SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.12948 · ACL · 2024

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick

Ruihan Yang, Yanghua Xiao, Xuandong Zhao, Jiangjie Chen, Yuansen Zhang, Jiayi Fu

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 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/2402.12948.json · badge: /api/ran/2402.12948.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
poruna-byte/gumbelsoft marked official in Papers with Code
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
Generator Ran
ran on a synthesized input · constructed an object; no result was computed
poruna-byte/gumbelsoft/wm/generator.py
pointer only (licence: NONE) · get_code("48e0b3c3783fa33d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, poruna-byte/gumbelsoft 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.

GumbelSoftGeneratorNg Ran
ran on a synthesized input · constructed an object; no result was computed
poruna-byte/gumbelsoft/wm/generator.py
pointer only (licence: NONE) · get_code("12fa3bba58f31fb6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, poruna-byte/gumbelsoft 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.

NgramWmGenerator Ran
ran on a synthesized input · constructed an object; no result was computed
poruna-byte/gumbelsoft/wm/generator.py
pointer only (licence: NONE) · get_code("04313094e52efa19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, poruna-byte/gumbelsoft 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.

inv_gumbel_cdf Ran
ran; our contract draft was wrong, not the code
poruna-byte/gumbelsoft/wm/generator.py
pointer only (licence: NONE) · get_code("f09a4fdd0361cc5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, poruna-byte/gumbelsoft 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark (GM watermark), is a standout solution for safeguarding machine-generated texts due to its notable detectability. However, GM watermark encounters a major challenge with generation diversity, always yielding identical outputs for the same prompt, negatively impacting generation diversity and user experience. To overcome this limitation, we propose a new type of GM watermark, the Logits-Addition watermark, and its three variants, specifically designed to enhance diversity. Among these, the GumbelSoft watermark (a softmax variant of the Logits-Addition watermark) demonstrates superior performance in high diversity settings, with its AUROC score outperforming those of the two alternative variants by 0.1 to 0.3 and surpassing other decoding-based watermarking methods by a minimum of 0.1. 1 * Corresponding author. 1 Code is available at https://github.com/ PorUna-byte/Gumbelsoft Fixed Decoder function ❄ ➕ Fixed Pseudo-random function ❄ Γ F sk … Watermarked LLM User Multiple conversations between Watermarked LLM and User Reason for the Repetition Possible Solutions Nth conversation Kyoto, Shanghai, Istanbul Recommend three cities suitable for vacation Kyoto, Shanghai, Istanbul Recommend three cities suitable for vacation 1st conversation • Add uncertainty to the Decoder function: 1. Drop the watermark with a predefined probability 2. Replace the 'argmax' with 'sample from softmax' • Add uncertainty to the Pseudo-random function: 3. Randomly modify(cyclically shift) watermark key Repeated response from LLMs!

For agents

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

get_harvested_code_for_paper("2402.12948")
get_code_for_paper("2402.12948")
have("2402.12948")

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

curl https://syntology.ai/api/ran/2402.12948.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.12948.svg)](https://syntology.ai/paper/2402.12948)

Connect an agent — have() is free.