SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.01779 · NeurIPS · 2025

Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets

Yuandong Tian

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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, 2 violated it and 1 has no contract verdict; 3 failures of our instrument; 1 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/2410.01779.json · badge: /api/ran/2410.01779.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
facebookresearch/luckmatters canonical (classifier label)
classifier basis: classifier_2025
6 ran · 1 no recorded run
FunctionStatusWhere it lives
ModularAdditionNN Ran
ran on a synthesized input
facebookresearch/luckmatters/ssl/real-dataset/cogo/modular_addition_simple2.py
pointer only (licence: NOASSERTION) · get_code("f4a22fe6c31525cc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

compute_diag_off_diag_avg Ran
ran; our contract draft was wrong, not the code
facebookresearch/luckmatters/ssl/real-dataset/cogo/modular_addition_simple2.py
pointer only (licence: NOASSERTION) · get_code("d3baec476b355c8d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

compute_mps Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/luckmatters/ssl/real-dataset/cogo/draw_dyn_fig3.py
pointer only (licence: NOASSERTION) · get_code("adde72772ab2aebb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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_bases Ran
ran, violated the contract we drafted
facebookresearch/luckmatters/ssl/real-dataset/cogo/analyze_util.py
pointer only (licence: NOASSERTION) · get_code("65dc337d2918e0b7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

fit_diag_11 Ran
ran; our contract draft was wrong, not the code
facebookresearch/luckmatters/ssl/real-dataset/cogo/modular_addition_simple2.py
pointer only (licence: NOASSERTION) · get_code("397c623e247709b3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

modular_addition Ran
ran, violated the contract we drafted
facebookresearch/luckmatters/ssl/real-dataset/cogo/modular_addition_simple2.py
pointer only (licence: NOASSERTION) · get_code("71713a75d37f00c5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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_model_traj Not yet run
unverified (harvested, no recorded run)
facebookresearch/luckmatters/ssl/real-dataset/cogo/analyze_util.py
pointer only (licence: NOASSERTION) · get_code("a78ac335f662ddcd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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, 0 later) and 4 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
compute_diag_off_diag_avg
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2201.12680 (2022-01)
Understanding Deep Contrastive Learning via Coordinate-wise Optimization
fit_diag_11
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2201.12680 (2022-01)
Understanding Deep Contrastive Learning via Coordinate-wise Optimization
modular_addition 1 other paper
1 dated earlier
2201.12680 (2022-01)
Understanding Deep Contrastive Learning via Coordinate-wise Optimization

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

We prove rich algebraic structures of the solution space for 2-layer neural networks with quadratic activation and L 2 loss, trained on reasoning tasks in Abelian group (e.g., modular addition). Such a rich structure enables analytical construction of global optimal solutions from partial solutions that only satisfy part of the loss, despite its high nonlinearity. We coin the framework as CoGS (Composing Global Solutions). Specifically, we show that the weight space over different numbers of hidden nodes of the 2-layer network is equipped with a semi-ring algebraic structure, and the loss function to be optimized consists of sum potentials, which are ring homomorphisms, allowing partial solutions to be composed into global ones by ring addition and multiplication. Our experiments show that around 95% of the solutions obtained by gradient descent match exactly our theoretical constructions. Although the global solutions constructed only required a small number of hidden nodes, our analysis on gradient dynamics shows that overparameterization asymptotically decouples training dynamics and is beneficial. We further show that training dynamics favors simpler solutions under weight decay, and thus high-order global solutions such as perfect memorization are unfavorable. The code is open sourced 1 .

For agents

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

get_harvested_code_for_paper("2410.01779")
get_code_for_paper("2410.01779")
have("2410.01779")

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

curl https://syntology.ai/api/ran/2410.01779.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.01779.svg)](https://syntology.ai/paper/2410.01779)

Connect an agent — have() is free.