SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.00611 · NeurIPS · 2023

A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry

Robert Bamler, Weiyang Liu, Tim Xiao

arXiv · PDF · Open in the Atlas

Code that ran

9 of 14 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2401.00611.json · badge: /api/ran/2401.00611.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
timxzz/abi_with_rebasin canonical (classifier label)
classifier basis: census
9 ran · 5 no recorded run
FunctionStatusWhere it lives
agreement Ran
ran, honoured the contract we drafted
timxzz/abi_with_rebasin/metrics.py
pointer only (licence: NONE) · get_code("10b8964e0c906ead")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

construct_config_string Ran
ran; our contract draft was wrong, not the code
timxzz/abi_with_rebasin/MNIST_HMC.py
pointer only (licence: NONE) · get_code("6da2c42649dcb1bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

cost_matrix Ran
ran; our contract draft was wrong, not the code
timxzz/abi_with_rebasin/rebasin.py
pointer only (licence: NONE) · get_code("fe0567580758cd02")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

load_hmc_samples Ran
ran; our contract draft was wrong, not the code
timxzz/abi_with_rebasin/utils.py
pointer only (licence: NONE) · get_code("b74ad0eadfe95127")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

object_to_flatten_dict Ran
ran; our contract draft was wrong, not the code
timxzz/abi_with_rebasin/MNIST_HMC.py
pointer only (licence: NONE) · get_code("3784325e58d559a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

to_numpy Ran
ran, honoured the contract we drafted
timxzz/abi_with_rebasin/MNIST_models.py
pointer only (licence: NONE) · get_code("2efb1c739594d5ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

total_variation_distance Ran
ran, honoured the contract we drafted
timxzz/abi_with_rebasin/metrics.py
pointer only (licence: NONE) · get_code("5567788db47b69bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

train_bnn Ran
ran, honoured the contract we drafted
timxzz/abi_with_rebasin/MNIST_VI.py
pointer only (licence: NONE) · get_code("a930a033d7a52021")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

w2_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
timxzz/abi_with_rebasin/metrics.py
pointer only (licence: NONE) · get_code("570cf6f632bc4a19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

acts_cost_matrix Not yet run
unverified (harvested, no recorded run)
timxzz/abi_with_rebasin/rebasin.py
pointer only (licence: NONE) · get_code("be95ccb8d35d9e3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

closest_permutation_by_activation Not yet run
unverified (harvested, no recorded run)
timxzz/abi_with_rebasin/rebasin.py
pointer only (licence: NONE) · get_code("0c008d33347d27ce")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

load_hmc_hyperparameters Not yet run
unverified (harvested, no recorded run)
timxzz/abi_with_rebasin/MNIST_HMC.py
pointer only (licence: NONE) · get_code("1e4d817efd08ff72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

train Not yet run
unverified (harvested, no recorded run)
timxzz/abi_with_rebasin/MNIST_net_matching.py
pointer only (licence: NONE) · get_code("ec9c68eaf082f7f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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.

train_bnn_step Not yet run
unverified (harvested, no recorded run)
timxzz/abi_with_rebasin/MNIST_VI.py
pointer only (licence: NONE) · get_code("3ac55ecfd1624ca5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, timxzz/abi_with_rebasin 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 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.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Bayesian neural networks (BNNs) are a principled approach to modeling predictive uncertainties in deep learning, which are important in safety-critical applications. Since exact Bayesian inference over the weights in a BNN is intractable, various approximate inference methods exist, among which sampling methods such as Hamiltonian Monte Carlo (HMC) are often considered the gold standard. While HMC provides high-quality samples, it lacks interpretable summary statistics because its sample mean and variance is meaningless in neural networks due to permutation symmetry. In this paper, we first show that the role of permutations can be meaningfully quantified by a number of transpositions metric. We then show that the recently proposed rebasin method [1] allows us to summarize HMC samples into a compact representation that provides a meaningful explicit uncertainty estimate for each weight in a neural network, thus unifying sampling methods with variational inference. We show that this compact representation allows us to compare trained BNNs directly in weight space across sampling methods and variational inference, and to efficiently prune neural networks trained without explicit Bayesian frameworks by exploiting uncertainty estimates from HMC.

For agents

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

get_harvested_code_for_paper("2401.00611")
get_code_for_paper("2401.00611")
have("2401.00611")

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

curl https://syntology.ai/api/ran/2401.00611.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.00611.svg)](https://syntology.ai/paper/2401.00611)

Connect an agent — have() is free.