SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04019 · ICML · 2021

Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 1 failure of our instrument; 2 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/2105.04019.json · badge: /api/ran/2105.04019.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
Felix-Petersen/diffsort community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
execute_sort Ran
ran; our contract draft was wrong, not the code
Felix-Petersen/diffsort/diffsort/diffsort.py
code served (permissive licence) · get_code("e735ee32bb1d6196")
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. 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 math

torch.manual_seed(0)

# Create a simple sorting network
# Each element is (split_a, split_b, combine_min, combine_max)
# These are used as: x @ split_a.T, x @ split_b.T, etc.
# So they need to be 2D tensors compatible with matrix multiplication

# For vectors of shape (batch, n_features), we need splits of shape (n_features, n_features)
# and combines of shape (n_features, n_features)

n_features = 4
batch_size = 2

# Create simple identity-like projection matrices for the sorting network
split_a = torch.eye(n_features, dtype=torch.float32)
split_b = torch.eye(n_features, dtype=torch.float32)
combine_min = torch.eye(n_features, dtype=torch.float32)
combine_max = torch.eye(n_features, dtype=torch.float32)

sorting_network = [
    (split_a, split_b, combine_min, combine_max)
]

# Create input vectors: shape (batch_size, n_features)
vectors = torch.randn(batch_size, n_features, dtype=torch.float32)

# Create ARGS dictionary with all parameters
ARGS = {
    'sorting_network': sorting_network,
    'vectors': vectors,
    'steepness': 10.0,
    'art_lambda': 0.25,
    'distribution': 'cauchy'
}
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 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
DiffSortNet Not yet run
unverified (harvested, no recorded run)
Felix-Petersen/diffsort/diffsort/diffsort.py
code served (permissive licence) · get_code("e17aeedc0dff9e6d")
How it ran

no invocation recorded.

sort Not yet run
unverified (harvested, no recorded run)
Felix-Petersen/diffsort/diffsort/diffsort.py
code served (permissive licence) · get_code("2247099fccb85f17")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints. That is, the ground truth order of sets of samples is known, while their absolute values remain unsupervised. For that, we propose differentiable sorting networks by relaxing their pairwise conditional swap operations. To address the problems of vanishing gradients and extensive blurring that arise with larger numbers of layers, we propose mapping activations to regions with moderate gradients. We consider odd-even as well as bitonic sorting networks, which outperform existing relaxations of the sorting operation. We show that bitonic sorting networks can achieve stable training on large input sets of up to 1024 elements.

For agents

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

get_harvested_code_for_paper("2105.04019")
get_code_for_paper("2105.04019")
have("2105.04019")

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

curl https://syntology.ai/api/ran/2105.04019.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.04019.svg)](https://syntology.ai/paper/2105.04019)

Connect an agent — have() is free.