SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.22747 · 2026

Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study

Fabio Cuzzolin, Kaizheng Wang, David Moens, Hans Hallez, Siu Chau, Yunjia Wang

arXiv · PDF · Open in the Atlas

Code that ran

11 of 15 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2602.22747.json · badge: /api/ran/2602.22747.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
DBO-DKFZ/uncertainty-benchmark canonical (classifier label)
classifier basis: census
11 ran · 4 no recorded run
FunctionStatusWhere it lives
apply_loss_heads Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/losses/EnsembleLosses.py
pointer only (licence: NONE) · get_code("02232fdaef3e4fd6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

computeMeanConfidence Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/metrics/metrics.py
pointer only (licence: NONE) · get_code("ff83216de639a533")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

compute_confidence Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/metrics/metrics.py
pointer only (licence: NONE) · get_code("19b084e416e0aaa0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

compute_temperature Ran
ran, honoured the contract we drafted
DBO-DKFZ/uncertainty-benchmark/src/pl_modules/temperature_scaling.py
pointer only (licence: NONE) · get_code("c7e1bbea778a593e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

create_df Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/eval/dataset_statistics.py
pointer only (licence: NONE) · get_code("e6d235606098808b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

eincheck Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DBO-DKFZ/uncertainty-benchmark/src/utils/einop.py
pointer only (licence: NONE) · get_code("e42c3f06c1e0cdb1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

normed_entropy Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/metrics/metrics.py
pointer only (licence: NONE) · get_code("0919a8421f2b0377")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

pairwise_acti_diversity Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DBO-DKFZ/uncertainty-benchmark/src/losses/EnsembleLosses.py
pointer only (licence: NONE) · get_code("0d8cf62d33feee0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

pairwise_weightCos Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DBO-DKFZ/uncertainty-benchmark/src/losses/EnsembleLosses.py
pointer only (licence: NONE) · get_code("17553b4c7ed54bba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

tile_extractor Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/eval/visualizations_base.py
pointer only (licence: NONE) · get_code("3508c2a20764f9bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

transform_batch_outputs Ran
ran; our contract draft was wrong, not the code
DBO-DKFZ/uncertainty-benchmark/src/pl_modules/basemodules.py
pointer only (licence: NONE) · get_code("cb45a2e3e06e2831")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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.

compute_temperature_from_list Not yet run
unverified (harvested, no recorded run)
DBO-DKFZ/uncertainty-benchmark/src/pl_modules/temperature_scaling.py
pointer only (licence: NONE) · get_code("9cc3a958a9a9ee1f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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. No invocation recorded.

create_risk_reject_curve Not yet run
unverified (harvested, no recorded run)
DBO-DKFZ/uncertainty-benchmark/src/eval/plot_functions.py
pointer only (licence: NONE) · get_code("68e62d7ae9aea425")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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. No invocation recorded.

einop Not yet run
unverified (harvested, no recorded run)
DBO-DKFZ/uncertainty-benchmark/src/utils/einop.py
pointer only (licence: NONE) · get_code("08c6e2c32fbaafec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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. No invocation recorded.

rsetattr Not yet run
unverified (harvested, no recorded run)
DBO-DKFZ/uncertainty-benchmark/src/pl_modules/temperature_scaling.py
pointer only (licence: NONE) · get_code("f9de4cdd8a624801")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DBO-DKFZ/uncertainty-benchmark 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 14 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
rsetattr 8 other papers
8 dated earlier
2203.04036 (2022-03)
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
2212.04501 (2022-12)
Learning Video Representations from Large Language Models
2305.13417 (2023-05)
VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers
and 5 more not named here

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

Epistemic uncertainty in neural networks is commonly modeled using two second-order paradigms: distribution-based representations, which rely on posterior parameter distributions, and set-based representations based on credal sets. These frameworks are often regarded as fundamentally noncomparable due to differing semantics, assumptions, and evaluation practices, leaving their relative merits unclear. Empirical comparisons are further confounded by variations in the underlying predictive models. To clarify this issue, we present a controlled comparative study enabling principled, like-for-like evaluation of the two paradigms. Both representations are constructed from the same finite collection of predictive distributions generated by a shared neural network, isolating representational effects from predictive accuracy. Our study evaluates each representation through the lens of 3 uncertainty measures across 14 benchmarks, including selective prediction and out-of-distribution detection, spanning 6 underlying predictive models and 10 independent runs per configuration. Our results show that meaningful comparison between these seemingly non-comparable frameworks is both feasible and informative, providing insights into how second-order representation choices impact practical uncertainty-aware performance.

For agents

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

get_harvested_code_for_paper("2602.22747")
get_code_for_paper("2602.22747")
have("2602.22747")

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

curl https://syntology.ai/api/ran/2602.22747.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.22747.svg)](https://syntology.ai/paper/2602.22747)

Connect an agent — have() is free.