SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02622 · ICML · 2025

Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms

Bastian Rieck, Julius Von Rohrscheidt

arXiv · PDF · Open in the Atlas

Code that ran

1 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 0 have no contract verdict; 0 failures of our instrument; 9 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/2410.02622.json · badge: /api/ran/2410.02622.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
aidos-lab/Diss-l-ECT canonical (classifier label)
classifier basis: census
1 ran · 9 no recorded run
FunctionStatusWhere it lives
run_xgb_model_n_times Ran
ran, honoured the contract we drafted
aidos-lab/Diss-l-ECT/run_experiments.py
code served (permissive licence) · get_code("8fe951753baecff8")
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 tuple, ndim 1, 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 torch
import numpy as np
from unittest.mock import MagicMock, patch
from statistics import mean, stdev

torch.manual_seed(0)

# Mock classes and functions that are referenced in the function body

class HeterophilousGraphDataset:
    def __init__(self, **kwargs):
        self.data = torch.randn(2, 4)
        self.labels = torch.randint(0, 2, (2,))

class MockDataset:
    def __init__(self, **kwargs):
        self.data = torch.randn(2, 4)
        self.labels = torch.randint(0, 2, (2,))

# Mock the xgb_model function to return a simple numeric result
def xgb_model(dataset, radius1=None, radius2=None, ECT_TYPE=None, 
              NUM_THETAS=None, DEVICE=None, metric=None, subsample_size=None):
    # Return a random metric value between 0 and 1
    return np.random.uniform(0.5, 0.95)

# Inject the mock xgb_model into globals for the function to use
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'xgb_model', xgb_model)
setattr(current_module, 'HeterophilousGraphDataset', HeterophilousGraphDataset)
setattr(current_module, 'Minesweeper', MockDataset)
setattr(current_module, 'Tolokers', MockDataset)
setattr(current_module, 'Questions', MockDataset)

# Define ARGS dict with valid arguments for run_xgb_model_n_times
ARGS = {
    'dataset_name': 'Minesweeper',
    'dataset_params': {'num_nodes': 10, 'num_features': 4},
    'radius1': 0.5,
    'radius2': 1.5,
    'num_runs': 5
}
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 tuple, ndim 1, dtype family float — a tuple 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
compute_ecc Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/ect.py
code served (permissive licence) · get_code("440b2d24fe3664cd")
How it ran

no invocation recorded.

compute_ecc Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/ect_bu.py
code served (permissive licence) · get_code("bae9959643560c32")
How it ran

no invocation recorded.

compute_ecc_derivative Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/ect.py
code served (permissive licence) · get_code("e2771bf68f1ae526")
How it ran

no invocation recorded.

compute_ect_points Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/ect_bu.py
code served (permissive licence) · get_code("f6cb3fbe8f75aa28")
How it ran

no invocation recorded.

compute_ect_points_derivative Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/ect.py
code served (permissive licence) · get_code("76ea006b2d660705")
How it ran

no invocation recorded.

compute_wecc Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/ect_bu.py
code served (permissive licence) · get_code("c78b4478a09ef692")
How it ran

no invocation recorded.

compute_wecc Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/wect.py
code served (permissive licence) · get_code("92843114cce30793")
How it ran

no invocation recorded.

compute_wect Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/layers/wect.py
code served (permissive licence) · get_code("eba2b34a99924f5d")
How it ran

no invocation recorded.

run_xgb_model_once Not yet run
unverified (harvested, no recorded run)
aidos-lab/Diss-l-ECT/run_experiments.py
code served (permissive licence) · get_code("3250624aaa0451fb")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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
compute_ect_points 1 other paper
1 dated earlier
2310.07630 (2023-10)
Differentiable Euler Characteristic Transforms for Shape Classification

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

The Euler Characteristic Transform (ECT) is an efficiently-computable geometrical-topological invariant that characterizes the global shape of data. In this paper, we introduce the Local Euler Characteristic Transform (ℓ-ECT), a novel extension of the ECT particularly designed to enhance expressivity and interpretability in graph representation learning. Unlike traditional graph neural networks (GNNs), which may lose critical local details through aggregation, the ℓ-ECT provides a lossless representation of local neighborhoods. This approach addresses key limitations in GNNs by preserving local structures while maintaining global interpretability. Moreover, we construct a rotation-invariant metric based on ℓ-ECTs for spatial alignment of data spaces. Our method exhibits superior performance compared to standard GNNs on a variety of benchmark nodeclassification tasks, while also offering theoretical guarantees that demonstrate its effectiveness.

For agents

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

get_harvested_code_for_paper("2410.02622")
get_code_for_paper("2410.02622")
have("2410.02622")

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

curl https://syntology.ai/api/ran/2410.02622.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.02622.svg)](https://syntology.ai/paper/2410.02622)

Connect an agent — have() is free.