SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.08047 · 2020

Simple, Scalable, and Stable Variational Deep Clustering

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2005.08047.json · badge: /api/ran/2005.08047.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
king/s3vdc canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
check_array_feature Ran
ran on a synthesized input
king/s3vdc/lib/check_array_feature.py
code served (permissive licence) · get_code("29cf17f228d80bc1")
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 tensorflow as tf

# Create a valid TensorFlow tensor with shape (2, 4)
# This represents a batch of 2 samples, each with 4 features
tensor_valid = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

ARGS = {
    "tensor": tensor_valid
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
find_feature_column Ran
ran on a synthesized input
king/s3vdc/lib/find_feature_column.py
code served (permissive licence) · get_code("6fe92c82e05db3ef")
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 MockFeatureColumn. 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 tensorflow as tf

# Create mock feature column objects
class MockFeatureColumn:
    def __init__(self, name):
        self.name = name

# Define feature columns with distinct names
feature_columns = [
    MockFeatureColumn("numeric_age"),
    MockFeatureColumn("numeric_income"),
    MockFeatureColumn("categorical_gender"),
    MockFeatureColumn("categorical_location"),
]

ARGS = {
    "name": "numeric",
    "feature_columns": feature_columns,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockFeatureColumn — a MockFeatureColumn output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockFeatureColumn 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
metric_calinski_harabaz Not yet run
unverified (harvested, no recorded run)
king/s3vdc/lib/calinski_harabaz.py
code served (permissive licence) · get_code("3e79e980eccc4c39")
How it ran

no invocation recorded.

metric_cluster_separation Not yet run
unverified (harvested, no recorded run)
king/s3vdc/lib/cluster_separation.py
code served (permissive licence) · get_code("29fa774c37796626")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep clustering (DC) has become the state-of-the-art for unsupervised clustering. In principle, DC represents a variety of unsupervised methods that jointly learn the underlying clusters and the latent representation directly from unstructured datasets. However, DC methods are generally poorly applied due to high operational costs, low scalability, and unstable results. In this paper, we first evaluate several popular DC variants in the context of industrial applicability using eight empirical criteria. We then choose to focus on variational deep clustering (VDC) methods, since they mostly meet those criteria except for simplicity, scalability, and stability. To address these three unmet criteria, we introduce four generic algorithmic improvements: initial $γ$-training, periodic $β$-annealing, mini-batch GMM (Gaussian mixture model) initialization, and inverse min-max transform. We also propose a novel clustering algorithm S3VDC (simple, scalable, and stable VDC) that incorporates all those improvements. Our experiments show that S3VDC outperforms the state-of-the-art on both benchmark tasks and a large unstructured industrial dataset without any ground truth label. In addition, we analytically evaluate the usability and interpretability of S3VDC.

For agents

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

get_harvested_code_for_paper("2005.08047")
get_code_for_paper("2005.08047")
have("2005.08047")

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

curl https://syntology.ai/api/ran/2005.08047.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.08047.svg)](https://syntology.ai/paper/2005.08047)

Connect an agent — have() is free.