SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.02037 · 2020

Uncertainty Estimation Using a Single Deep Deterministic Neural Network

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 4 have no contract verdict; 0 failures of our instrument; 3 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/2003.02037.json · badge: /api/ran/2003.02037.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
y0ast/deterministic-uncertainty-quantification canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
get_auroc_ood Ran
ran on a synthesized input
y0ast/deterministic-uncertainty-quantification/utils/evaluate_ood.py
code served (permissive licence) · get_code("edd0ba21eac3f8ac")
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. 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 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
import numpy as np

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.fc(x)

class SimpleDataset(torch.utils.data.Dataset):
    def __init__(self, size=2, input_dim=4, num_classes=3):
        self.size = size
        self.input_dim = input_dim
        self.num_classes = num_classes
        self.transform = None
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        x = torch.randn(self.input_dim)
        y = torch.randint(0, self.num_classes, (1,)).item()
        if self.transform:
            x = self.transform(x)
        return x, y

true_dataset = SimpleDataset(size=2, input_dim=4, num_classes=3)
ood_dataset = SimpleDataset(size=2, input_dim=4, num_classes=3)
model = SimpleModel()

ARGS = {
    'true_dataset': true_dataset,
    'ood_dataset': ood_dataset,
    'model': model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — 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
loop_over_dataloader Ran
ran on a synthesized input
y0ast/deterministic-uncertainty-quantification/utils/evaluate_ood.py
code served (permissive licence) · get_code("7c564eadd854cc48")
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. 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 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
import numpy as np

torch.manual_seed(0)

# Define a minimal model that satisfies the function's usage
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = MinimalModel()

# Create a minimal dataloader (list of (data, target) tuples)
# Batch size 2, input dim 4, num_classes 3
dataloader = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,)))
]

ARGS = {
    "model": model,
    "dataloader": dataloader
}
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 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
prepare_ood_datasets Ran
ran on a synthesized input
y0ast/deterministic-uncertainty-quantification/utils/evaluate_ood.py
code served (permissive licence) · get_code("a59be78abd1c6d34")
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 torch.utils.data as data

torch.manual_seed(0)

# Create minimal dataset classes
class TinyDataset(data.Dataset):
    def __init__(self, size=2, dim=4):
        self.size = size
        self.dim = dim
        self.transform = None
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(self.dim), torch.tensor(0)

class TinyOODDataset(data.Dataset):
    def __init__(self, size=2, dim=4):
        self.size = size
        self.dim = dim
        self.transform = None
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(self.dim), torch.tensor(1)

# Construct the datasets
true_dataset = TinyDataset(size=2, dim=4)
ood_dataset = TinyOODDataset(size=2, dim=4)

# Define the arguments dictionary
ARGS = {
    'true_dataset': true_dataset,
    'ood_dataset': ood_dataset
}
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 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
y0ast/deterministic-uncertainty-quantification/train_deep_ensemble.py
code served (permissive licence) · get_code("d17a6bd8c8316c6e")
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. 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 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

torch.manual_seed(0)

# Create a simple model that takes input and produces class logits
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.linear(x)

# Create multiple models
models = nn.ModuleList([
    SimpleModel(input_dim=4, num_classes=3),
    SimpleModel(input_dim=4, num_classes=3),
])

# Create a simple test loader with 2 batches
# Each batch has 2 samples with 4 features
test_loader = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

# Add dataset length attribute to loader
test_loader_obj = type('TestLoader', (), {
    '__iter__': lambda self: iter(test_loader),
    '__len__': lambda self: 4,
    'dataset': type('Dataset', (), {'__len__': lambda self: 4})()
})()

# Create a loss function that matches the expected signature
# The function calls loss_fn(predictions[i], target, reduction='sum')
def loss_fn(predictions, target, reduction='mean'):
    return nn.functional.cross_entropy(predictions, target, reduction=reduction)

ARGS = {
    'models': models,
    'test_loader': test_loader_obj,
    'loss_fn': loss_fn,
}
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, 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_FashionMNIST Not yet run
unverified (harvested, no recorded run)
y0ast/deterministic-uncertainty-quantification/utils/datasets.py
code served (permissive licence) · get_code("1617e4e7db1c46ac")
How it ran

no invocation recorded.

get_MNIST Not yet run
unverified (harvested, no recorded run)
y0ast/deterministic-uncertainty-quantification/utils/datasets.py
code served (permissive licence) · get_code("f850d3f8ef5fec41")
How it ran

no invocation recorded.

get_SVHN Not yet run
unverified (harvested, no recorded run)
y0ast/deterministic-uncertainty-quantification/utils/datasets.py
code served (permissive licence) · get_code("f1678bdf5e885e9b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model, we improve upon or match Deep Ensembles in out of distribution detection on notable difficult dataset pairs such as FashionMNIST vs. MNIST, and CIFAR-10 vs. SVHN.

For agents

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

get_harvested_code_for_paper("2003.02037")
get_code_for_paper("2003.02037")
have("2003.02037")

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

curl https://syntology.ai/api/ran/2003.02037.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.02037.svg)](https://syntology.ai/paper/2003.02037)

Connect an agent — have() is free.