SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.13652 · 2024

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 5 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/2409.13652.json · badge: /api/ran/2409.13652.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
stephenqz/oats canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
find_layers Ran
ran; our contract draft was wrong, not the code
stephenqz/oats/OATS/pruning_utils.py
pointer only (licence: NONE) · get_code("14fab8e91e876c60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stephenqz/oats 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.

get_layer0_inputs Ran
ran; our contract draft was wrong, not the code
stephenqz/oats/vit/prune_oats_vit.py
pointer only (licence: NONE) · get_code("62216694a6019cdb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stephenqz/oats 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.

load_checkpoint Ran
ran; our contract draft was wrong, not the code
stephenqz/oats/OATS/pruning_utils.py
pointer only (licence: NONE) · get_code("660047a46e099ddf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stephenqz/oats 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.

map_tensors Ran
ran; our contract draft was wrong, not the code
stephenqz/oats/gpu_utils.py
pointer only (licence: NONE) · get_code("aa35d790b60452f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stephenqz/oats 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.

prepare_dataloader Ran
ran; our contract draft was wrong, not the code
stephenqz/oats/data_utils.py
pointer only (licence: NONE) · get_code("b8bb7d55280d7e8f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stephenqz/oats 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.

get_dataset Not yet run
unverified (harvested, no recorded run)
stephenqz/oats/data_utils.py
pointer only (licence: NONE) · get_code("8e17212c620812e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, stephenqz/oats 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. 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
find_layers 21 other papers
9 dated earlier, 11 later, 1 same year, order not determinable · 5 only as an assembly brick
2306.11695 (2023-06)
A Simple and Effective Pruning Approach for Large Language Models
2310.05175 (2023-10)
Outlier Weighed Layerwise Sparsity (OWL ): A Missing Secret Sauce for Pruning LLMs to High Sparsity
2310.08915 (2023-10)
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
and 18 more not named here

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

The recent paradigm shift to large-scale foundation models has brought about a new era for deep learning that, while has found great success in practice, has also been plagued by prohibitively expensive costs in terms of high memory consumption and compute. To mitigate these issues, there has been a concerted effort in post-hoc neural network pruning techniques that do not require costly retraining. Despite the considerable progress being made, existing methods often exhibit a steady drop in model performance as the compression increases. In this paper, we present a novel approach to compressing large transformers, coined OATS, that utilizes the second moment information in the input embeddings to decompose the model weights into a sum of sparse and low-rank matrices. Without any retraining, OATS achieves state-of-the-art performance when compressing models by up to $60\%$ on large language models such as Llama-3 and Phi-3 and vision transformers such as ViT and DINOv2 while delivering up to $1.37\times$ the CPU acceleration versus a model that was comparably pruned.

For agents

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

get_harvested_code_for_paper("2409.13652")
get_code_for_paper("2409.13652")
have("2409.13652")

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

curl https://syntology.ai/api/ran/2409.13652.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.13652.svg)](https://syntology.ai/paper/2409.13652)

Connect an agent — have() is free.