SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16481 · 2022

On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification

arXiv · PDF · Open in the Atlas

Code that ran

14 of 16 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; 2 honoured the contract we drafted, 1 violated it and 7 have no contract verdict; 4 failures of our instrument; 2 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/2203.16481.json · badge: /api/ran/2203.16481.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
activatedgeek/bayesian-classification canonical (classifier label)
classifier basis not recorded on the link
14 ran · 2 no recorded run
FunctionStatusWhere it lives
collect_runs Ran
ran; our contract draft was wrong, not the code
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/notebook_utils.py
code served (permissive licence) · get_code("27e48eb779078e1a")
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 DataFrame. 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 tempfile
import os
import json
from pathlib import Path
import pandas as pd

# Create a temporary directory structure for the function
temp_dir = tempfile.mkdtemp()
base_log_dir = Path(temp_dir)

# Create a couple of run directories with necessary files
run1_dir = base_log_dir / "run_001"
run1_dir.mkdir(exist_ok=True)

run2_dir = base_log_dir / "run_002"
run2_dir.mkdir(exist_ok=True)

# Create config.json for run_001
config1 = {
    "model": {
        "hidden_size": 64,
        "num_layers": 2
    },
    "learning_rate": 0.001,
    "batch_size": 32
}
with open(run1_dir / "config.json", "w") as f:
    json.dump(config1, f)

# Create run.json for run_001
run1 = {
    "epoch": 10,
    "loss": {
        "train": 0.5,
        "val": 0.6
    },
    "accuracy": 0.95
}
with open(run1_dir / "run.json", "w") as f:
    json.dump(run1, f)

# Create metrics.h5 placeholder for run_001
with open(run1_dir / "metrics.h5", "w") as f:
    f.write("")

# Create config.json for run_002
config2 = {
    "model": {
        "hidden_size": 128,
        "num_layers": 3
    },
    "learning_rate": 0.0001,
    "batch_size": 16
}
with open(run2_dir / "config.json", "w") as f:
    json.dump(config2, f)

# Create run.json for run_002
run2 = {
    "epoch": 5,
    "loss": {
        "train": 0.3,
        "val": 0.4
    },
    "accuracy": 0.97
}
with open(run2_dir / "run.json", "w") as f:
    json.dump(run2, f)

# Create metrics.h5 placeholder for run_002
with open(run2_dir / "metrics.h5", "w") as f:
    f.write("")

ARGS = {
    "base_log_dir": str(base_log_dir),
    "metrics_must_exist": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
device Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/exp_utils.py
code served (permissive licence) · get_code("f35c35e0ab818b93")
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, device: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 as t

t.manual_seed(0)

ARGS = {
    'device': 'cpu'
}
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 — 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 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
ewma Ran
ran on a synthesized input
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/plot.py
code served (permissive licence) · get_code("8f08beab287a74d2")
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 1, dtype family float, shape (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 numpy as np
import scipy.signal

# Construct a small array for the ewma function
array = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

# Set alpha parameter (decay factor between 0 and 1)
alpha = 0.3

ARGS = {
    "array": array,
    "alpha": alpha,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (5,) — shape (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
flatten Ran
ran; our contract draft was wrong, not the code
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/notebook_utils.py
code served (permissive licence) · get_code("0529d320cd63ce5a")
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 torch

torch.manual_seed(0)

# The function `flatten` takes a dictionary and recursively flattens nested dicts
# by concatenating keys with dots. It only needs one parameter: in_dict

# Create a nested dictionary structure to test the flatten function
nested_dict = {
    'a': 1,
    'b': 2,
    'c': {
        'd': 3,
        'e': 4,
        'f': {
            'g': 5,
            'h': 6
        }
    },
    'i': 'value',
    'j': {
        'k': [1, 2, 3],
        'l': {'m': 7}
    }
}

ARGS = {
    'in_dict': nested_dict
}
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 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
float_parameter Ran
ran, honoured the contract we drafted
activatedgeek/bayesian-classification/src/data_aug/augmentations.py
code served (permissive licence) · get_code("be1cf2403304fa6d")
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 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 numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - level: a numeric value between 0 and PARAMETER_MAX (appears to be 10 based on division by 10.0)
# - maxval: a numeric value representing the maximum value to scale
# The function returns: float(level) * maxval / 10.0

# Simple test values
level = 5
maxval = 20.0

ARGS = {
    "level": level,
    "maxval": maxval,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
get_cosine_schedule Ran
ran on a synthesized input
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/utils.py
code served (permissive licence) · get_code("212c42ec4fea4835")
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. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T22:17:51Z. 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 math
from typing import Callable

def get_cosine_schedule(samples_per_cycle: int) -> Callable[[int], float]:

    def schedule(i: int) -> float:
        cycle_progress = i % samples_per_cycle / samples_per_cycle
        scale = 0.5 * (math.cos(math.pi * cycle_progress) + 1.0)
        return scale
    return schedule


ARGS = {
    "samples_per_cycle": 100,
}
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 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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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_sizes Ran
ran on a synthesized input
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/plot.py
code served (permissive licence) · get_code("8b17daa681f75fdc")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal model with some parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 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
int_parameter Ran
ran, honoured the contract we drafted
activatedgeek/bayesian-classification/src/data_aug/augmentations.py
code served (permissive licence) · get_code("beaa91443124b324")
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 int, ndim 0, dtype family int, 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 numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - level: an integer between 0 and PARAMETER_MAX (which appears to be 10 based on the division)
# - maxval: a numeric value representing the maximum value to scale

# The function simply scales maxval according to level/10
# No complex objects needed - just numeric values

ARGS = {
    "level": 5,
    "maxval": 100
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
sample_level Ran
ran, violated the contract we drafted
activatedgeek/bayesian-classification/src/data_aug/augmentations.py
code served (permissive licence) · get_code("5cc8d4764ac07a35")
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 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 numpy as np

def sample_level(n):
    return np.random.uniform(low=0.1, high=n)

ARGS = {
    "n": 5
}
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 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
test Ran
ran on a synthesized input
activatedgeek/bayesian-classification/experiments/train_aug_lik.py
code served (permissive licence) · get_code("b13c39f5f6f594b3")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Build a small model that takes input and produces logits
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)  # 4 input features, 3 classes
    
    def forward(self, x):
        return self.linear(x)

# Build a custom criterion that accepts N parameter
class CustomCriterion(nn.Module):
    def forward(self, f_hat, Y, N):
        # Standard cross entropy, but accepts N parameter
        return nn.functional.cross_entropy(f_hat, Y)

# Create data loader: list of (X, Y) tuples
# Batch size 2, 4 features, 3 classes
X1 = torch.randn(2, 4)
Y1 = torch.tensor([0, 1])
X2 = torch.randn(2, 4)
Y2 = torch.tensor([2, 1])
data_loader = [(X1, Y1), (X2, Y2)]

# Create model and criterion
net = SimpleNet()
criterion = CustomCriterion()

# Device (CPU only)
device = 'cpu'

ARGS = {
    'data_loader': data_loader,
    'net': net,
    'criterion': criterion,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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
test_bma Ran
ran on a synthesized input
activatedgeek/bayesian-classification/experiments/train_aug_lik.py
code served (permissive licence) · get_code("12cf4ec8f4c807be")
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 torch
import torch.nn as nn
from pathlib import Path
import tempfile
import os

torch.manual_seed(0)

# Create a simple neural network
class SimpleNet(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super().__init__()
        self.fc1 = nn.Linear(input_dim, 8)
        self.fc2 = nn.Linear(8, num_classes)
    
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

net = SimpleNet(input_dim=4, num_classes=3)

# Create a data loader with small batches
data_loader = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

# Create a temporary directory with sample model weights
samples_dir = tempfile.mkdtemp()
for i in range(2):
    sample_path = os.path.join(samples_dir, f'sample_{i}.pt')
    torch.save(net.state_dict(), sample_path)

# Create NLL criterion
nll_criterion = nn.CrossEntropyLoss(reduction='sum')

# Device
device = 'cpu'

ARGS = {
    'net': net,
    'data_loader': data_loader,
    'samples_dir': samples_dir,
    'nll_criterion': nll_criterion,
    'device': device,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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
train_test_split Ran
ran on a synthesized input
activatedgeek/bayesian-classification/src/data_aug/datasets.py
code served (permissive licence) · get_code("4dbfc79b7cf9df58")
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. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T22:17:51Z. 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.utils.data import Dataset

torch.manual_seed(0)

class SimpleDataset(Dataset):
    def __init__(self, size=10):
        self.size = size
        self.data = torch.randn(size, 4)
        self.labels = torch.randint(0, 2, (size,))
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return self.data[idx], self.labels[idx]

dataset = SimpleDataset(size=10)

ARGS = {
    "dataset": dataset,
    "val_size": 0.2,
    "seed": 42,
}
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 tuple — a tuple output has no array shape of its own; none is stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
unique_cols Ran
ran; our contract draft was wrong, not the code
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/notebook_utils.py
code served (permissive licence) · get_code("34decb89bfa1acc6")
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 pandas as pd
import numpy as np

# Create a minimal DataFrame with some columns
df = pd.DataFrame({
    'col_constant': [1, 1],
    'col_varying': [1, 2],
    'heartbeat': [0, 0],
    'log_dir': ['/path', '/path'],
    'run_id': ['id1', 'id2'],
    'meta.options.param1': [10, 10],
    'meta.options.param2': [20, 30],
    'result.acc_last': [0.9, 0.91],
    'result.loss': [0.1, 0.2],
    'another_varying': ['a', 'b'],
    'another_constant': ['x', 'x'],
})

blacklist = set(['heartbeat', 'log_dir', 'run_id', 'host.cpu', 'host.gpus.driver_version', 'host.hostname', 'host.python_version', 'start_time', 'status', 'stop_time', 'the_dir', 'result.acc_last', 'result.acc_mean', 'result.acc_std', 'result.acc_stderr', 'result.lp_ensemble', 'result.lp_ensemble_std', 'result.lp_ensemble_stderr', 'result.lp_last', 'result.lp_mean', 'result.lp_std', 'result.lp_stderr'])

ARGS = {
    'df': df,
    'blacklist': blacklist,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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
weighted_var_se Ran
ran on a synthesized input
activatedgeek/bayesian-classification/src/bnn_priors/bnn_priors/plot.py
code served (permissive licence) · get_code("3fed205996d7794e")
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 2, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T22:17:51Z. 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 numpy as np

torch.manual_seed(0)

# Create weights: shape (n,)
w = torch.tensor([0.1, 0.2, 0.3, 0.4], dtype=torch.float32)

# Create data x: shape (..., n)
# Using batch shape (2,) so x is (2, 4)
x = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "w": w,
    "x": x,
}
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, ndim 2, 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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
aug Not yet run
unverified (harvested, no recorded run)
activatedgeek/bayesian-classification/src/data_aug/datasets.py
code served (permissive licence) · get_code("f3e585fbf55734ee")
How it ran

no invocation recorded.

prepare_transforms Not yet run
unverified (harvested, no recorded run)
activatedgeek/bayesian-classification/src/data_aug/datasets.py
code served (permissive licence) · get_code("39e9624185b2cc27")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 3 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
float_parameter 19 other papers
12 dated earlier, 7 later · 2 only as an assembly brick
1912.02781 (2019-12)
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
2006.16241 (2020-06)
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
2009.09238 (2020-09)
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
and 16 more not named here
int_parameter 19 other papers
12 dated earlier, 7 later · 2 only as an assembly brick
1912.02781 (2019-12)
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
2006.16241 (2020-06)
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
2009.09238 (2020-09)
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
and 16 more not named here
sample_level 17 other papers
10 dated earlier, 7 later · 3 only as an assembly brick
1912.02781 (2019-12)
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
2006.16241 (2020-06)
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
2009.09238 (2020-09)
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
and 14 more not named here
collect_runs 1 other paper
1 dated earlier
2105.06964 (2021-05)
BNNpriors: A library for Bayesian neural network inference with different prior distributions
device 1 other paper
1 dated earlier
2105.06964 (2021-05)
BNNpriors: A library for Bayesian neural network inference with different prior distributions
flatten 1 other paper
1 dated earlier
2105.06964 (2021-05)
BNNpriors: A library for Bayesian neural network inference with different prior distributions
unique_cols 1 other paper
1 dated earlier
2105.06964 (2021-05)
BNNpriors: A library for Bayesian neural network inference with different prior distributions

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

Aleatoric uncertainty captures the inherent randomness of the data, such as measurement noise. In Bayesian regression, we often use a Gaussian observation model, where we control the level of aleatoric uncertainty with a noise variance parameter. By contrast, for Bayesian classification we use a categorical distribution with no mechanism to represent our beliefs about aleatoric uncertainty. Our work shows that explicitly accounting for aleatoric uncertainty significantly improves the performance of Bayesian neural networks. We note that many standard benchmarks, such as CIFAR, have essentially no aleatoric uncertainty. Moreover, we show data augmentation in approximate inference has the effect of softening the likelihood, leading to underconfidence and profoundly misrepresenting our honest beliefs about aleatoric uncertainty. Accordingly, we find that a cold posterior, tempered by a power greater than one, often more honestly reflects our beliefs about aleatoric uncertainty than no tempering -- providing an explicit link between data augmentation and cold posteriors. We show that we can match or exceed the performance of posterior tempering by using a Dirichlet observation model, where we explicitly control the level of aleatoric uncertainty, without any need for tempering.

For agents

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

get_harvested_code_for_paper("2203.16481")
get_code_for_paper("2203.16481")
have("2203.16481")

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

curl https://syntology.ai/api/ran/2203.16481.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.16481.svg)](https://syntology.ai/paper/2203.16481)

Connect an agent — have() is free.