SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.04779 · 2023

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 4 failures of our instrument; 2 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/2304.04779.json · badge: /api/ran/2304.04779.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
thudm/graphmae2 canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
thudm/graphmae2/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from LiuXiaoxuanPKU/GACT-ICML, is pointer only (licence: NONE) · get_code("adf3b9c6c22af5ce")
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 LiuXiaoxuanPKU/GACT-ICML, 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.

auc_pair_loss Ran
ran; our contract draft was wrong, not the code
thudm/graphmae2/models/loss_func.py
code served (permissive licence) · get_code("87767eda0a0d0829")
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 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 torch.nn.functional as F

torch.manual_seed(0)

# The function auc_pair_loss takes three tensor arguments: x, y, z
# It normalizes them, computes similarities and dissimilarities, then returns a loss
# All three tensors should have the same shape for broadcasting to work

batch_size = 2
embedding_dim = 4

x = torch.randn(batch_size, embedding_dim)
y = torch.randn(batch_size, embedding_dim)
z = torch.randn(batch_size, embedding_dim)

ARGS = {
    "x": x,
    "y": y,
    "z": z,
}
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 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
create_activation Ran
ran on a synthesized input
thudm/graphmae2/utils.py
code served (permissive licence) · get_code("de1094fa7090d5c5")
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 ReLU. 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

torch.manual_seed(0)

# The function takes a single parameter: name
# It checks the name against various strings and returns the corresponding activation module
# or raises NotImplementedError if not recognized

ARGS = {
    'name': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
get_current_lr Ran
ran, honoured the contract we drafted
thudm/graphmae2/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from ZiyanLiu16/MUGEN, is pointer only (licence: NONE) · get_code("c9c9174dc014b586")
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 ZiyanLiu16/MUGEN, 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.

my_sweep_cut Ran
ran on a synthesized input
thudm/graphmae2/datasets/localclustering.py
code served (permissive licence) · get_code("ee059dcaf57afa9b")
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 float, shape (3,) 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 MockGraph:
    def __init__(self, num_nodes=5):
        self.num_nodes = num_nodes
        # Create a simple adjacency matrix (sparse representation)
        self.adjacency_matrix = np.zeros((num_nodes, num_nodes), dtype=np.float32)
        # Add some edges to make it non-trivial
        self.adjacency_matrix[0, 1] = 1.0
        self.adjacency_matrix[1, 0] = 1.0
        self.adjacency_matrix[1, 2] = 1.0
        self.adjacency_matrix[2, 1] = 1.0
        self.adjacency_matrix[2, 3] = 1.0
        self.adjacency_matrix[3, 2] = 1.0
        
        # Degree array (sum of edges for each node)
        self.d = np.array([1.0, 2.0, 2.0, 1.0, 0.0], dtype=np.float32)
        
        # Total volume of graph
        self.vol_G = float(np.sum(self.d))

g = MockGraph(num_nodes=5)
node = np.array([0, 1, 2], dtype=np.int64)

ARGS = {
    "g": g,
    "node": node
}
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 float, shape (3,) — shape (3,) 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
scale_feats Ran
ran on a synthesized input
thudm/graphmae2/datasets/data_proc.py
code served (permissive licence) · get_code("59c343e0da75c6fe")
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
import logging
from sklearn.preprocessing import StandardScaler

torch.manual_seed(0)

# The function expects a single parameter 'x' which should be a torch tensor
# that has a .numpy() method and can be processed by StandardScaler.
# Based on the function body:
# - x must be convertible to numpy via .numpy()
# - the numpy array will be fit and transformed by StandardScaler
# - the result will be converted back to a float tensor

# Create a small tensor with shape (2, 4) - 2 samples, 4 features
x = torch.randn(2, 4)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sklearn, 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
sce_loss Ran
ran; our contract draft was wrong, not the code
thudm/graphmae2/models/loss_func.py
pointer only (licence: MIT); the stored copy get_code serves, from ZiyanLiu16/MUGEN, is pointer only (licence: NONE) · get_code("6f9bb5eb98ec4887")
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 ZiyanLiu16/MUGEN, 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.

trunc_normal_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thudm/graphmae2/models/loss_func.py
code served (permissive licence) · get_code("915b71e73a54fc97")
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 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
import math

torch.manual_seed(0)

# Create a small tensor to be modified by trunc_normal_
tensor = torch.empty(2, 4)

# Define parameters for truncated normal initialization
mean = 0.0
std = 1.0
a = -2.0
b = 2.0

ARGS = {
    'tensor': tensor,
    'mean': mean,
    'std': std,
    'a': a,
    'b': b
}
Setup block drafted by
a language model, Claude Sonnet 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
calc_local_clustering Not yet run
unverified (harvested, no recorded run)
thudm/graphmae2/datasets/localclustering.py
code served (permissive licence) · get_code("cfc02746de2038a9")
How it ran

no invocation recorded.

setup_module Not yet run
unverified (harvested, no recorded run)
thudm/graphmae2/models/edcoder.py
code served (permissive licence) · get_code("35589fecfce05259")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 6 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
trunc_normal_ 160 other papers
56 dated earlier, 1 the same month, 101 later, 2 same year, order not determinable · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
accuracy 6 other papers
1 dated earlier, 5 later
2206.11357 (2022-06)
GACT: Activation Compressed Training for Generic Network Architectures
2310.10362 (2023-10)
Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks
2402.07225 (2024-02)
Rethinking Graph Masked Autoencoders through Alignment and Uniformity
and 3 more not named here
sce_loss 6 other papers
6 later
2309.04589 (2023-09)
Motif-aware Attribute Masking for Molecular Graph Pre-training
2310.00800 (2023-10)
GRAPHPATCHER: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
2402.07225 (2024-02)
Rethinking Graph Masked Autoencoders through Alignment and Uniformity
and 3 more not named here
get_current_lr 4 other papers
4 later
2402.07225 (2024-02)
Rethinking Graph Masked Autoencoders through Alignment and Uniformity
2402.13630 (2024-02)
UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
2410.13798 (2024-10)
Learning Graph Quantized Tokenizers
and 1 more not named here
auc_pair_loss 1 other paper
1 later
2410.13798 (2024-10)
Learning Graph Quantized Tokenizers
setup_module 1 other paper
1 later
2410.13798 (2024-10)
Learning Graph Quantized Tokenizers

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 self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data. Among both sets of graph SSL techniques, the masked graph autoencoders (e.g., GraphMAE)--one type of generative method--have recently produced promising results. The idea behind this is to reconstruct the node features (or structures)--that are randomly masked from the input--with the autoencoder architecture. However, the performance of masked feature reconstruction naturally relies on the discriminability of the input features and is usually vulnerable to disturbance in the features. In this paper, we present a masked self-supervised learning framework GraphMAE2 with the goal of overcoming this issue. The idea is to impose regularization on feature reconstruction for graph SSL. Specifically, we design the strategies of multi-view random re-mask decoding and latent representation prediction to regularize the feature reconstruction. The multi-view random re-mask decoding is to introduce randomness into reconstruction in the feature space, while the latent representation prediction is to enforce the reconstruction in the embedding space. Extensive experiments show that GraphMAE2 can consistently generate top results on various public datasets, including at least 2.45% improvements over state-of-the-art baselines on ogbn-Papers100M with 111M nodes and 1.6B edges.

For agents

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

get_harvested_code_for_paper("2304.04779")
get_code_for_paper("2304.04779")
have("2304.04779")

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

curl https://syntology.ai/api/ran/2304.04779.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.04779.svg)](https://syntology.ai/paper/2304.04779)

Connect an agent — have() is free.