/DiffAlign/diffalign/neuralnet/transformer_model_with_y.py
pointer only (licence: NONE) · get_code("daf3cb16ce2173f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Aalto-QuML/DiffAlign 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. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 1 later) and 11 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
336 dated earlier, 11 the same month, 128 later, 9 same year, order not determinable, 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
clamp 2 other papers
2 dated earlier
Tanke_Social_Diffusion_Long-term_Multiple_Human_Motion_Anticipation_ICCV_2023_paper (2023 (year only))
Social Diffusion: Long-term Multiple Human Motion Anticipation
2303.16570 (2023-03)
Point2Vec for Self-Supervised Representation Learning on Point Clouds
compute_laplacian 1 other paper
1 dated earlier
2308.16212 (2023-08)
RetroBridge: Modeling Retrosynthesis with Markov Bridges
get_eigenvalues_features 1 other paper
1 dated earlier
2308.16212 (2023-08)
RetroBridge: Modeling Retrosynthesis with Markov Bridges
get_eigenvectors_features 1 other paper
1 dated earlier
2308.16212 (2023-08)
RetroBridge: Modeling Retrosynthesis with Markov Bridges

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

Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that standard permutation equivariant denoisers face fundamental limitations in these tasks due to their inability to break symmetries in noisy inputs. To address this, we propose aligning input and target graphs to break input symmetries while preserving permutation equivariance in non-matching graph portions. Using retrosynthesis (i.e., the task of predicting precursors for synthesis of a given target molecule) as our application domain, we show how alignment dramatically improves discrete diffusion model performance from 5% to a SOTA-matching 54.7% top-1 accuracy. Code is available at https://github.com/Aalto-QuML/DiffAlign.

For agents

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

get_harvested_code_for_paper("2405.17656")
get_code_for_paper("2405.17656")
have("2405.17656")

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

curl https://syntology.ai/api/ran/2405.17656.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.17656.svg)](https://syntology.ai/paper/2405.17656)

Connect an agent — have() is free.