SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.11409 · 2021

On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 1 has no contract verdict; 0 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/2102.11409.json · badge: /api/ran/2102.11409.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
y0ast/DUE canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
initial_values Ran
ran on a synthesized input
y0ast/DUE/due/dkl.py
code served (permissive licence) · get_code("5f1d65960f069d48")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Create a minimal feature extractor that takes an image tensor and outputs features
class SimpleFeatureExtractor(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(3, 16, kernel_size=3, padding=1)
        self.pool = nn.AdaptiveAvgPool2d((2, 2))
        self.flatten = nn.Flatten()
        self.fc = nn.Linear(16 * 2 * 2, 8)
    
    def forward(self, x):
        x = self.conv(x)
        x = self.pool(x)
        x = self.flatten(x)
        x = self.fc(x)
        return x

# Create a minimal dataset
class SimpleDataset:
    def __init__(self, num_samples=100):
        self.num_samples = num_samples
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        # Return (image_tensor, label)
        # Images are 3x4x4 (channels, height, width)
        x = torch.randn(3, 4, 4)
        y = torch.tensor(idx % 2)
        return (x, y)

# Build the arguments
train_dataset = SimpleDataset(num_samples=100)
feature_extractor = SimpleFeatureExtractor()
n_inducing_points = 5

ARGS = {
    "train_dataset": train_dataset,
    "feature_extractor": feature_extractor,
    "n_inducing_points": n_inducing_points,
}
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 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
random_ortho Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from y0ast/DUE
pointer only · get_code("23d31486a37ba535")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
random_ortho 2 other papers
1 dated earlier, 1 later
2006.10108 (2020-06)
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
2305.04933 (2023-05)
Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
initial_values 1 other paper
1 later
2305.04933 (2023-05)
Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial

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

Inducing point Gaussian process approximations are often considered a gold standard in uncertainty estimation since they retain many of the properties of the exact GP and scale to large datasets. A major drawback is that they have difficulty scaling to high dimensional inputs. Deep Kernel Learning (DKL) promises a solution: a deep feature extractor transforms the inputs over which an inducing point Gaussian process is defined. However, DKL has been shown to provide unreliable uncertainty estimates in practice. We study why, and show that with no constraints, the DKL objective pushes "far-away" data points to be mapped to the same features as those of training-set points. With this insight we propose to constrain DKL's feature extractor to approximately preserve distances through a bi-Lipschitz constraint, resulting in a feature space favorable to DKL. We obtain a model, DUE, which demonstrates uncertainty quality outperforming previous DKL and other single forward pass uncertainty methods, while maintaining the speed and accuracy of standard neural networks.

For agents

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

get_harvested_code_for_paper("2102.11409")
get_code_for_paper("2102.11409")
have("2102.11409")

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

curl https://syntology.ai/api/ran/2102.11409.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.11409.svg)](https://syntology.ai/paper/2102.11409)

Connect an agent — have() is free.