SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.00967 · 2021

Multiresolution Equivariant Graph Variational Autoencoder

arXiv · PDF · Open in the Atlas

Code that ran

9 of 14 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; 3 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 4 failures of our instrument; 5 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/2106.00967.json · badge: /api/ran/2106.00967.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
hytruongson/mgvae canonical (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
bachnguyente/temporal-mgn community (classifier label)
classifier basis: plan_row
3 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
create_adj Ran
ran, honoured the contract we drafted
hytruongson/mgvae/image_generation/train_mgvae.py
pointer only (licence: NONE) · get_code("7255f9ca58519b0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hytruongson/mgvae 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.

dot_product_decode Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from DaehanKim/vgae_pytorch
pointer only · get_code("ae488d391f6d24c2")
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.

dot_product_decode Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hytruongson/mgvae/general_graph_generation/train_mgvae_2nd.py
pointer only (licence: NONE) · get_code("119e67f25fbbc40b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hytruongson/mgvae 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.

filter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hytruongson/mgvae/citation_link_prediction/train_mgvae.py
pointer only (licence: NONE) · get_code("5dd9c22126dfe7c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hytruongson/mgvae 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.

generate_graphs_tmp Ran
ran on a synthesized input
bachnguyente/temporal-mgn/covid/code/utils.py
code served (permissive licence) · get_code("508d336e43180746")
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 os
import tempfile
import pandas as pd
import networkx as nx
from datetime import date, timedelta

# Create temporary directory and CSV files for testing
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, 'graphs'), exist_ok=True)

# Create sample CSV files that the function will try to read
sample_data_1 = pd.DataFrame({
    0: [1, 2, 3],
    1: [2, 3, 4],
    2: [0.5, 0.7, 0.9]
})
sample_data_2 = pd.DataFrame({
    0: [4, 5, 6],
    1: [5, 6, 7],
    2: [0.3, 0.6, 0.8]
})

# Write CSV files without headers
date_str_1 = '2023-01-01'
date_str_2 = '2023-01-02'
csv_path_1 = os.path.join(temp_dir, 'graphs', f'US_{date_str_1}.csv')
csv_path_2 = os.path.join(temp_dir, 'graphs', f'US_{date_str_2}.csv')

sample_data_1.to_csv(csv_path_1, header=False, index=False)
sample_data_2.to_csv(csv_path_2, header=False, index=False)

# Change working directory to temp_dir so relative paths work
original_cwd = os.getcwd()
os.chdir(temp_dir)

dates = [date_str_1, date_str_2]
country = 'US'

ARGS = {
    'dates': dates,
    'country': country
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, pandas — 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
generate_new_features Ran
ran on a synthesized input
bachnguyente/temporal-mgn/covid/code/utils.py
code served (permissive licence) · get_code("7fbc7c45eee17668")
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 3, 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.

import numpy as np
import pandas as pd
import networkx as nx

# Create a small graph with 3 nodes
G1 = nx.Graph()
G1.add_nodes_from(['node_0', 'node_1', 'node_2'])
G1.add_edges_from([('node_0', 'node_1'), ('node_1', 'node_2')])

G2 = nx.Graph()
G2.add_nodes_from(['node_0', 'node_1', 'node_2'])
G2.add_edges_from([('node_0', 'node_1'), ('node_1', 'node_2')])

G3 = nx.Graph()
G3.add_nodes_from(['node_0', 'node_1', 'node_2'])
G3.add_edges_from([('node_0', 'node_1'), ('node_1', 'node_2')])

Gs = [G1, G2, G3]

# Create labels DataFrame with nodes as index and dates as columns
dates = ['2024-01-01', '2024-01-02', '2024-01-03', '2024-01-04', '2024-01-05']
labels_data = {
    '2024-01-01': [1.0, 2.0, 3.0],
    '2024-01-02': [1.5, 2.5, 3.5],
    '2024-01-03': [2.0, 3.0, 4.0],
    '2024-01-04': [2.5, 3.5, 4.5],
    '2024-01-05': [3.0, 4.0, 5.0],
}
labels = pd.DataFrame(labels_data, index=['node_0', 'node_1', 'node_2'])

ARGS = {
    'Gs': Gs,
    'labels': labels,
    'dates': dates,
    'window': 7,
    'scaled': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, 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
glorot_init Ran
ran, honoured the contract we drafted
bachnguyente/temporal-mgn/chickenpox/temporal_model.py
code served (permissive licence) · get_code("33c8d926f0ebceb3")
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 Parameter, ndim 2, dtype family float, shape (4, 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

input_dim = 4
output_dim = 3

ARGS = {
    'input_dim': input_dim,
    'output_dim': output_dim
}
Setup block drafted by
a language model, Claude Sonnet 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 Parameter, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
glorot_init Ran
ran, honoured the contract we drafted
hytruongson/mgvae/image_generation/train_mgvae.py
pointer only (licence: NONE) · get_code("636ecbcda942ffd4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hytruongson/mgvae 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.

multiresolution_loss Ran
ran; our contract draft was wrong, not the code
hytruongson/mgvae/image_generation/train_mgvae.py
pointer only (licence: NONE) · get_code("90abd55553a0dc07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hytruongson/mgvae 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.

arima Not yet run
unverified (harvested, no recorded run)
bachnguyente/temporal-mgn/covid/code/models.py
code served (permissive licence) · get_code("0543ccfabf65c3aa")
How it ran

no invocation recorded.

read_meta_datasets Not yet run
unverified (harvested, no recorded run)
bachnguyente/temporal-mgn/covid/code/utils.py
code served (permissive licence) · get_code("2d4c9b982ec3f620")
How it ran

no invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
bachnguyente/temporal-mgn/covid/code/experiments.py
code served (permissive licence) · get_code("99b16ab3641139d0")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
bachnguyente/temporal-mgn/covid/code/experiments.py
code served (permissive licence) · get_code("a65ee9aa33f86221")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
bachnguyente/temporal-mgn/covid/code/metalearn.py
code served (permissive licence) · get_code("61c34f488910d4c6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 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
dot_product_decode 3 other papers
2 dated earlier, 1 later
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1906.06532 (2019-06)
Attributed Graph Clustering: A Deep Attentional Embedding Approach
2407.04999 (2024-07)
Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNs
glorot_init 1 other paper
1 dated earlier
1611.07308 (2016-11)
Variational Graph Auto-Encoders

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

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation.

For agents

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

get_harvested_code_for_paper("2106.00967")
get_code_for_paper("2106.00967")
have("2106.00967")

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

curl https://syntology.ai/api/ran/2106.00967.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.00967.svg)](https://syntology.ai/paper/2106.00967)

Connect an agent — have() is free.