SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.09810 · ICLR · 2021

White Paper of the ICLR 2021 Workshop on Geometrical and Topological Representation Learning ICLR 2021 CHALLENGE FOR COMPUTATIONAL GEOMETRY & TOPOLOGY: DESIGN AND RESULTS

Nina Miolane, Matteo Caorsi, Umberto Lupo, Marius Guerard

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 7 have no contract verdict; 0 failures of our instrument; 3 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/2108.09810.json · badge: /api/ran/2108.09810.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
geomstats/challenge-iclr-2021 canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
NearestNeighbor Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/1st-prize__mihaelanistor__Noise-Invariant-Topological-Features/models.py
code served (permissive licence) · get_code("7b8eb9cd52a03af3")
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 float, 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 numpy as np

torch.manual_seed(0)

# Create a distance matrix (4x4 for 4 samples)
# Each row represents distances from one sample to all others
distmat = torch.tensor([
    [0.0, 1.5, 2.3, 3.1],
    [1.5, 0.0, 1.2, 2.8],
    [2.3, 1.2, 0.0, 1.9],
    [3.1, 2.8, 1.9, 0.0]
], dtype=torch.float32)

# Create corresponding labels (4 labels for 4 samples)
labels = [0, 1, 1, 2]

ARGS = {
    "distmat": distmat,
    "labels": labels
}
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 float, 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
calc_r Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/tomogwen__Fuzzy-C-Means-Clustering-for-Persistence-Diagrams-and-Riemannian-Manifolds/giotto_fcm.py
code served (permissive licence) · get_code("af8f763f934b9b83")
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 2, dtype family float, shape (2, 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

# Create a small weight matrix W with shape (2, 3)
# n=2 rows, c=3 columns
W = np.array([
    [0.5, 0.3, 0.2],
    [0.1, 0.6, 0.3]
], dtype=np.float64)

ARGS = {
    "W": W,
    "fuzzy": True,
    "check_zero": False
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
gen_data Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/tomogwen__Fuzzy-C-Means-Clustering-for-Persistence-Diagrams-and-Riemannian-Manifolds/synthetic_data.py
code served (permissive licence) · get_code("afa0e81b8654f178")
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
from sklearn import datasets
import random

ARGS = {
    "seed": 42,
    "noise": 0.05,
    "n_samples": 100
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
gen_data2 Ran
ran, honoured the contract we drafted
geomstats/challenge-iclr-2021/tomogwen__Fuzzy-C-Means-Clustering-for-Persistence-Diagrams-and-Riemannian-Manifolds/synthetic_data.py
code served (permissive licence) · get_code("4dc9b2bab540890c")
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
from sklearn import datasets
import random

ARGS = {
    "seed": 42,
    "noise": 0.1,
    "n_samples": 100,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
occ_feature_preprocess Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/SomeshMohapatra__Protein-Peptide-Interactions-with-TDA/utils_occ_model.py
code served (permissive licence) · get_code("a03a815dfdd2b5ab")
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. 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 numpy as np
from sklearn import model_selection, metrics, svm, ensemble

# Create small input features
X_list = [np.random.randn(5, 3), np.random.randn(5, 2)]

ARGS = {
    "X": X_list,
    "y": None,
    "test_split": 0.2,
    "random_state": 108,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
occ_scorer Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/SomeshMohapatra__Protein-Peptide-Interactions-with-TDA/utils_occ_model.py
code served (permissive licence) · get_code("41f9cf1b9fb3a124")
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 float, 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 numpy as np
from sklearn.svm import OneClassSVM

# Create a simple one-class classifier (OneClassSVM)
# The function calls estimator.predict(X), so we need a model with a predict method
estimator = OneClassSVM(kernel='rbf', gamma='auto')

# Create small test data - 5 samples with 4 features
# The estimator needs to be fitted first
X_train = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [1.1, 2.1, 3.1, 4.1],
    [1.2, 2.2, 3.2, 4.2],
])
estimator.fit(X_train)

# Create test data for scoring - 2 samples with 4 features
# predict() returns labels (1 for inliers, -1 for outliers in OneClassSVM)
# but the occ_scorer function expects predictions of 1 or 0
# We'll use a mock estimator that returns proper binary predictions
class MockOneClassEstimator:
    def predict(self, X):
        # Return binary predictions: mix of 1s and 0s/other values
        # This should work with the occ_scorer logic
        return np.array([1, 1])

estimator = MockOneClassEstimator()

X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0],
])

ARGS = {
    "estimator": estimator,
    "X": X,
    "y": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
pretty_metrics Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/marek094__Investigating-CNN-Weights-with-Topology/helpers.py
code served (permissive licence) · get_code("0a0fc5f8bc37b0ae")
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 DataFrame. 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 pandas as pd

# Create a minimal DataFrame with the structure expected by pretty_metrics
metrics = pd.DataFrame({
    'Unnamed: 0': [0, 1],
    'config.dnn_architecture': ['arch1', 'arch2'],
    'modeldir': ['/path/to/model1', '/path/to/model2'],
    'config.b_init': ['init1', 'init2'],
    'loss': [0.5, 0.3],
    'accuracy': [0.9, 0.95]
})

# Set the index to have meaningful values
metrics.index = pd.Index(['run_1', 'run_2'], name='experiment')

ARGS = {
    'metrics': metrics
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
simulate_data_on_small_circle Ran
ran on a synthesized input
geomstats/challenge-iclr-2021/ZhiyLiu__Shape-Analysis-with-Skeletal-Models-and-Principal-Nested-Spheres/utils.py
code served (permissive licence) · get_code("37c64575189aff3e")
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 2, dtype family float, shape (3, 10) 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

# Set random seed for reproducibility
np.random.seed(0)

# The function simulate_data_on_small_circle takes one parameter: num
# It has a default value of 50, so we can call it with or without arguments
# Let's test with a small number for efficiency

ARGS = {
    "num": 10
}
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 2, dtype family float, shape (3, 10) — shape (3, 10) 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
compute_diagrams Not yet run
unverified (harvested, no recorded run)
geomstats/challenge-iclr-2021/tomogwen__Fuzzy-C-Means-Clustering-for-Persistence-Diagrams-and-Riemannian-Manifolds/synthetic_data.py
code served (permissive licence) · get_code("66be322ffcae3859")
How it ran

no invocation recorded.

filter_dataset Not yet run
unverified (harvested, no recorded run)
geomstats/challenge-iclr-2021/SomeshMohapatra__Protein-Peptide-Interactions-with-TDA/utils_occ_model.py
code served (permissive licence) · get_code("273aa4a4162f2bbf")
How it ran

no invocation recorded.

pd_fuzzy Not yet run
unverified (harvested, no recorded run)
geomstats/challenge-iclr-2021/tomogwen__Fuzzy-C-Means-Clustering-for-Persistence-Diagrams-and-Riemannian-Manifolds/giotto_fcm.py
code served (permissive licence) · get_code("a55659e675ebcb38")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 10 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
gen_data2 1 other paper
1 dated earlier
2006.02796 (2020-06)
Fuzzy c-Means Clustering for Persistence Diagrams

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 presents the computational challenge on differential geometry and topology that happened within the ICLR 2021 workshop "Geometric and Topological Representation Learning". The competition asked participants to provide creative contributions to the fields of computational geometry and topology through the open-source repositories Geomstats and Giotto-TDA. The challenge at-

For agents

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

get_harvested_code_for_paper("2108.09810")
get_code_for_paper("2108.09810")
have("2108.09810")

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

curl https://syntology.ai/api/ran/2108.09810.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.09810.svg)](https://syntology.ai/paper/2108.09810)

Connect an agent — have() is free.