SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.01050 · 2018

Training VAEs Under Structured Residuals

arXiv · PDF · Open in the Atlas

Code that ran

3 of 9 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 3 have no contract verdict; 0 failures of our instrument; 6 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/1804.01050.json · badge: /api/ran/1804.01050.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
Garoe/tf_mvg community (classifier label)
classifier basis not recorded on the link
3 ran · 6 no recorded run
FunctionStatusWhere it lives
get_np_replicated_identity_matrix Ran
ran on a synthesized input
Garoe/tf_mvg/mvg_distributions/utils/numpy_ops.py
code served (permissive licence) · get_code("b343ad7fac310629")
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, 5) 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 math
import numpy as np
import tensorflow as tf

# Set up arguments for get_np_replicated_identity_matrix
ARGS = {
    "width": 3,
    "height": 5,
    "dtype": tf.float32
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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, 5) — shape (3, 5) 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
get_np_replicated_identity_matrix_with_noise Ran
ran on a synthesized input
Garoe/tf_mvg/mvg_distributions/utils/numpy_ops.py
code served (permissive licence) · get_code("e6182291ac68f012")
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, 5) 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 math
import numpy as np
import tensorflow as tf

ARGS = {
    "width": 3,
    "height": 5,
    "limit": 0.05,
    "dtype": tf.float32
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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, 5) — shape (3, 5) 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
kl_divergence_gaussian Ran
ran on a synthesized input
Garoe/tf_mvg/mvg_distributions/kl_divergence.py
code served (permissive licence) · get_code("ba812715659ccca0")
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 SymbolicTensor. 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
import numpy as np

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

# Create small tensors for testing
batch_size = 2
dim = 4

# mu1: mean of first Gaussian distribution
mu1 = tf.constant(np.random.randn(batch_size, dim).astype(np.float32))

# log_sigma_sq1: log of variance of first Gaussian distribution
log_sigma_sq1 = tf.constant(np.random.randn(batch_size, dim).astype(np.float32))

# mu2: mean of second Gaussian distribution
mu2 = tf.constant(np.random.randn(batch_size, dim).astype(np.float32))

# log_sigma_sq2: log of variance of second Gaussian distribution
log_sigma_sq2 = tf.constant(np.random.randn(batch_size, dim).astype(np.float32))

# mean_batch: whether to return mean over batch dimension
mean_batch = True

# name: scope name for the operation
name = 'kl_divergence_gaussian'

ARGS = {
    'mu1': mu1,
    'log_sigma_sq1': log_sigma_sq1,
    'mu2': mu2,
    'log_sigma_sq2': log_sigma_sq2,
    'mean_batch': mean_batch,
    'name': name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
get_np_gradient_ellipse Not yet run
unverified (harvested, no recorded run)
Garoe/tf_mvg/mvg_distributions/utils/numpy_ops.py
code served (permissive licence) · get_code("ab892725364e45ae")
How it ran

no invocation recorded.

kl_divergence_mv_gaussian Not yet run
unverified (harvested, no recorded run)
Garoe/tf_mvg/mvg_distributions/kl_divergence.py
code served (permissive licence) · get_code("897e6ab02ae26d95")
How it ran

no invocation recorded.

kl_divergence_unit_gaussian Not yet run
unverified (harvested, no recorded run)
Garoe/tf_mvg/mvg_distributions/kl_divergence.py
code served (permissive licence) · get_code("c900f416e0104fc0")
How it ran

no invocation recorded.

neg_log_likelihood_diag_gaussian Not yet run
unverified (harvested, no recorded run)
Garoe/tf_mvg/mvg_distributions/log_likelihoods.py
code served (permissive licence) · get_code("901cea700f6aee66")
How it ran

no invocation recorded.

neg_log_likelihood_mv_gaussian Not yet run
unverified (harvested, no recorded run)
Garoe/tf_mvg/mvg_distributions/log_likelihoods.py
code served (permissive licence) · get_code("8b569e41c60f50c5")
How it ran

no invocation recorded.

squared_error_with_covariance Not yet run
unverified (harvested, no recorded run)
Garoe/tf_mvg/mvg_distributions/log_likelihoods.py
code served (permissive licence) · get_code("5638eb1b070755e9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 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.

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

Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized likelihood model, whereby the output uncertainty of each pixel is assumed to be independent. This approximation is clearly limited as demonstrated by observing a residual image from a VAE reconstruction, which often possess a high level of structure. This paper demonstrates a novel scheme to incorporate a structured Gaussian likelihood prediction network within the VAE that allows the residual correlations to be modeled. Our novel architecture, with minimal increase in complexity, incorporates the covariance matrix prediction within the VAE. We also propose a new mechanism for allowing structured uncertainty on color images. Furthermore, we provide a scheme for effectively training this model, and include some suggestions for improving performance in terms of efficiency or modeling longer range correlations.

For agents

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

get_harvested_code_for_paper("1804.01050")
get_code_for_paper("1804.01050")
have("1804.01050")

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

curl https://syntology.ai/api/ran/1804.01050.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.01050.svg)](https://syntology.ai/paper/1804.01050)

Connect an agent — have() is free.