SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11175 · ACL · 2024

M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection

Iryna Gurevych, Artem Shelmanov, Alham Fikri, Preslav Nakov, Osama Afzal, Yuxia Wang, Nizar Habash, Akim Tsvigun, Jinyan Su, Jonibek Mansurov, Giovanni Puccetti, Tarek Mahmoud, and 2 more

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 7 failures of our instrument; 2 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/2402.11175.json · badge: /api/ran/2402.11175.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
mbzuai-nlp/m4gt-bench canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
analyze Ran
ran; our contract draft was wrong, not the code
mbzuai-nlp/m4gt-bench/src/GLTR/server.py
pointer only (licence: NONE) · get_code("c3dfa77d1a3ca4e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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_top_k Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mbzuai-nlp/m4gt-bench/src/extract_gltr_features.py
pointer only (licence: NONE) · get_code("c05abc7d4fef8a91")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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_data Ran
ran; our contract draft was wrong, not the code
mbzuai-nlp/m4gt-bench/src/transformer_detector.py
pointer only (licence: NONE) · get_code("3c1eb3db9a05dc2a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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_gltr_features Ran
ran; our contract draft was wrong, not the code
mbzuai-nlp/m4gt-bench/src/gltr_lr.py
pointer only (licence: NONE) · get_code("c15227bbe3011bf3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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.

gltr_payload_to_features Ran
ran, honoured the contract we drafted
mbzuai-nlp/m4gt-bench/src/extract_gltr_features.py
pointer only (licence: NONE) · get_code("d12230a391190b64")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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_function Ran
ran; our contract draft was wrong, not the code
mbzuai-nlp/m4gt-bench/src/transformer_detector.py
pointer only (licence: NONE) · get_code("59853f665d709fd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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.

register_api Ran
ran; our contract draft was wrong, not the code
mbzuai-nlp/m4gt-bench/src/GLTR/backend/class_register.py
pointer only (licence: NONE) · get_code("23dd1413a544be59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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.

train Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mbzuai-nlp/m4gt-bench/src/gltr_lr.py
pointer only (licence: NONE) · get_code("53711ba356067419")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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.

top_k_logits Not yet run
unverified (harvested, no recorded run)
mbzuai-nlp/m4gt-bench/src/GLTR/backend/api.py
pointer only (licence: NONE) · get_code("7be611d6e7fba121")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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.

train Not yet run
unverified (harvested, no recorded run)
mbzuai-nlp/m4gt-bench/src/gltr_svm.py
pointer only (licence: NONE) · get_code("cb4ff66520d69188")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbzuai-nlp/m4gt-bench 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, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 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
analyze 1 other paper
1 dated earlier
1906.04043 (2019-06)
GLTR: Statistical Detection and Visualization of Generated Text
preprocess_function 1 other paper
1 later
2404.14183 (2024-04)
SemEval-2024 Task 8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detection
register_api 1 other paper
1 dated earlier
1906.04043 (2019-06)
GLTR: Statistical Detection and Visualization of Generated Text
top_k_logits 1 other paper
1 dated earlier
1906.04043 (2019-06)
GLTR: Statistical Detection and Visualization of Generated Text

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 advent of Large Language Models (LLMs) has brought an unprecedented surge in machinegenerated text (MGT) across diverse channels. This raises legitimate concerns about its potential misuse and societal implications. The need to identify and differentiate such content from genuine human-generated text is critical in combating disinformation, preserving the integrity of education and scientific fields, and maintaining trust in communication. In this work, we address this problem by introducing a new benchmark based on a multilingual, multidomain, and multi-generator corpus of MGTs -M4GT-Bench. The benchmark is compiled of three tasks: (1) mono-lingual and multi-lingual binary MGT detection; (2) multi-way detection where one need to identify, which particular model generated the text; and (3) mixed humanmachine text detection, where a word boundary delimiting MGT from human-written content should be determined. On the developed benchmark, we have tested several MGT detection baselines and also conducted an evaluation of human performance. We see that obtaining good performance in MGT detection usually requires an access to the training data from the same domain and generators. The benchmark is available at https://github. com/mbzuai-nlp/M4GT-Bench. Source Human Parallel Data Total New test Domain Total= Upsample+ Parallel davinci-003 ChatGPT Cohere Dolly-v2 BLOOMz Machine GPT-4 OUTFOX 16

For agents

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

get_harvested_code_for_paper("2402.11175")
get_code_for_paper("2402.11175")
have("2402.11175")

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

curl https://syntology.ai/api/ran/2402.11175.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11175.svg)](https://syntology.ai/paper/2402.11175)

Connect an agent — have() is free.