SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.13692 · 2026

Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection

Yu Wu, Xiao Pu, Xiuli Bi, Lin Yuan, Zepeng Cheng

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 1 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/2604.13692.json · badge: /api/ran/2604.13692.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
PuXiao06/DRGD community
Papers with Code archive
4 ran · 1 no recorded run
FunctionStatusWhere it lives
AdaIn Ran
ran; our contract draft was wrong, not the code
PuXiao06/DRGD/module/model.py
pointer only (licence: NONE) · get_code("deaed503a2106d5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PuXiao06/DRGD 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.

GradientReversalFunction Ran
ran on a synthesized input · constructed an object; no result was computed
PuXiao06/DRGD/module/model.py
pointer only (licence: NONE) · get_code("c8b04dd7c4747a92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PuXiao06/DRGD 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.

IB_Module Ran
ran on a synthesized input · constructed an object; no result was computed
PuXiao06/DRGD/module/model.py
pointer only (licence: NONE) · get_code("64ce5681a66b663c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PuXiao06/DRGD 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.

grad_reverse Ran
ran, honoured the contract we drafted
PuXiao06/DRGD/module/model.py
pointer only (licence: NONE) · get_code("5c9517d15decf27f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PuXiao06/DRGD 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.

BertForAIHumanClassification Not yet run
unverified (harvested, no recorded run)
PuXiao06/DRGD/module/model.py
pointer only (licence: NONE) · get_code("5ffd77157899d8f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PuXiao06/DRGD 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 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.

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

As large language models (LLMs) generate text that increasingly resembles human writing, the subtle cues that distinguish AI-generated content from human-written content become increasingly challenging to capture. Reliance on generator-specific artifacts is inherently unstable, since new models emerge rapidly and reduce the robustness of such shortcuts. This generalizes unseen generators as a central and challenging problem for AI-text detection. To tackle this challenge, we propose a progressively structured framework that disentangles AI-detection semantics from generator-aware artifacts. This is achieved through a compact latent encoding that encourages semantic minimality, followed by perturbation-based regularization to reduce residual entanglement, and finally a discriminative adaptation stage that aligns representations with task objectives. Experiments on MAGE benchmark, covering 20 representative LLMs across 7 categories, demonstrate consistent improvements over state-of-the-art methods, achieving up to 24.2% accuracy gain and 26.2% F 1 improvement. Notably, performance continues to improve as the diversity of training generators increases, confirming strong scalability and generalization in open-set scenarios. Our source code will be publicly available at https://github.com/PuXiao06/DRGD.

For agents

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

get_harvested_code_for_paper("2604.13692")
get_code_for_paper("2604.13692")
have("2604.13692")

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

curl https://syntology.ai/api/ran/2604.13692.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.13692.svg)](https://syntology.ai/paper/2604.13692)

Connect an agent — have() is free.