SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.07800 · 2026

Approximating Matrix Functions with Deep Neural Networks and Transformers

Simone Brugiapaglia, Rahul Padmanabhan

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2602.07800.json · badge: /api/ran/2602.07800.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
rahul3/LAWT canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
FunctionStatusWhere it lives
Embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) · constructed an object; no result was computed
rahul3/LAWT/src/model/transformer.py
pointer only (licence: NONE) · get_code("a3e27bd1e8b628ed")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rahul3/LAWT when it was checked. 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.

bool_flag Ran
ran, violated the contract we drafted
rahul3/LAWT/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from cisnlp/ofa, is pointer only (licence: NONE) · get_code("cc66d68d2046d6a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rahul3/LAWT when it was checked. 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.

create_logger Ran
ran; our contract draft was wrong, not the code
rahul3/LAWT/src/logger.py
pointer only (licence: NOASSERTION) · get_code("2f7db44ecae76417")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

generate_wigner_matrices Ran
ran, honoured the contract we drafted
rahul3/LAWT/src/envs/generators.py
pointer only (licence: NOASSERTION) · get_code("38b1e59f26ffe6c5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

get_logger Ran
ran; our contract draft was wrong, not the code
rahul3/LAWT/src/neuralnet/common.py
pointer only (licence: NOASSERTION) · get_code("122fce61b2b8891b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

get_masks Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rahul3/LAWT/src/model/transformer.py
pointer only (licence: NONE) · get_code("b2470f4f0c09db41")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rahul3/LAWT when it was checked. 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.

idx_to_infix Ran
ran; our contract draft was wrong, not the code
rahul3/LAWT/src/evaluator.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/gcd, is pointer only (licence: NOASSERTION) · get_code("cb6c41af2e200c64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rahul3/LAWT when it was checked. 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.

log_loss Ran
ran, honoured the contract we drafted
rahul3/LAWT/src/neuralnet/common.py
pointer only (licence: NOASSERTION) · get_code("21772223de978a2d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

timeout Ran
ran; our contract draft was wrong, not the code
rahul3/LAWT/src/utils.py
pointer only (licence: NOASSERTION) · get_code("e7b55aa114a5156a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

check_hypothesis Not yet run
unverified (harvested, no recorded run)
rahul3/LAWT/src/evaluator.py
pointer only (licence: NOASSERTION) · get_code("cc07a1ed781ef988")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

get_optimizer Not yet run
unverified (harvested, no recorded run)
rahul3/LAWT/src/optim.py
pointer only (licence: NOASSERTION) · get_code("d4552faa79e349b3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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.

initialize_exp Not yet run
unverified (harvested, no recorded run)
rahul3/LAWT/src/utils.py
pointer only (licence: NOASSERTION) · get_code("c4d4b0ccb9f71797")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, rahul3/LAWT (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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
Embedding 18 other papers
18 dated earlier · 3 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1905.12790 (2019-05)
A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
1911.02116 (2019-11)
Unsupervised Cross-lingual Representation Learning at Scale
and 15 more not named here
get_masks 8 other papers
8 dated earlier · 1 only as an assembly brick
1911.02116 (2019-11)
Unsupervised Cross-lingual Representation Learning at Scale
2010.03017 (2020-10)
On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
2110.03501 (2021-10)
Pretrained Language Models are Symbolic Mathematics Solvers too!
and 5 more not named here
bool_flag 5 other papers
5 dated earlier
1911.02116 (2019-11)
Unsupervised Cross-lingual Representation Learning at Scale
2110.03501 (2021-10)
Pretrained Language Models are Symbolic Mathematics Solvers too!
2311.08849 (2023-11)
OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
and 2 more not named here
create_logger 4 other papers
4 dated earlier
2110.03501 (2021-10)
Pretrained Language Models are Symbolic Mathematics Solvers too!
2210.03403 (2022-10)
TAN Without a Burn: Scaling Laws of DP-SGD
2404.11341 (2024-04)
The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology
and 1 more not named here
timeout 3 other papers
3 dated earlier
2110.03501 (2021-10)
Pretrained Language Models are Symbolic Mathematics Solvers too!
2207.03578 (2022-07)
Code Translation with Compiler Representations
2411.00566 (2024-11)
PatternBoost: Constructions in Mathematics with a Little Help from AI
idx_to_infix 1 other paper
1 dated earlier
2308.15594 (2023-08)
Learning the greatest common divisor: explaining transformer predictions
initialize_exp 1 other paper
1 dated earlier
2110.03501 (2021-10)
Pretrained Language Models are Symbolic Mathematics Solvers too!

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

Transformers have revolutionized natural language processing, but their use for numerical computation has received less attention. We study the approximation of matrix functions, which map scalar functions to matrices, using neural networks including transformers. We focus on functions mapping square matrices to square matrices of the same dimension. These types of matrix functions appear throughout scientific computing, e.g., the matrix exponential in continuous-time Markov chains and the matrix sign function in stability analysis of dynamical systems. In this paper, we make two contributions. First, we prove bounds on the width and depth of ReLU networks needed to approximate the matrix exponential to an arbitrary precision. Second, we show experimentally that a transformer encoder-decoder with suitable numerical encodings can approximate certain matrix functions at a relative error of 5% with high probability. Our study reveals that the encoding scheme strongly affects performance, with different schemes working better for different functions.

For agents

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

get_harvested_code_for_paper("2602.07800")
get_code_for_paper("2602.07800")
have("2602.07800")

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

curl https://syntology.ai/api/ran/2602.07800.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.07800.svg)](https://syntology.ai/paper/2602.07800)

Connect an agent — have() is free.