SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.07710 · ICML · 2024

A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models

Hongyang Zhang, Heng Huang, Zhengmian Hu, Yihan Wu, Junfeng Guo

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 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/2310.07710.json · badge: /api/ran/2310.07710.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
yihwu/dipmark canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
Xieyangxinyu/Unbiased-Watermark-via-Maximal-Coupling community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
group_batch Ran
ran; our contract draft was wrong, not the code
yihwu/dipmark/experiments/common.py
pointer only (licence: NONE) · get_code("fcb42d6d6ae5fede")
How it ran

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

remove_tailing_pad_s Ran
ran; our contract draft was wrong, not the code
yihwu/dipmark/experiments/common.py
pointer only (licence: NONE) · get_code("d17ca30c3cb5a568")
How it ran

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

remove_tailing_pad_s Ran
ran; our contract draft was wrong, not the code
yihwu/dipmark/supplement_experiments/common.py
pointer only (licence: NONE) · get_code("8fce068341c10519")
How it ran

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

tokenize_batch Ran
ran; our contract draft was wrong, not the code
yihwu/dipmark/experiments/common.py
pointer only (licence: NONE) · get_code("f1719e1084c00e31")
How it ran

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

tokenize_batch Ran
ran; our contract draft was wrong, not the code
yihwu/dipmark/supplement_experiments/common.py
pointer only (licence: NONE) · get_code("5d2181f3979041ec")
How it ran

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

DiPMarkGenerator Not yet run
unverified (harvested, no recorded run)
Xieyangxinyu/Unbiased-Watermark-via-Maximal-Coupling/wm/generator.py
code served (permissive licence) · get_code("b20f0d1f63f03397")
How it ran

no invocation recorded.

OpenaiGenerator Not yet run
unverified (harvested, no recorded run)
Xieyangxinyu/Unbiased-Watermark-via-Maximal-Coupling/wm/generator.py
code served (permissive licence) · get_code("1c7ac5cf0a297126")
How it ran

no invocation recorded.

WmGenerator Not yet run
unverified (harvested, no recorded run)
Xieyangxinyu/Unbiased-Watermark-via-Maximal-Coupling/wm/generator.py
code served (permissive licence) · get_code("3e361b18729f8b2b")
How it ran

no invocation recorded.

patch_model Not yet run
unverified (harvested, no recorded run)
yihwu/dipmark/dipmark/monkeypatch.py
pointer only (licence: NONE) · get_code("95a197396b0f2a97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yihwu/dipmark 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 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, 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 7 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
OpenaiGenerator
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2301.10226 (2023-01)
A Watermark for Large Language Models
WmGenerator
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2301.10226 (2023-01)
A Watermark for Large Language Models

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

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original generated content after watermarking. Our research extends and improves upon existing watermarking framework, placing emphasis on the importance of a Distribution-Preserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking (distribution-preserving), is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens (resilient). DiPmark operates by selecting a random set of tokens prior to the generation of a word, then modifying the token distribution through a distribution-preserving reweight function to enhance the probability of these selected tokens during the sampling process. Extensive empirical evaluation on various language models and tasks demonstrates our approach's distribution-preserving property, accessibility, and resilience, making it a effective solution for watermarking tasks that demand impeccable quality preservation. Code is available at 1 .

For agents

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

get_harvested_code_for_paper("2310.07710")
get_code_for_paper("2310.07710")
have("2310.07710")

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

curl https://syntology.ai/api/ran/2310.07710.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.07710.svg)](https://syntology.ai/paper/2310.07710)

Connect an agent — have() is free.