SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.06160 · NeurIPS · 2024

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?

Subhro Das, Soumya Ghosh, Prasanna Sattigeri, Yuheng Bu, Gregory Wornell, Maohao Shen, J Ryu

arXiv · PDF · Open in the Atlas

Code that ran

6 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 0 have no contract verdict; 6 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/2402.06160.json · badge: /api/ran/2402.06160.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
maohaos2/edl-mirage canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
maohaos2/edl-mirage/src/edl_mirage/posterior_networks/metrics.py
code served (permissive licence) · get_code("f45e658afd35c335")
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 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

torch.manual_seed(0)

# Construct arguments for the accuracy function
# Y: ground truth labels (batch_size,) or (batch_size, 1)
# alpha: model outputs/logits (batch_size, num_classes)

Y = torch.tensor([0, 1], dtype=torch.long)

# alpha should have shape (batch_size, num_classes) with at least 2 classes
# max(-1)[1] gets the argmax class index
alpha = torch.randn(2, 4)

ARGS = {
    "Y": Y,
    "alpha": alpha,
}
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 ndarray, 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
alexnet Ran
ran; our contract draft was wrong, not the code
maohaos2/edl-mirage/src/edl_mirage/architectures/alexnet_sequential.py
pointer only (licence: MIT); the stored copy get_code serves, from mengyuanchen21/re-edl, is pointer only (licence: NONE) · get_code("53ebd0b432c5eaf0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mengyuanchen21/re-edl, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

brier_score Ran
ran; our contract draft was wrong, not the code
maohaos2/edl-mirage/src/edl_mirage/posterior_networks/metrics.py
code served (permissive licence) · get_code("d6163ccad1b08028")
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 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

torch.manual_seed(0)

# Y: ground truth class labels, shape (batch_size,) or (batch_size, 1)
# Should contain class indices that will be used to index into alpha
Y = torch.tensor([[0], [2]])

# alpha: logits or unnormalized probabilities, shape (batch_size, num_classes)
# The function normalizes this and uses it as p
# batch_size should match Y.size(0), num_classes should be > max(Y)
alpha = torch.randn(2, 4)

ARGS = {
    "Y": Y,
    "alpha": alpha,
}
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 ndarray, 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
confidence Ran
ran; our contract draft was wrong, not the code
maohaos2/edl-mirage/src/edl_mirage/posterior_networks/metrics.py
code served (permissive licence) · get_code("9f54021fbf12648a")
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 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
from sklearn import metrics

torch.manual_seed(0)

# Create small tensors for the function
# Y: ground truth labels (batch_size=2, num_classes=4)
Y = torch.tensor([[0], [1]])  # shape (2, 1)

# alpha: logits/unnormalized scores (batch_size=2, num_classes=4)
alpha = torch.tensor([[2.0, 1.0, 0.5, 0.2],
                      [0.1, 3.0, 1.5, 0.3]], dtype=torch.float32)  # shape (2, 4)

ARGS = {
    'Y': Y,
    'alpha': alpha,
    'score_type': 'AUROC',
    'uncertainty_type': 'aleatoric'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sklearn, 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
resnet18 Ran
ran; our contract draft was wrong, not the code
maohaos2/edl-mirage/src/edl_mirage/architectures/resnet_sequential.py
pointer only (licence: MIT); the stored copy get_code serves, from mengyuanchen21/re-edl, is pointer only (licence: NONE) · get_code("8091430f67780266")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mengyuanchen21/re-edl, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resnet18_no_batchnorm Ran
ran; our contract draft was wrong, not the code
maohaos2/edl-mirage/src/edl_mirage/architectures/resnet_sequential.py
code served (permissive licence) · get_code("37c968f01b7af16b")
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 ResNet. 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)

ARGS = {
    "output_dim": 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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 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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
alexnet 3 other papers
2 dated earlier, 1 later
2303.02045 (2023-03)
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
2311.08726 (2023-11)
Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission
2410.00393 (2024-10)
Revisiting Essential and Nonessential Settings of Evidential Deep Learning
resnet18 3 other papers
2 dated earlier, 1 later
2303.02045 (2023-03)
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
2311.08726 (2023-11)
Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission
2410.00393 (2024-10)
Revisiting Essential and Nonessential Settings of Evidential Deep Learning

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

This paper questions the effectiveness of a modern predictive uncertainty quantification approach, called evidential deep learning (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function. Despite their perceived strong empirical performance on downstream tasks, a line of recent studies by Bengs et al. identify limitations of the existing methods to conclude their learned epistemic uncertainties are unreliable, e.g., in that they are non-vanishing even with infinite data. Building on and sharpening such analysis, we 1) provide a sharper understanding of the asymptotic behavior of a wide class of EDL methods by unifying various objective functions; 2) reveal that the EDL methods can be better interpreted as an out-of-distribution detection algorithm based on energy-based-models; and 3) conduct extensive ablation studies to better assess their empirical effectiveness with real-world datasets. Through all these analyses, we conclude that even when EDL methods are empirically effective on downstream tasks, this occurs despite their poor uncertainty quantification capabilities. Our investigation suggests that incorporating model uncertainty can help EDL methods faithfully quantify uncertainties and further improve performance on representative downstream tasks, albeit at the cost of additional computational complexity. 1

For agents

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

get_harvested_code_for_paper("2402.06160")
get_code_for_paper("2402.06160")
have("2402.06160")

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

curl https://syntology.ai/api/ran/2402.06160.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.06160.svg)](https://syntology.ai/paper/2402.06160)

Connect an agent — have() is free.