SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.10710 · ICLR · 2020

Deeply uncertain: comparing methods of uncertainty quantification in deep learning algorithms

João Caldeira, Brian Nord

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 5 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/2004.10710.json · badge: /api/ran/2004.10710.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
deepskies/DeeplyUncertain-Public canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
heteroscedastic_loss Ran
ran on a synthesized input
deepskies/DeeplyUncertain-Public/models/cd.py
code served (permissive licence) · get_code("830613bbdec4cc81")
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

# Create tiny test tensors
batch_size = 2
n_outputs = 4

# true: shape (batch_size, n_outputs)
true = tf.constant([[1.0, 2.0, 3.0, 4.0],
                    [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

# pred: shape (batch_size, 2*n_outputs) - contains mean and log_var concatenated
# First n_outputs are mean, second n_outputs are log_var
mean_vals = [[0.5, 1.5, 2.5, 3.5],
             [4.5, 5.5, 6.5, 7.5]]
log_var_vals = [[0.1, 0.2, 0.3, 0.4],
                [0.5, 0.6, 0.7, 0.8]]
pred = tf.constant(mean_vals + log_var_vals, dtype=tf.float32)
pred = tf.transpose(pred)
pred = tf.reshape(tf.concat([mean_vals, log_var_vals], axis=1), [batch_size, 2*n_outputs])

ARGS = {
    "true": true,
    "pred": pred
}
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
mse_loss Ran
ran on a synthesized input
deepskies/DeeplyUncertain-Public/models/cd.py
code served (permissive licence) · get_code("2096dc49ec86fdfc")
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 random seeds for reproducibility
tf.random.set_seed(0)
np.random.seed(0)

# Create small test tensors
# true: shape (batch_size, n_outputs) - the ground truth labels
# pred: shape (batch_size, 2*n_outputs) - predictions with mean and variance
batch_size = 2
n_outputs = 4

true = tf.constant(np.random.randn(batch_size, n_outputs), dtype=tf.float32)
pred = tf.constant(np.random.randn(batch_size, 2 * n_outputs), dtype=tf.float32)

ARGS = {
    "true": true,
    "pred": pred,
}
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
negloglik Ran
ran on a synthesized input
deepskies/DeeplyUncertain-Public/models/mlp_tf.py
code served (permissive licence) · get_code("c03137913323b668")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch.distributions as dist

torch.manual_seed(0)

# Create a tiny batch of data
# y_data should be a tensor that can be passed to rv_y.log_prob()
y_data = torch.randn(2, 4)

# Create a random variable (distribution) that has a log_prob method
# Using a Normal distribution as a simple example
# The distribution should be able to compute log_prob for tensors of shape (2, 4)
rv_y = dist.Normal(loc=torch.zeros(2, 4), scale=torch.ones(2, 4))

ARGS = {
    'y_data': y_data,
    'rv_y': rv_y,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
pendulum Ran
ran on a synthesized input
deepskies/DeeplyUncertain-Public/data_gen.py
code served (permissive licence) · get_code("c43201ee46e298b3")
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 2026-09-27T00:55:05Z. 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 numpy as np

ARGS = {
    'n': 10,
    'n_t': 5,
    'g_range': [5, 15],
    'theta_range': [5, 15],
    'ell_range': [0.2, 0.8],
    'm_range': [0.02, 0.1],
    't_spread': [0.03, 0.03],
    'ell_spread': [0.0, 0.0],
    'seed': 42,
}
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 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
scale Ran
ran on a synthesized input
deepskies/DeeplyUncertain-Public/preprocessing.py
code served (permissive licence) · get_code("5bdad93691882744")
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 numpy as np
from sklearn.preprocessing import MinMaxScaler

# Create small numpy arrays for train, val, and test sets
np.random.seed(0)
train_set = np.random.randn(10, 3).astype(np.float32)
val_set = np.random.randn(8, 3).astype(np.float32)
test_set = np.random.randn(6, 3).astype(np.float32)

ARGS = {
    "train_set": train_set,
    "val_set": val_set,
    "test_set": test_set,
    "min_val": 0,
    "max_val": 1,
    "gap": 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
make_model Not yet run
unverified (harvested, no recorded run)
deepskies/DeeplyUncertain-Public/models/cd.py
code served (permissive licence) · get_code("efc992a53400a386")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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 present a comparison of methods for uncertainty quantification (UQ) in deep learning algorithms in the context of a simple physical system. Three of the most common uncertainty quantification methods -Bayesian Neural Networks (BNN), Concrete Dropout (CD), and Deep Ensembles (DE) -are compared to the standard analytic error propagation. We discuss this comparison in terms endemic to both machine learning ("epistemic" and "aleatoric") and the physical sciences ("statistical" and "systematic"). The comparisons are presented in terms of simulated experimental measurements of a single pendulum -a prototypical physical system for studying measurement and analysis techniques. Our results highlight some pitfalls that may occur when using these UQ methods. For example, when the variation of noise in the training set is small, all methods predicted the same relative uncertainty independently of the inputs. This issue is particularly hard to avoid in BNN. On the other hand, when the test set contains samples far from the training distribution, we found that no methods sufficiently increased the uncertainties associated to their predictions. This problem was particularly clear for CD. In light of these results, we make some recommendations for usage and interpretation of UQ methods.

For agents

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

get_harvested_code_for_paper("2004.10710")
get_code_for_paper("2004.10710")
have("2004.10710")

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

curl https://syntology.ai/api/ran/2004.10710.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.10710.svg)](https://syntology.ai/paper/2004.10710)

Connect an agent — have() is free.