SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.01289 · 2021

Representation Learning for Clustering via Building Consensus

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 6 failures of our instrument; 0 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/2105.01289.json · badge: /api/ran/2105.01289.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
JayanthRR/ConCURL_NCE canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
byol_loss_fn Ran
ran; our contract draft was wrong, not the code
JayanthRR/ConCURL_NCE/losses.py
code served (permissive licence) · get_code("de5ec551fb74b9c5")
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 1, dtype family float, shape (2,) 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

torch.manual_seed(0)

# The function byol_loss_fn takes two tensors x and y
# and computes: 2 - 2 * (x * y).sum(dim=-1)
# This means x and y are multiplied element-wise, summed along the last dimension
# So x and y should have the same shape with at least one dimension

# Create small tensors: batch size 2, embedding dimension 4
x = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "x": x,
    "y": y
}
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 1, dtype family float, shape (2,) — shape (2,) 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
center_crop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JayanthRR/ConCURL_NCE/lib/custom_transforms.py
code served (permissive licence) · get_code("693513ff2d202308")
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 3, dtype family float, shape (2, 2, 0) 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

torch.manual_seed(0)

# The function expects:
# - x: a 3D tensor with shape (batch, height, width)
# - center_crop_size: a tuple or list of (crop_height, crop_width)

# Create a small 3D tensor: batch=2, height=4, width=3
x = torch.randn(2, 4, 3)

# Create center_crop_size with smaller dimensions than x
# so the crop is valid (must be smaller than x dimensions)
center_crop_size = (2, 1)

ARGS = {
    "x": x,
    "center_crop_size": center_crop_size,
}
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 3, dtype family float, shape (2, 2, 0) — shape (2, 2, 0) 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
JayanthRR/ConCURL_NCE/model_utils/nce_resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

distributed_sinkhorn Ran
ran; our contract draft was wrong, not the code
JayanthRR/ConCURL_NCE/losses.py
code served (permissive licence) · get_code("2afdf62a2f77e421")
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 (3, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# Q is a 2D tensor that gets normalized and processed
# Shape should be (num_samples, num_classes) - using distinct dimensions
Q = torch.rand(4, 3)

# nmb_iters is the number of iterations for the Sinkhorn algorithm
nmb_iters = 5

ARGS = {
    "Q": Q,
    "nmb_iters": nmb_iters,
}
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 2, dtype family float, shape (3, 4) — shape (3, 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
getQ Ran
ran; our contract draft was wrong, not the code
JayanthRR/ConCURL_NCE/losses.py
code served (permissive licence) · get_code("7d0517cb29119e33")
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 (3, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# out_queue should be a 2D tensor
# The function calls .t() on it, so it needs to be transposable
# Then it's divided by epsilon and exp is taken
# Shape: (batch_size, num_features) - let's use (3, 4)
out_queue = torch.randn(3, 4)

# epsilon is a float parameter with default 0.05
epsilon = 0.05

ARGS = {
    "out_queue": out_queue,
    "epsilon": epsilon,
}
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 2, dtype family float, shape (3, 4) — shape (3, 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
random_num_generator Ran
ran, honoured the contract we drafted
JayanthRR/ConCURL_NCE/lib/custom_transforms.py
code served (permissive licence) · get_code("abf95b2d2f20e322")
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 float64, ndim 0, 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

# Set random seed for reproducibility
np.random.seed(42)

# Create a valid config for 'uniform' distribution
config_uniform = ['uniform', 0.5, 1.5]

# Create the ARGS dictionary with all required parameters
ARGS = {
    'config': config_uniform,
    'random_state': np.random
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
to_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JayanthRR/ConCURL_NCE/lib/custom_transforms.py
code served (permissive licence) · get_code("382714b2c227ba48")
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 3, dtype family float, shape (2, 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 numpy as np

torch.manual_seed(0)

# The function expects x to be a numpy array with shape (H, W, C)
# It will transpose to (C, H, W) and convert to torch tensor
x = np.random.randn(4, 3, 2).astype(np.float32)

ARGS = {
    "x": x
}
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
305 dated earlier, 6 the same month, 369 later, 6 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
center_crop 2 other papers
2 dated earlier
1904.01990 (2019-04)
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
2008.03813 (2020-08)
Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
random_num_generator 2 other papers
2 dated earlier
1904.01990 (2019-04)
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
2008.03813 (2020-08)
Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
to_tensor 2 other papers
2 dated earlier
1904.01990 (2019-04)
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
2008.03813 (2020-08)
Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
distributed_sinkhorn 1 other paper
1 the same month
2105.13353 (2021-05)
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering

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 focus on unsupervised representation learning for clustering of images. Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must be close in the representation space (exemplar consistency), and/or similar images must have similar cluster assignments (population consistency). We define an additional notion of consistency, consensus consistency, which ensures that representations are learned to induce similar partitions for variations in the representation space, different clustering algorithms or different initializations of a single clustering algorithm. We define a clustering loss by executing variations in the representation space and seamlessly integrate all three consistencies (consensus, exemplar and population) into an end-to-end learning framework. The proposed algorithm, consensus clustering using unsupervised representation learning (ConCURL), improves upon the clustering performance of state-of-the-art methods on four out of five image datasets. Furthermore, we extend the evaluation procedure for clustering to reflect the challenges encountered in real-world clustering tasks, such as maintaining clustering performance in cases with distribution shifts. We also perform a detailed ablation study for a deeper understanding of the proposed algorithm. The code and the trained models are available at https://github.com/JayanthRR/ConCURL_NCE.

For agents

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

get_harvested_code_for_paper("2105.01289")
get_code_for_paper("2105.01289")
have("2105.01289")

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

curl https://syntology.ai/api/ran/2105.01289.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.01289.svg)](https://syntology.ai/paper/2105.01289)

Connect an agent — have() is free.