SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.01524 · 2022

Variational Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 1 has no contract verdict; 2 failures of our instrument; 0 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/2207.01524.json · badge: /api/ran/2207.01524.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
iliiliiliili/vnn-jax-enn canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
iliiliiliili/variational-nn-pytorch canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
iliiliiliili/layer-ensembles-pytorch extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
create_initializer Ran
ran on a synthesized input
iliiliiliili/vnn-jax-enn/enn/networks/vnn.py
code served (permissive licence) · get_code("a4fce2ea92afbddb")
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 list, ndim 2, 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 haiku as hk

ARGS = {
    'names': [
        None,
        'he_uniform',
        'he_normal',
        'glorot_normal',
        'glorot_uniform',
        '1',
        '2'
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
haiku — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
parse_name Ran
ran; our contract draft was wrong, not the code
iliiliiliili/variational-nn-pytorch/tools/create-accuracy-tex-report.py
code served (permissive licence) · get_code("57ce689d6320daf3")
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 list, 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 torch
import torch.nn as nn

# The function parse_name takes a single parameter: name (str)
# It processes the string by:
# 1. Searching for dataset keywords in the name
# 2. Replacing underscores with spaces
# 3. Truncating if name is too long
# 4. Returning a list with [dataset, processed_name]

# Valid test cases for the name parameter
ARGS = {
    'name': 'cifar10_n_test_model_with_long_name_that_might_exceed_the_character_limit_for_truncation'
}
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 list, ndim 1, dtype family float — a list 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
specific_lens_layer Ran
ran; our contract draft was wrong, not the code
iliiliiliili/layer-ensembles-pytorch/networks/layer_ensemble.py
code served (permissive licence) · get_code("7f92c78d35a4518d")
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 as nn
from typing import Any, List, Optional, Literal, Tuple, Union

torch.manual_seed(0)

class LayerEnsembleBase(nn.Module):
    __COLLECTION = []

    def __init__(self) -> None:
        super().__init__()
        LayerEnsembleBase.__COLLECTION.append(self)

    def build(self, ensembles: nn.Module, batch_norm_module: Any, batch_norm_size: int, activation: Optional[nn.Module]=None, use_batch_norm: bool=False, batch_norm_eps: float=0.001, batch_norm_momentum: float=0.01) -> None:
        super().__init__()
        self.ensembles = ensembles
        self.num_ensemble = len(ensembles)
        self.suffix = nn.Identity()
        self.sample = None
        if use_batch_norm:
            self.suffix = nn.Sequential(self.suffix, batch_norm_module(batch_norm_size, eps=batch_norm_eps, momentum=batch_norm_momentum))
        if activation is not None:
            self.suffix = nn.Sequential(self.suffix, activation)

    def forward(self, input, sample=None):
        if sample is None:
            sample = self.sample
        if sample is None:
            raise Exception('No sample provided')
        result = self.ensembles[sample](input)
        result = self.suffix(result)
        self.sample = None
        return result

    @staticmethod
    def collect():
        result = LayerEnsembleBase.__COLLECTION
        LayerEnsembleBase.__COLLECTION = []
        return result


class SimpleEnsemble(nn.Module):
    def __init__(self, num_members: int, input_dim: int = 4, output_dim: int = 3):
        super().__init__()
        self.members = nn.ModuleList([
            nn.Linear(input_dim, output_dim) for _ in range(num_members)
        ])
    
    def __len__(self):
        return len(self.members)
    
    def __getitem__(self, idx):
        return self.members[idx]


def specific_lens_layer(num_ensemble, Layer: LayerEnsembleBase):
    return lambda *args, **kwargs: Layer(num_ensemble, *args, **kwargs)


num_ensemble = 3
ensemble_module = SimpleEnsemble(num_members=num_ensemble, input_dim=4, output_dim=3)

ARGS = {
    "num_ensemble": num_ensemble,
    "Layer": LayerEnsembleBase
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty estimation in neural networks which, instead of considering a distribution over weights, samples outputs of each layer from a corresponding Gaussian distribution, parametrized by the predictions of mean and variance sub-layers. In uncertainty quality estimation experiments, we show that the proposed method achieves better uncertainty quality than other single-bin Bayesian Model Averaging methods, such as Monte Carlo Dropout or Bayes By Backpropagation methods.

For agents

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

get_harvested_code_for_paper("2207.01524")
get_code_for_paper("2207.01524")
have("2207.01524")

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

curl https://syntology.ai/api/ran/2207.01524.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.01524.svg)](https://syntology.ai/paper/2207.01524)

Connect an agent — have() is free.