SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2511.05064 · NeurIPS · 2025

Order-Level Attention Similarity Across Language Models: A Latent Commonality

Hanlin Gu, Lixin Fan, Jinglin Liang, Jin Zhong, Shuangping Huang, Yunqing Hu, Huiyuan Zhang, Huifang Li

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 4 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/2511.05064.json · badge: /api/ran/2511.05064.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
jinglin-liang/OLAS canonical (classifier label)
classifier basis: census
12 ran · 4 no recorded run
FunctionStatusWhere it lives
cal_dp_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jinglin-liang/OLAS/models/ola_model.py
pointer only (licence: NONE) · get_code("93ba74ac3c903901")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

combine_attention_orders Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/models/ola_utils.py
pointer only (licence: NONE) · get_code("ad5b8493137884f1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/convs/resnet.py
pointer only (licence: NONE) · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/convs/modified_represnet.py
pointer only (licence: NONE); the stored copy get_code serves, from sajaddarabi/BiRealNet, is pointer only (licence: NONE) · get_code("d5cd7ffe2dc51b21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/convs/resnet.py
pointer only (licence: NONE) · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/convs/resnet_cbam.py
pointer only (licence: NONE); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/convs/modified_represnet.py
pointer only (licence: NONE) · get_code("1907f2ae25449f39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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_interested_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jinglin-liang/OLAS/models/ola_utils.py
pointer only (licence: NONE) · get_code("7d7d7520c89b7a9f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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_outliers_mask Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/models/ola_utils.py
pointer only (licence: NONE) · get_code("6bc8fcce934a8ab0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

is_causal_lm Ran
ran, violated the contract we drafted
jinglin-liang/OLAS/models/ola_model.py
pointer only (licence: NONE) · get_code("abec4c7afc0e1c8f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

preprocess_ola Ran
ran, honoured the contract we drafted
jinglin-liang/OLAS/models/ola_model.py
pointer only (licence: NONE) · get_code("9a210759d5a7dd98")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

resnet18_rep Ran
ran; our contract draft was wrong, not the code
jinglin-liang/OLAS/convs/modified_represnet.py
pointer only (licence: NONE) · get_code("ecaa7ca05d715804")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

resnet18 Not yet run
unverified (harvested, no recorded run)
jinglin-liang/OLAS/convs/resnet.py
pointer only (licence: NONE) · get_code("8eb956355f7c42ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

resnet18 Not yet run
unverified (harvested, no recorded run)
jinglin-liang/OLAS/convs/ucir_resnet.py
pointer only (licence: NONE) · get_code("4742faeabce1f66b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

resnet18_cbam Not yet run
unverified (harvested, no recorded run)
jinglin-liang/OLAS/convs/resnet_cbam.py
pointer only (licence: NONE) · get_code("9d7277889d69cf2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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.

resnet34_cbam Not yet run
unverified (harvested, no recorded run)
jinglin-liang/OLAS/convs/resnet_cbam.py
pointer only (licence: NONE) · get_code("9eb3d43ee2e8ae7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jinglin-liang/OLAS 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 2 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
669 dated earlier, 13 later, 4 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
conv1x1 431 other papers
411 dated earlier, 1 the same month, 13 later, 5 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
297 dated earlier, 1 the same month, 9 later, 4 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
88 dated earlier, 4 later, 2 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
conv3x3 74 other papers
70 dated earlier, 3 later, 1 same year, order not determinable · 5 only as an assembly brick
1605.07146 (2016-05)
Wide Residual Networks
1707.01629 (2017-07)
Dual Path Networks
1802.05668 (2018-02)
Model compression via distillation and quantization
and 71 more not named here
resnet34_cbam 11 other papers
11 dated earlier
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
aaai_29079 (2024 (year only))
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
and 8 more not named here
resnet18_cbam 10 other papers
10 dated earlier
2308.09297 (2023-08)
NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
and 7 more not named here
conv1x1 9 other papers
9 dated earlier
1808.00278 (2018-08)
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
1812.11800 (2018-12)
Regularized Binary Network Training
2108.05722 (2021-08)
MT-ORL: Multi-Task Occlusion Relationship Learning
and 6 more not named here
resnet18_rep 6 other papers
6 dated earlier
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
aaai_29079 (2024 (year only))
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
2403.14101 (2024-03)
Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
and 3 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

In this paper, we explore an important yet previously neglected question: Do context aggregation patterns across Language Models (LMs) share commonalities? While some works have investigated context aggregation or attention weights in LMs, they typically focus on individual models or attention heads, lacking a systematic analysis across multiple LMs to explore their commonalities. In contrast, we focus on the commonalities among LMs, which can deepen our understanding of LMs and even facilitate cross-model knowledge transfer. In this work, we introduce the Order-Level Attention (OLA) derived from the order-wise decomposition of Attention Rollout and reveal that the OLA at the same order across LMs exhibits significant similarities. Furthermore, we discover an implicit mapping between OLA and syntactic knowledge. Based on these two findings, we propose the Transferable OLA Adapter (TOA), a training-free cross-LM adapter transfer method. Specifically, we treat the OLA as a unified syntactic feature representation and train an adapter that takes OLA as input. Due to the similarities in OLA across LMs, the adapter generalizes to unseen LMs without requiring any parameter updates. Extensive experiments demonstrate that TOA's cross-LM generalization effectively enhances the performance of unseen LMs. Code is available at https://github.com/jinglin-liang/OLAS.

For agents

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

get_harvested_code_for_paper("2511.05064")
get_code_for_paper("2511.05064")
have("2511.05064")

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

curl https://syntology.ai/api/ran/2511.05064.json

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

[![Syntology run record](https://syntology.ai/api/ran/2511.05064.svg)](https://syntology.ai/paper/2511.05064)

Connect an agent — have() is free.