SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.07035 · 2021

Deep Bayesian Unsupervised Lifelong Learning

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 4 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/2106.07035.json · badge: /api/ran/2106.07035.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
KingSpencer/DBULL canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
createFullOutputFileName Ran
ran on a synthesized input
KingSpencer/DBULL/OrganizeResultUtil.py
code served (permissive licence) · get_code("6b74e338a9ff3f18")
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 str. 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 os
import tempfile

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

ARGS = {
    "wholeFolderName": temp_dir,
    "fileName": "output.txt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
createOutputFolderName Ran
ran on a synthesized input
KingSpencer/DBULL/OrganizeResultUtil.py
code served (permissive licence) · get_code("09c8203e4451bc35")
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 str. 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 os
import tempfile

# Create a temporary directory for output
temp_dir = tempfile.mkdtemp()

ARGS = {
    'outputPath': temp_dir,
    'Kmax': 10,
    'dataset': 'cifar10',
    'epoch': 5,
    'batch_iter': 100,
    'scale': 2.0,
    'batchsize': 32,
    'rep': 1,
    'sf': 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_models Ran
ran on a synthesized input
KingSpencer/DBULL/DBULL_dp_gen.py
code served (permissive licence) · get_code("8d6ceeef4ca16578")
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 os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

ARGS = {
    'model_flag': 'dense',
    'batch_size': 2,
    'original_dim': 784,
    'latent_dim': 16,
    'intermediate_dim': [512, 256, 128]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras — 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
get_temp_vade Ran
ran on a synthesized input
KingSpencer/DBULL/DBULL_dp_gen.py
code served (permissive licence) · get_code("8652748318ce9bb6")
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 Functional. 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 os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

import tensorflow as tf
tf.get_logger().setLevel('ERROR')

from keras.layers import Input, Dense, Lambda, Conv2D, Reshape, UpSampling2D, MaxPooling2D, Flatten
from keras.models import Model, load_model
from keras import backend as K

ARGS = {
    'batch_size': 2,
    'original_dim': 8,
    'latent_dim': 4,
    'intermediate_dim': [16, 12, 6]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
load_data Ran
ran on a synthesized input
KingSpencer/DBULL/DBULL_dp_recon.py
code served (permissive licence) · get_code("0294f2b68309f026")
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 dict. 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 os
import sys
import gzip
import tempfile
from six.moves import cPickle
import numpy as np

# Create a temporary directory and a fake mnist.pkl.gz file
temp_dir = tempfile.mkdtemp()
dataset_dir = os.path.join(temp_dir, 'dataset', 'mnist')
os.makedirs(dataset_dir, exist_ok=True)

# Create fake MNIST data
x_train = np.random.rand(100, 28, 28).astype('float32')
y_train = np.random.randint(0, 10, 100)
x_test = np.random.rand(20, 28, 28).astype('float32')
y_test = np.random.randint(0, 10, 20)

# Save as pickle and gzip
pkl_path = os.path.join(dataset_dir, 'mnist.pkl.gz')
with gzip.open(pkl_path, 'wb') as f:
    cPickle.dump(((x_train, y_train), (x_test, y_test)), f)

ARGS = {
    'root_path': temp_dir,
    'flatten': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, six — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_data Ran
ran on a synthesized input
KingSpencer/DBULL/SelectPartialData.py
code served (permissive licence) · get_code("a0b497d77e8da8e1")
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. 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
import os
import tempfile
import gzip
from six.moves import cPickle

# Create a temporary directory for mock dataset
temp_dir = tempfile.mkdtemp()
dataset_dir = os.path.join(temp_dir, 'dataset')
os.makedirs(dataset_dir, exist_ok=True)

# Create mock MNIST data
mnist_dir = os.path.join(dataset_dir, 'mnist')
os.makedirs(mnist_dir, exist_ok=True)

# Generate small dummy MNIST data
x_train = np.random.rand(10, 28, 28).astype('float32')
y_train = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.uint8)
x_test = np.random.rand(5, 28, 28).astype('float32')
y_test = np.array([0, 1, 2, 3, 4], dtype=np.uint8)

# Save as gzipped pickle
mnist_path = os.path.join(mnist_dir, 'mnist.pkl.gz')
with gzip.open(mnist_path, 'wb') as f:
    cPickle.dump(((x_train, y_train), (x_test, y_test)), f)

ARGS = {
    'dataset': 'mnist',
    'root_path': temp_dir,
    'flatten': True,
    'numbers': range(10)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, six — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
obtainDPParam Ran
ran on a synthesized input
KingSpencer/DBULL/GenImageUtil.py
code served (permissive licence) · get_code("9f2c82532a22c14b")
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. 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 numpy as np

torch.manual_seed(0)

# Construct a valid DPParam dictionary
# The function expects keys: 'm', 'B', 'nu', 'kappa'
DPParam = {
    'm': torch.randn(4),  # mean vector
    'B': torch.randn(4, 4),  # covariance/precision matrix
    'nu': 3.5,  # degrees of freedom (scalar)
    'kappa': 2.1  # concentration parameter (scalar)
}

ARGS = {
    'DPParam': DPParam
}
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 — a tuple 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
load_pretrain_online_weights Not yet run
unverified (harvested, no recorded run)
KingSpencer/DBULL/DBULL_dp_recon.py
code served (permissive licence) · get_code("17f367a828b845b6")
How it ran

no invocation recorded.

sampling Not yet run
unverified (harvested, no recorded run)
KingSpencer/DBULL/DBULL_dp.py
code served (permissive licence) · get_code("b60959ebdc07b9a5")
How it ran

no invocation recorded.

sampling Not yet run
unverified (harvested, no recorded run)
KingSpencer/DBULL/DBULL_dp_online_percentage.py
code served (permissive licence) · get_code("7c5003d7f7561fdf")
How it ran

no invocation recorded.

sampling Not yet run
unverified (harvested, no recorded run)
KingSpencer/DBULL/get_mnist_latent.py
code served (permissive licence) · get_code("2eca652b5973f715")
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 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
sampling 2 other papers
2 dated earlier
1312.6114 (2013-12)
Auto-Encoding Variational Bayes
1902.04601 (2019-02)
Contrastive Variational Autoencoder Enhances Salient Features

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

Lifelong Learning (LL) refers to the ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Much attention has been given lately to Supervised Lifelong Learning (SLL) with a stream of labelled data. In contrast, we focus on resolving challenges in Unsupervised Lifelong Learning (ULL) with streaming unlabelled data when the data distribution and the unknown class labels evolve over time. Bayesian framework is natural to incorporate past knowledge and sequentially update the belief with new data. We develop a fully Bayesian inference framework for ULL with a novel end-to-end Deep Bayesian Unsupervised Lifelong Learning (DBULL) algorithm, which can progressively discover new clusters without forgetting the past with unlabelled data while learning latent representations. To efficiently maintain past knowledge, we develop a novel knowledge preservation mechanism via sufficient statistics of the latent representation for raw data. To detect the potential new clusters on the fly, we develop an automatic cluster discovery and redundancy removal strategy in our inference inspired by Nonparametric Bayesian statistics techniques. We demonstrate the effectiveness of our approach using image and text corpora benchmark datasets in both LL and batch settings.

For agents

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

get_harvested_code_for_paper("2106.07035")
get_code_for_paper("2106.07035")
have("2106.07035")

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

curl https://syntology.ai/api/ran/2106.07035.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.07035.svg)](https://syntology.ai/paper/2106.07035)

Connect an agent — have() is free.