SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.11237 · 2023

Watermarking LLMs with Weight Quantization

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 9 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/2310.11237.json · badge: /api/ran/2310.11237.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
twilight92z/quantize-watermark canonical (classifier label)
classifier basis: census
1 ran · 9 no recorded run
FunctionStatusWhere it lives
get_device_map Ran
ran; our contract draft was wrong, not the code
twilight92z/quantize-watermark/code/param_shift.py
pointer only (licence: NONE) · get_code("3536b543be489008")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

compare Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/param_shift.py
pointer only (licence: NONE) · get_code("2db132a7046c33f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

get_config Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/maintain_fp32/predict.py
pointer only (licence: NONE) · get_code("3bf3a7a0190964e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

get_data Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/sft_data.py
pointer only (licence: NONE) · get_code("53542a9c2ab91d17")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

get_data Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/maintain_fp32/data_processor.py
pointer only (licence: NONE) · get_code("958ef50d9bd77afb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

get_model Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/param_shift.py
pointer only (licence: NONE) · get_code("256a9c18c8b869a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/sft_data.py
pointer only (licence: NONE) · get_code("924af28ba0f50fbf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

quant_online Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/maintain_int8/rollback.py
pointer only (licence: NONE) · get_code("6e7ff7fe47364201")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

tokenize Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/sft_data.py
pointer only (licence: NONE) · get_code("79e4422d6f6bff4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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.

tokenize Not yet run
unverified (harvested, no recorded run)
twilight92z/quantize-watermark/code/maintain_fp32/data_processor.py
pointer only (licence: NONE) · get_code("dd30351922015b11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, twilight92z/quantize-watermark 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, 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 10 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

Abuse of large language models reveals high risks as large language models are being deployed at an astonishing speed. It is important to protect the model weights to avoid malicious usage that violates licenses of open-source large language models. This paper proposes a novel watermarking strategy that plants watermarks in the quantization process of large language models without pre-defined triggers during inference. The watermark works when the model is used in the fp32 mode and remains hidden when the model is quantized to int8, in this way, the users can only inference the model without further supervised fine-tuning of the model. We successfully plant the watermark into open-source large language model weights including GPT-Neo and LLaMA. We hope our proposed method can provide a potential direction for protecting model weights in the era of large language model applications.

For agents

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

get_harvested_code_for_paper("2310.11237")
get_code_for_paper("2310.11237")
have("2310.11237")

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

curl https://syntology.ai/api/ran/2310.11237.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.11237.svg)](https://syntology.ai/paper/2310.11237)

Connect an agent — have() is free.