SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.20449 · 2026

Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference

Chi Han, Jeonghwan Kim, Heng Ji, Huimin Zhao, Anna Hart

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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, 0 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/2602.20449.json · badge: /api/ran/2602.20449.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
ahart34/protein canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
ascii_encode_2000 Ran
ran, honoured the contract we drafted
ahart34/protein/early_exit/script/evaluation_runner.py
pointer only (licence: NONE) · get_code("9469003bfd837465")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

detect_variables Ran
ran; our contract draft was wrong, not the code
ahart34/protein/early_exit/util.py
pointer only (licence: NONE) · get_code("eab8b6a6ced6d93e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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_root_logger Ran
ran; our contract draft was wrong, not the code
ahart34/protein/early_exit/util.py
pointer only (licence: NONE) · get_code("70a68fd646c6e4a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

has_nans Ran
ran; our contract draft was wrong, not the code
ahart34/protein/early_exit/script/file_preview.py
pointer only (licence: NONE) · get_code("373d8941e92a806b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

infer_k_from_target_column Ran
ran; our contract draft was wrong, not the code
ahart34/protein/early_exit/script/file_preview_2.py
pointer only (licence: NONE) · get_code("f12d90ada9ba406f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

nanmean_compat Ran
ran; our contract draft was wrong, not the code
ahart34/protein/early_exit/script/file_preview.py
pointer only (licence: NONE) · get_code("fd321785071e233c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

nanmin_compat Ran
ran; our contract draft was wrong, not the code
ahart34/protein/early_exit/script/file_preview.py
pointer only (licence: NONE) · get_code("3a9d3aea89fcc071")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

excess_aurc_per_layer_cl Not yet run
unverified (harvested, no recorded run)
ahart34/protein/early_exit/script/evaluate_confidence.py
pointer only (licence: NONE) · get_code("db100fb0bd99c8fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

excess_aurc_per_layer_loss_derived Not yet run
unverified (harvested, no recorded run)
ahart34/protein/early_exit/script/evaluate_confidence.py
pointer only (licence: NONE) · get_code("8c577a427a01b148")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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.

load_confidence_data Not yet run
unverified (harvested, no recorded run)
ahart34/protein/early_exit/script/plot_confidence.py
pointer only (licence: NONE) · get_code("d10eb536d0ba8913")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahart34/protein 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
get_root_logger 8 other papers
8 dated earlier
2106.06935 (2021-06)
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
2205.10128 (2022-05)
Neural-Symbolic Models for Logical Queries on Knowledge Graphs
2206.04798 (2022-06)
A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
and 5 more not named here
detect_variables 7 other papers
7 dated earlier
2106.06935 (2021-06)
Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
2205.10128 (2022-05)
Neural-Symbolic Models for Logical Queries on Knowledge Graphs
2302.02209 (2023-02)
A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
and 4 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

Modern Protein Language Models (PLMs) apply transformer-based model architectures from natural language processing to biological sequences, predicting a variety of protein functions and properties. However, protein language has key differences from natural language, such as a rich functional space despite a vocabulary of only 20 amino acids. These differences motivate research into how transformer-based architectures operate differently in the protein domain and how we can better leverage PLMs to solve protein-related tasks. In this work, we begin by directly comparing how the distribution of information stored across layers of attention heads differs between the protein and natural language domain. Furthermore, we adapt a simple early-exit technique-originally used in the natural language domain to improve efficiency at the cost of performance-to achieve both increased accuracy and substantial efficiency gains in protein non-structural property prediction by allowing the model to automatically select protein representations from the intermediate layers of the PLMs for the specific task and protein at hand. We achieve performance gains ranging from 0.4 to 7.01 percentage points while simultaneously improving efficiency by over 10% across models and non-structural prediction tasks. Our work opens up an area of research directly comparing how language models change behavior when moved into the protein domain and advances language modeling in biological domains. Code is available at https://github.com/ahart34/protein with instructions on downloading data.

For agents

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

get_harvested_code_for_paper("2602.20449")
get_code_for_paper("2602.20449")
have("2602.20449")

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

curl https://syntology.ai/api/ran/2602.20449.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.20449.svg)](https://syntology.ai/paper/2602.20449)

Connect an agent — have() is free.