SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.05795 · NeurIPS · 2023

Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularization

Feng Chen, Russell Hart, Linlin Yu, Yifei Lou

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 3 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/2311.05795.json · badge: /api/ran/2311.05795.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
neoques/graph-posterior-network canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
gaussian_log_prob Ran
ran; our contract draft was wrong, not the code
neoques/graph-posterior-network/gpn/layers/bayesian.py
code served (permissive licence) · get_code("7d8580c54cec1ef4")
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 math

torch.manual_seed(0)

# Create small tensors for the function parameters
# w: weight tensor (batch_size=2, features=4)
w = torch.randn(2, 4)

# mu: mean tensor (batch_size=2, features=4)
mu = torch.randn(2, 4)

# sigma: standard deviation tensor (batch_size=2, features=4)
sigma = torch.abs(torch.randn(2, 4)) + 0.1  # ensure positive values

ARGS = {
    "w": w,
    "mu": mu,
    "sigma": sigma,
}
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
get_df Ran
ran, honoured the contract we drafted
neoques/graph-posterior-network/generate_all_figs.py
code served (permissive licence) · get_code("9d29290e613909a7")
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 DataFrame. 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 os
import tempfile
import json
import yaml
import shutil

# Create a temporary directory structure that mimics ray_results
temp_dir = tempfile.mkdtemp()
ray_results_dir = os.path.join(temp_dir, 'ray_results')
os.makedirs(ray_results_dir)

# Create a trial directory structure
trial_name = 'test_trial'
trial_dir = os.path.join(ray_results_dir, f'experiment_{trial_name}_2024')
os.makedirs(trial_dir)

# Create a trial run subdirectory
run_dir = os.path.join(trial_dir, 'run_1')
os.makedirs(run_dir)

# Create params.json
params = {
    'model': {
        'dist_reg': 0.001,
        'orig_dist_reg': 0.002,
        'KNN_K': 5,
        'dist_sigma': 1.0,
        'dist_embedding_beta': 0.5,
        'activation_type': 'relu',
        'entropy_reg': 0.1,
        'lipschitz_reg': 0.01,
        'lipschitz_init': 0.9
    },
    'data': {
        'dataset': 'cifar10'
    }
}

with open(os.path.join(run_dir, 'params.json'), 'w') as f:
    yaml.dump(params, f)

# Create result.json
results = {
    'val_accuracy': 0.95,
    'test_ood_detection_epistemic_auroc': 0.88,
    'test_accuracy': 0.93
}

with open(os.path.join(run_dir, 'result.json'), 'w') as f:
    yaml.dump(results, f)

# Change to temp directory so relative path works
original_cwd = os.getcwd()
os.chdir(temp_dir)

try:
    ARGS = {
        'trial_name': trial_name
    }
finally:
    os.chdir(original_cwd)
    # Clean up will happen when temp_dir is garbage collected
    # For persistence during execution, we keep it

ARGS = {
    'trial_name': 'test_trial'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
get_sigma Ran
ran; our contract draft was wrong, not the code
neoques/graph-posterior-network/gpn/layers/bayesian.py
code served (permissive licence) · get_code("931b17fe71a65ea4")
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

torch.manual_seed(0)

# Create a small tensor for rho parameter
# The function applies log(1 + exp(rho)) to transform it to sigma
rho = torch.randn(2, 4)

ARGS = {
    "rho": rho
}
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
sample_weight Ran
ran; our contract draft was wrong, not the code
neoques/graph-posterior-network/gpn/layers/bayesian.py
code served (permissive licence) · get_code("78c49071964e5ac2")
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

torch.manual_seed(0)

# Create small tensors for mu and rho
# mu: mean of the weight distribution
# rho: parameter that gets transformed to variance via get_sigma
mu = torch.randn(2, 4)
rho = torch.randn(2, 4)

ARGS = {
    "mu": mu,
    "rho": rho,
}
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 1 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
get_sigma 2 other papers
1 dated earlier, 1 later
2110.14012 (2021-10)
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
2406.04041 (2024-06)
Linear Opinion Pooling for Uncertainty Quantification on Graphs
sample_weight 2 other papers
1 dated earlier, 1 later
2110.14012 (2021-10)
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
2406.04041 (2024-06)
Linear Opinion Pooling for Uncertainty Quantification on Graphs
gaussian_log_prob 1 other paper
1 dated earlier
2110.14012 (2021-10)
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification

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

Deep neural networks have achieved significant success in the last decades, but they are not well-calibrated and often produce unreliable predictions. A large number of literature relies on uncertainty quantification to evaluate the reliability of a learning model, which is particularly important for applications of out-ofdistribution (OOD) detection and misclassification detection. We are interested in uncertainty quantification for interdependent node-level classification. We start our analysis based on graph posterior networks (GPNs) that optimize the uncertainty cross-entropy (UCE)-based loss function. We describe the theoretical limitations of the widely-used UCE loss. To alleviate the identified drawbacks, we propose a distance-based regularization that encourages clustered OOD nodes to remain clustered in the latent space. We conduct extensive comparison experiments on eight standard datasets and demonstrate that the proposed regularization outperforms the state-of-the-art in both OOD detection and misclassification detection.

For agents

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

get_harvested_code_for_paper("2311.05795")
get_code_for_paper("2311.05795")
have("2311.05795")

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

curl https://syntology.ai/api/ran/2311.05795.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.05795.svg)](https://syntology.ai/paper/2311.05795)

Connect an agent — have() is free.