SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04825 · EMNLP · 2021

Artificial Text Detection via Examining the Topology of Attention Maps

Evgeny Burnaev, Laida Kushnareva, Dmitri Piontkovski, Irina Piontkovskaya, Daniil Cherniavskii, Ekaterina Artemova, Vladislav Mikhailov, Serguei Barannikov, Alexander Bernstein

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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; 8 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2109.04825.json · badge: /api/ran/2109.04825.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
danchern97/tda4atd marked official in Papers with Code
Papers with Code archive
9 ran · 0 no recorded run
FunctionStatusWhere it lives
barcode_entropy Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("6486319f6396dcb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_mean Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("72a17f917c17d964")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_number Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("a85cfca2bcaa9f99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_number_of_barcodes Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("ece9f4884ba61658")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_pop_inf Ran
ran; our contract draft was wrong, not the code
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("2a3d5f88ec1f40b6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_std Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("ec2164194aa5ef9a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_sum Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("100138690422e928")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

barcode_time Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("b1c33d05c2c4d881")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

count_ripser_features Ran
ran, honoured the contract we drafted
danchern97/tda4atd/ripser_count.py
pointer only (licence: NONE) · get_code("45f088ee843c2b8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, danchern97/tda4atd 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content. Despite the prominent performance of existing methods for artificial text detection, they still lack interpretability and robustness towards unseen models. To this end, we propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) which is currently understudied in the field of NLP. We empirically show that the features derived from the BERT model outperform count-and neural-based baselines up to 10% on three common datasets, and tend to be the most robust towards unseen GPT-style generation models as opposed to existing methods. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties. The results demonstrate that TDA is a promising line with respect to NLP tasks, specifically the ones that incorporate surface and structural information.

For agents

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

get_harvested_code_for_paper("2109.04825")
get_code_for_paper("2109.04825")
have("2109.04825")

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

curl https://syntology.ai/api/ran/2109.04825.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.04825.svg)](https://syntology.ai/paper/2109.04825)

Connect an agent — have() is free.