SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.10685 · NeurIPS · 2024

Scale Equivariant Graph Metanetworks

Yannis Panagakis, Giorgos Bouritsas, Ioannis Kalogeropoulos

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2406.10685.json · badge: /api/ran/2406.10685.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
jkalogero/scalegmn canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
residual_param_update Ran
ran, honoured the contract we drafted
jkalogero/scalegmn/inr_editing.py
code served (permissive licence) · get_code("321acff21ae45e89")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:11:28Z). 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 expects lists of weights and biases (likely tensors or arrays)
# and lists of delta_weights and delta_biases to add to them.
# It iterates through indices and performs element-wise addition.

# Create small tensors with distinct shapes for clarity
weights = [
    torch.randn(4, 3),
    torch.randn(3, 2),
    torch.randn(2, 1)
]

biases = [
    torch.randn(3),
    torch.randn(2),
    torch.randn(1)
]

delta_weights = [
    torch.randn(4, 3),
    torch.randn(3, 2),
    torch.randn(2, 1)
]

delta_biases = [
    torch.randn(3),
    torch.randn(2),
    torch.randn(1)
]

ARGS = {
    "weights": weights,
    "biases": biases,
    "delta_weights": delta_weights,
    "delta_biases": delta_biases
}
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 tuple — a tuple output has no array shape of its own; none is 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
evaluate Ran
ran; our contract draft was wrong, not the code
jkalogero/scalegmn/predicting_generalization.py
code served (permissive licence) · get_code("248f1ce6a37e2737")
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 dict. 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 torch.nn.functional as F
import numpy as np
from sklearn.metrics import r2_score
from scipy.stats import kendalltau

torch.manual_seed(0)

# Create a minimal neural network that takes a batch and outputs predictions
class MinimalNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 1)
    
    def forward(self, x):
        return self.linear(x.x)

# Create a minimal batch class that has the required attributes
class MinimalBatch:
    def __init__(self, x, y):
        self.x = x
        self.y = y
    
    def to(self, device):
        self.x = self.x.to(device)
        self.y = self.y.to(device)
        return self

# Create sample data loader with 2 batches
batch1_x = torch.randn(2, 4)
batch1_y = torch.rand(2)
batch1 = MinimalBatch(batch1_x, batch1_y)

batch2_x = torch.randn(2, 4)
batch2_y = torch.rand(2)
batch2 = MinimalBatch(batch2_x, batch2_y)

loader = [batch1, batch2]

# Create the network
net = MinimalNet()

# Create a loss function
loss_fn = nn.BCELoss()

# Set device
device = torch.device('cpu')

ARGS = {
    'net': net,
    'loader': loader,
    'loss_fn': loss_fn,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

This paper pertains to an emerging machine learning paradigm: learning higherorder functions, i.e. functions whose inputs are functions themselves, particularly when these inputs are Neural Networks (NNs). With the growing interest in architectures that process NNs, a recurring design principle has permeated the field: adhering to the permutation symmetries arising from the connectionist structure of NNs. However, are these the sole symmetries present in NN parameterizations? Zooming into most practical activation functions (e.g. sine, ReLU, tanh) answers this question negatively and gives rise to intriguing new symmetries, which we collectively refer to as scaling symmetries, that is, non-zero scalar multiplications and divisions of weights and biases. In this work, we propose Scale Equivariant Graph MetaNetworks -ScaleGMNs, a framework that adapts the Graph Metanetwork (message-passing) paradigm by incorporating scaling symmetries and thus rendering neuron and edge representations equivariant to valid scalings. We introduce novel building blocks, of independent technical interest, that allow for equivariance or invariance with respect to individual scalar multipliers or their product and use them in all components of ScaleGMN. Furthermore, we prove that, under certain expressivity conditions, ScaleGMN can simulate the forward and backward pass of any input feedforward neural network. Experimental results demonstrate that our method advances the state-of-the-art performance for several datasets and activation functions, highlighting the power of scaling symmetries as an inductive bias for NN processing. The source code is publicly available at https://github.com/jkalogero/scalegmn.

For agents

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

get_harvested_code_for_paper("2406.10685")
get_code_for_paper("2406.10685")
have("2406.10685")

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

curl https://syntology.ai/api/ran/2406.10685.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.10685.svg)](https://syntology.ai/paper/2406.10685)

Connect an agent — have() is free.