SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.05241 · NeurIPS · 2021

Multi-Facet Clustering Variational Autoencoders

Chris Holmes, Fabian Falck, Haoting Zhang, Matthew Willetts, George Nicholson, Christopher Yau

arXiv · PDF · Open in the Atlas

Code that ran

14 of 25 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 6 failures of our instrument; 11 no recorded run), 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/2106.05241.json · badge: /api/ran/2106.05241.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
FabianFalck/mfcvae canonical (classifier label)
classifier basis: classifier_2025
7 ran · 5 no recorded run
eelxpeng/UnsupervisedDeepLearning-Pytorch community
Papers with Code archive
4 ran · 1 no recorded run
addtt/boiler-pytorch unrelated (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
Zhiyuan1991/proVLAE community
Papers with Code archive
1 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
FCSharedDecoder Ran
ran on a synthesized input
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("3c2568c9b4080187")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float, shape (2, 6) 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 torch.nn as nn
from typing import List

def build_fc_network(layer_dims, activation='relu', dropout_prob=0.0, batch_norm=False):
    """
    Stacks multiple fully-connected layers with an activation function and a dropout layer in between.
    """
    net = []
    for i in range(1, len(layer_dims)):
        net.append(nn.Linear(layer_dims[i - 1], layer_dims[i]))
        if activation == 'relu':
            net.append(nn.ReLU())
        elif activation == 'leaky_relu':
            net.append(nn.LeakyReLU())
        elif activation == 'elu':
            net.append(nn.ELU())
        elif activation == 'sigmoid':
            net.append(nn.Sigmoid())
        if batch_norm:
            net.append(nn.BatchNorm1d(layer_dims[i]))
        net.append(nn.Dropout(dropout_prob))
    net = nn.Sequential(*net)
    return net

class FCSharedDecoder(nn.Module):

    def __init__(self, layer_dims: List[int], J_n_mixtures: int, activation: str='relu', dropout_prob: float=0.0, do_fc_batch_norm: bool=False):
        super(self.__class__, self).__init__()
        self.J_n_mixtures = J_n_mixtures
        self.net = build_fc_network(layer_dims=layer_dims, activation=activation, dropout_prob=dropout_prob, batch_norm=do_fc_batch_norm)

    def forward(self, z_sample_q_z_j_x_list: List[torch.tensor]):
        z_sample_q_z_x = torch.cat(z_sample_q_z_j_x_list, dim=1)
        return self.net(z_sample_q_z_x)


INIT_ARGS = {
    'layer_dims': [12, 8, 6],
    'J_n_mixtures': 3,
    'activation': 'relu',
    'dropout_prob': 0.1,
    'do_fc_batch_norm': False,
}

ARGS = {
    'z_sample_q_z_j_x_list': [
        torch.randn(2, 4),
        torch.randn(2, 4),
        torch.randn(2, 4),
    ],
}

model = FCSharedDecoder(**INIT_ARGS)
output = model(**ARGS)
print(f"Output shape: {output.shape}")
print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 (2, 6) — shape (2, 6) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
FCseparateEncoders Ran
ran on a synthesized input
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("d8c0031da2c81f1e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) 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 torch
import torch.nn as nn
from typing import List

def build_fc_network(layer_dims, activation='relu', dropout_prob=0.0, batch_norm=False):
    """
    Stacks multiple fully-connected layers with an activation function and a dropout layer in between.
    """
    net = []
    for i in range(1, len(layer_dims)):
        net.append(nn.Linear(layer_dims[i - 1], layer_dims[i]))
        if activation == 'relu':
            net.append(nn.ReLU())
        elif activation == 'leaky_relu':
            net.append(nn.LeakyReLU())
        elif activation == 'elu':
            net.append(nn.ELU())
        elif activation == 'sigmoid':
            net.append(nn.Sigmoid())
        if batch_norm:
            net.append(nn.BatchNorm1d(layer_dims[i]))
        net.append(nn.Dropout(dropout_prob))
    net = nn.Sequential(*net)
    return net

class FCseparateEncoders(nn.Module):

    def __init__(self, layer_dims: List[int], J_n_mixtures: int, activation: str='relu', dropout_prob: float=0.0, do_fc_batch_norm: bool=False):
        super(self.__class__, self).__init__()
        self.J_n_mixtures = J_n_mixtures
        self.net_list = nn.ModuleList()
        for j in range(self.J_n_mixtures):
            self.net_list.append(build_fc_network(layer_dims=layer_dims[j], activation=activation, dropout_prob=dropout_prob, batch_norm=do_fc_batch_norm))

    def forward(self, x):
        h_list = []
        for j in range(self.J_n_mixtures):
            h = self.net_list[j](x)
            h_list.append(h)
        return h_list


INIT_ARGS = {
    'layer_dims': [[4, 8, 3], [4, 6, 3]],
    'J_n_mixtures': 2,
    'activation': 'relu',
    'dropout_prob': 0.1,
    'do_fc_batch_norm': False
}

ARGS = {
    'x': torch.randn(2, 4)
}

if __name__ == '__main__':
    model = FCseparateEncoders(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output type: {type(output)}")
    print(f"Number of outputs: {len(output)}")
    for i, out in enumerate(output):
        print(f"Output {i} shape: {out.shape}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
FCsharedEncoder Ran
ran on a synthesized input
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("6a768b080b45bdca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) 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 torch
import torch.nn as nn
from typing import List

def build_fc_network(layer_dims, activation='relu', dropout_prob=0.0, batch_norm=False):
    """
    Stacks multiple fully-connected layers with an activation function and a dropout layer in between.

    - Source used as orientation: https://github.com/eelxpeng/UnsupervisedDeepLearning-Pytorch/blob/master/udlp/clustering/vade.py

    Args: 
        layer_dims: A list of integers, where (starting from 1) the (i-1)th and ith entry indicates the input
                    and output dimension of the ith layer, respectively.
        activation: Activation function to choose. "relu" or "sigmoid".
        dropout_prob: Dropout probability between every fully connected layer with activation.

    Returns: 
        An nn.Sequential object of the layers.
    """
    net = []
    for i in range(1, len(layer_dims)):
        net.append(nn.Linear(layer_dims[i - 1], layer_dims[i]))
        if activation == 'relu':
            net.append(nn.ReLU())
        elif activation == 'leaky_relu':
            net.append(nn.LeakyReLU())
        elif activation == 'elu':
            net.append(nn.ELU())
        elif activation == 'sigmoid':
            net.append(nn.Sigmoid())
        if batch_norm:
            net.append(nn.BatchNorm1d(layer_dims[i]))
        net.append(nn.Dropout(dropout_prob))
    net = nn.Sequential(*net)
    return net

class FCsharedEncoder(nn.Module):

    def __init__(self, layer_dims: List[int], J_n_mixtures: int, activation: str='relu', dropout_prob: float=0.0, do_fc_batch_norm: bool=False):
        super(self.__class__, self).__init__()
        self.J_n_mixtures = J_n_mixtures
        self.net = build_fc_network(layer_dims=layer_dims, activation=activation, dropout_prob=dropout_prob, batch_norm=do_fc_batch_norm)

    def forward(self, x):
        h = self.net(x)
        h_list = [h for _ in range(self.J_n_mixtures)]
        return h_list


INIT_ARGS = {
    'layer_dims': [4, 8, 3],
    'J_n_mixtures': 2,
    'activation': 'relu',
    'dropout_prob': 0.1,
    'do_fc_batch_norm': False
}

ARGS = {
    'x': torch.randn(2, 4)
}

if __name__ == '__main__':
    model = FCsharedEncoder(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output type: {type(output)}")
    print(f"Output length: {len(output)}")
    print(f"Output[0] shape: {output[0].shape}")
    print(f"Output[1] shape: {output[1].shape}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
MnistVAE Ran
ran on a synthesized input · constructed an object; no result was computed
addtt/boiler-pytorch/models/mnist_vae.py
code served (permissive licence) · get_code("26f5b491fc1c025d")
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 an instance of its own class, MnistVAE: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn
from torch.distributions import Normal
import numpy as np

torch.manual_seed(0)

ARGS = {
    'z_dim': 8,
}
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 MnistVAE — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MnistVAE 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
Normal Ran
ran on a synthesized input
Zhiyuan1991/proVLAE/model_ladder_pro_celbA.py
pointer only (licence: NOASSERTION) · get_code("211690ea3f81115d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhiyuan1991/proVLAE (NOASSERTION). 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.

ResidualConvBlock Ran
ran on a synthesized input
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("12e98decb92b6980")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, 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 torch.nn as nn

# INIT_ARGS: parameters for ResidualConvBlock.__init__
INIT_ARGS = {
    'n_channels': 8,
    'activation': 'relu'
}

# ARGS: parameters for the forward method
# The forward method takes x as input
# x should be a 4D tensor: (batch, channels, height, width)
# channels must match n_channels from INIT_ARGS
ARGS = {
    'x': torch.randn(2, 8, 16, 16)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
adjust_learning_rate Ran
ran, honoured the contract we drafted
eelxpeng/UnsupervisedDeepLearning-Pytorch/udlp/clustering/vade.py
code served (permissive licence) · get_code("fbb874d411d9eea7")
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 torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model with parameters
model = nn.Linear(4, 2)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define arguments for adjust_learning_rate
ARGS = {
    'init_lr': 0.1,
    'optimizer': optimizer,
    'epoch': 5
}
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 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
buildNetwork Ran
ran; our contract draft was wrong, not the code
eelxpeng/UnsupervisedDeepLearning-Pytorch/udlp/clustering/vade.py
code served (permissive licence) · get_code("f0527d9b7e69a1b1")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    'layers': [4, 8, 16, 3],
    'activation': 'relu',
    'dropout': 0.5
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
build_cnn_network Ran
ran; our contract draft was wrong, not the code
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("9b58e319e01d091f")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'transpose_conv': False,
    'kernel_size': 3,
    'stride': 1,
    'output_padding': None,
    'activation': 'leaky_relu',
    'dropout_prob': 0.1,
    'weight_norm': False,
    'batch_norm': True,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
build_fc_network Ran
ran; our contract draft was wrong, not the code
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("53afb335f775301f")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    'layer_dims': [10, 8, 6, 4],
    'activation': 'relu',
    'dropout_prob': 0.2,
    'batch_norm': True
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_module_device Ran
ran; our contract draft was wrong, not the code
addtt/boiler-pytorch/models/mnist_vae.py
code served (permissive licence) · get_code("41380e1185791a99")
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 device. 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
from torch import nn

torch.manual_seed(0)

class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

module = SimpleModule()

ARGS = {
    "module": module
}
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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
log_likelihood_samplesImean_sigma Ran
ran; our contract draft was wrong, not the code
eelxpeng/UnsupervisedDeepLearning-Pytorch/udlp/clustering/vade.py
code served (permissive licence) · get_code("d2619b31897cb53e")
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 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
import math

torch.manual_seed(0)

# Analyze the function:
# - samples: tensor, used with .size()[1] to get dimension, and in arithmetic operations
# - mu: tensor, used in arithmetic with samples
# - logvar: tensor, used in arithmetic with samples
# All three should have compatible shapes for broadcasting

batch_size = 2
feature_dim = 4

samples = torch.randn(batch_size, feature_dim)
mu = torch.randn(batch_size, feature_dim)
logvar = torch.randn(batch_size, feature_dim)

ARGS = {
    "samples": samples,
    "mu": mu,
    "logvar": logvar
}
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 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
log_likelihood_samples_unit_gaussian Ran
ran; our contract draft was wrong, not the code
eelxpeng/UnsupervisedDeepLearning-Pytorch/udlp/clustering/vade.py
code served (permissive licence) · get_code("7a946359766e7688")
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 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
import math

torch.manual_seed(0)

# The function expects 'samples' to be a tensor
# It calls:
# - samples.size()[1] to get the second dimension
# - torch.sum(0.5 * samples ** 2, 1) which sums over dimension 1
# So samples should be a 2D tensor with shape (batch_size, feature_dim)

samples = torch.randn(2, 4)

ARGS = {
    "samples": samples
}
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 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
softplus_inverse_numpy Ran
ran, violated the contract we drafted
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("8882946f83006f1b")
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 ndarray, ndim 1, dtype family float, shape (4,) 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

# The function takes two parameters:
# - x: input array (should be numeric, typically float)
# - beta: scaling parameter (should be numeric, typically float)

# Create small test inputs
x = np.array([0.5, 1.0, 1.5, 2.0], dtype=np.float32)
beta = 1.0

ARGS = {
    "x": x,
    "beta": beta,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (4,) — shape (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
BaseGenerativeModel Not yet run
unverified (harvested, no recorded run)
addtt/boiler-pytorch/models/mnist_vae.py
code served (permissive licence) · get_code("52f7b3f9c293acc1")
How it ran

no invocation recorded.

BaseModel Not yet run
unverified (harvested, no recorded run)
addtt/boiler-pytorch/models/mnist_vae.py
code served (permissive licence) · get_code("bb6c3a3a8b164360")
How it ran

no invocation recorded.

Bernoulli Not yet run
unverified (harvested, no recorded run)
Zhiyuan1991/proVLAE/model_ladder_pro_celbA.py
pointer only (licence: NOASSERTION) · get_code("17b77e2df6e4b53f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhiyuan1991/proVLAE (NOASSERTION). 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. No invocation recorded.

CONVvlaeDecoderCelebA Not yet run
unverified (harvested, no recorded run)
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("531a8ab1dbcdf6cd")
How it ran

no invocation recorded.

CONVvlaeEncoderCelebA Not yet run
unverified (harvested, no recorded run)
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("16a945d4f4868865")
How it ran

no invocation recorded.

FCvlaeDecoder Not yet run
unverified (harvested, no recorded run)
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("66f5f1c1582b0467")
How it ran

no invocation recorded.

FCvlaeEncoder Not yet run
unverified (harvested, no recorded run)
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("83df06166b5ae307")
How it ran

no invocation recorded.

MFCVAE Not yet run
unverified (harvested, no recorded run)
FabianFalck/mfcvae/mfcvae.py
code served (permissive licence) · get_code("defcc3d876b77dae")
How it ran

no invocation recorded.

VAE_ladder Not yet run
unverified (harvested, no recorded run)
Zhiyuan1991/proVLAE/model_ladder_pro_celbA.py
pointer only (licence: NOASSERTION) · get_code("8f2b6bf45d13ab4b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Zhiyuan1991/proVLAE (NOASSERTION). 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. No invocation recorded.

VaDE Not yet run
unverified (harvested, no recorded run)
eelxpeng/UnsupervisedDeepLearning-Pytorch/udlp/clustering/vade.py
code served (permissive licence) · get_code("6c018f96de64c8af")
How it ran

no invocation recorded.

cluster_acc Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from slim1017/VaDE
pointer only; the stored copy get_code serves, from slim1017/VaDE, is pointer only (licence: NONE) · get_code("4c9bb7ea70e75b6f")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. No invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 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 24 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
cluster_acc
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1611.05148 (2016-11)
Variational Deep Embedding: An Unsupervised and Generative Approach to 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

Work in deep clustering focuses on finding a single partition of data. However, high-dimensional data, such as images, typically feature multiple interesting characteristics one could cluster over. For example, images of objects against a background could be clustered over the shape of the object and separately by the colour of the background. In this paper, we introduce Multi-Facet Clustering Variational Autoencoders (MFCVAE), a novel class of variational autoencoders with a hierarchy of latent variables, each with a Mixture-of-Gaussians prior, that learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end. MFC-VAE uses a progressively-trained ladder architecture which leads to highly stable performance. We provide novel theoretical results for optimising the ELBO analytically with respect to the categorical variational posterior distribution, correcting earlier influential theoretical work. On image benchmarks, we demonstrate that our approach separates out and clusters over different aspects of the data in a disentangled manner. We also show other advantages of our model: the compositionality of its latent space and that it provides controlled generation of samples.

For agents

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

get_harvested_code_for_paper("2106.05241")
get_code_for_paper("2106.05241")
have("2106.05241")

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

curl https://syntology.ai/api/ran/2106.05241.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.05241.svg)](https://syntology.ai/paper/2106.05241)

Connect an agent — have() is free.