SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.08665 · 2018

Learning Latent Permutations with Gumbel-Sinkhorn Networks

arXiv · PDF · Open in the Atlas

Code that ran

None of the 6 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (6 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/1802.08665.json · badge: /api/ran/1802.08665.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
google/gumbel_sinkhorn canonical (classifier label)
classifier basis: census
0 ran · 6 no recorded run
FunctionStatusWhere it lives
kendall_tau Not yet run
unverified (harvested, no recorded run)
google/gumbel_sinkhorn/sinkhorn_ops.py
code served (permissive licence) · get_code("0333e85f0ad554ad")
How it ran

no invocation recorded.

matching Not yet run
unverified (harvested, no recorded run)
google/gumbel_sinkhorn/sinkhorn_ops.py
code served (permissive licence) · get_code("3f1ab6103613b1de")
How it ran

no invocation recorded.

restore_checkpoint_if_exists Not yet run
unverified (harvested, no recorded run)
google/gumbel_sinkhorn/sorting/sorting_eval.py
code served (permissive licence) · get_code("b1d6f8bcfaec6f24")
How it ran

no invocation recorded.

sample_gumbel Not yet run
unverified (harvested, no recorded run)
google/gumbel_sinkhorn/sinkhorn_ops.py
code served (permissive licence) · get_code("f4b5cb2c941d138e")
How it ran

no invocation recorded.

set_optimizer Not yet run
unverified (harvested, no recorded run)
google/gumbel_sinkhorn/optimizer.py
code served (permissive licence) · get_code("a66e302bfd882730")
How it ran

no invocation recorded.

wait_for_new_checkpoint Not yet run
unverified (harvested, no recorded run)
google/gumbel_sinkhorn/sorting/sorting_eval.py
code served (permissive licence) · get_code("e3783afe5ced98c5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn iteration is attractive because it functions as a simple, easy-to-implement analog of the softmax operator. With this, we can define the Gumbel-Sinkhorn method, an extension of the Gumbel-Softmax method (Jang et al. 2016, Maddison2016 et al. 2016) to distributions over latent matchings. We demonstrate the effectiveness of our method by outperforming competitive baselines on a range of qualitatively different tasks: sorting numbers, solving jigsaw puzzles, and identifying neural signals in worms.

For agents

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

get_harvested_code_for_paper("1802.08665")
get_code_for_paper("1802.08665")
have("1802.08665")

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

curl https://syntology.ai/api/ran/1802.08665.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.08665.svg)](https://syntology.ai/paper/1802.08665)

Connect an agent — have() is free.