SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.06291 · 2022

Do Bayesian Neural Networks Need To Be Fully Stochastic?

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 1 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/2211.06291.json · badge: /api/ran/2211.06291.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
MrinankSharma/do_bnns_need_to_be_fully_stochastic canonical (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
Conv2D Ran
ran on a synthesized input · constructed an object; no result was computed
MrinankSharma/do_bnns_need_to_be_fully_stochastic/VI/baselines/cifar/partially_stochastic_models/partially_stochastic_variational_wide_resnet.py
code served (permissive licence) · get_code("2016192a8b36e38a")
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, Conv2D: 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 tensorflow as tf

ARGS = {
    'filters': 32,
    'seed': 42,
}
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 Conv2D — 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 Conv2D 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_nonlinearity_from_string Ran
ran on a synthesized input
MrinankSharma/do_bnns_need_to_be_fully_stochastic/1D_Regression/src/models/bayesian_mlps.py
code served (permissive licence) · get_code("2552b71ce2921337")
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 function. 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.functional as F

torch.manual_seed(0)

# The function takes a string parameter and returns a nonlinearity function
# based on the string value. We need to test one of the valid cases.

ARGS = {
    'non_linearity': 'relu'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
plot_kl_dict Ran
ran on a synthesized input
MrinankSharma/do_bnns_need_to_be_fully_stochastic/1D_Regression/src/plotting/models.py
code served (permissive licence) · get_code("9a8bcdd8ba2aa1f0")
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 module. 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
import matplotlib.pyplot as plt
import seaborn as sns

torch.manual_seed(0)

# Create kl_dict with tensor values
# The function expects a dict where values are tensors with .numel(), .detach(), .cpu(), .numpy()
kl_dict = {
    'layer_1': torch.randn(10),
    'layer_2': torch.randn(8),
    'layer_3': torch.randn(12),
    'empty_layer': torch.tensor([]),  # nonempty_dicts filters this out
}

ARGS = {
    'kl_dict': kl_dict,
    'title': 'KL Divergence Distribution'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, seaborn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
plot_mean Ran
ran on a synthesized input
MrinankSharma/do_bnns_need_to_be_fully_stochastic/1D_Regression/src/plotting/one_d_regression.py
code served (permissive licence) · get_code("40347cf519f666be")
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 module. 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
import numpy as np

torch.manual_seed(0)

# Create a minimal network that satisfies the function's usage
class MinimalNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(1, 1)
        self.device_val = 'cpu'
    
    @property
    def device(self):
        return self.device_val
    
    def forward(self, x, mode='sample'):
        # Returns (mu, something) tuple
        mu = self.linear(x)
        return mu, torch.zeros_like(mu)

network = MinimalNetwork()

# Create a minimal datamodule with the required structure
class MinimalDataset:
    def __init__(self):
        self.X = np.array([[1.0], [2.0], [3.0], [4.0]])
        self.Y = np.array([[2.0], [4.0], [6.0], [8.0]])

class MinimalDataLoader:
    def __init__(self):
        self.dataset = MinimalDataset()
    
    def __iter__(self):
        return iter([])

class MinimalDataModule:
    def __init__(self):
        self._train_loader = MinimalDataLoader()
        self._val_loader = MinimalDataLoader()
        self._test_loader = MinimalDataLoader()
    
    def train_dataloader(self):
        return self._train_loader
    
    def val_dataloader(self):
        return self._val_loader
    
    def test_dataloader(self):
        return self._test_loader

datamodule = MinimalDataModule()

ARGS = {
    'network': network,
    'datamodule': datamodule,
    'n_mc': 3,
    'n_grid': 10,
    'title': 'Test Plot',
    'xlim': (-2.0, 2.0),
    'ylim': (-1.0, 1.0),
    'new_fig': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
deterministic_basic_block Not yet run
unverified (harvested, no recorded run)
MrinankSharma/do_bnns_need_to_be_fully_stochastic/VI/baselines/cifar/partially_stochastic_models/partially_stochastic_variational_wide_resnet.py
code served (permissive licence) · get_code("4767fde16748d4a5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 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.

FunctionAlso present inEarliest-datedOthers named
Conv2D 1 other paper
1 dated earlier
2201.05125 (2022-01)
GradMax: Growing Neural Networks using Gradient Information

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

We investigate the benefit of treating all the parameters in a Bayesian neural network stochastically and find compelling theoretical and empirical evidence that this standard construction may be unnecessary. To this end, we prove that expressive predictive distributions require only small amounts of stochasticity. In particular, partially stochastic networks with only $n$ stochastic biases are universal probabilistic predictors for $n$-dimensional predictive problems. In empirical investigations, we find no systematic benefit of full stochasticity across four different inference modalities and eight datasets; partially stochastic networks can match and sometimes even outperform fully stochastic networks, despite their reduced memory costs.

For agents

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

get_harvested_code_for_paper("2211.06291")
get_code_for_paper("2211.06291")
have("2211.06291")

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

curl https://syntology.ai/api/ran/2211.06291.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.06291.svg)](https://syntology.ai/paper/2211.06291)

Connect an agent — have() is free.