Jun Sun, Ruihan Zhang
7 of 8 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; 5 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2601.03401.json · badge: /api/ran/2601.03401.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.
| Repository | Role | Ran |
|---|---|---|
| cat-claws/unlearnable | canonical (classifier label) classifier basis: census |
7 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| evaluate | Ran ran, honoured the contract we drafted |
cat-claws/unlearnable/cifar10-retrain.py pointer only (licence: NONE) · get_code("68ae70e88b74a05c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
| extract_embeddings | Ran ran on a synthesized input |
cat-claws/unlearnable/learn-info.py pointer only (licence: NONE) · get_code("67d10fd3e5710c00") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
| f | Ran ran, honoured the contract we drafted |
cat-claws/unlearnable/grad.py pointer only (licence: NONE) · get_code("d1249f7f35b74dfa") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
| grad_loss | Ran ran, honoured the contract we drafted |
cat-claws/unlearnable/cifar10-opposite-1.py pointer only (licence: NONE) · get_code("29aad02efea28c0a") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
| grad_similarity | Ran ran, honoured the contract we drafted |
cat-claws/unlearnable/cifar10-opposite-2.py pointer only (licence: NONE) · get_code("5a8fe9f82311437d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
| info_nce_loss | Ran ran; our contract draft was wrong, not the code |
cat-claws/unlearnable/learn-info.py pointer only (licence: NONE) · get_code("2874718fd7af4eb8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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, honoured the contract we drafted |
cat-claws/unlearnable/cifar10-retrain.py pointer only (licence: NONE) · get_code("84300d44f7c4a28c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
| transforms | Not yet run unverified (harvested, no recorded run) |
cat-claws/unlearnable/hardcoded_transforms.py pointer only (licence: NONE) · get_code("79cf83b9eec0ed68") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, cat-claws/unlearnable 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. |
Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of data protection against unwanted model learning in a realistic blackbox setting. We propose Disclaimer Injection, a novel data-level defence that renders text unlearnable to LLMs. Rather than relying on model-side controls or explicit data removal, our approach exploits the models' own alignment mechanisms: by injecting carefully designed alignment-triggering disclaimers to prevent effective learning. Through layerwise analysis, we find that fine-tuning on such protected data induces persistent activation of alignment-related layers, causing alignment constraints to override task learning even on common inputs. Consequently, models trained on such data exhibit substantial and systematic performance degradation compared to standard fine-tuning. Our results identify alignment behaviour as a previously unexplored lever for data protection and, to our knowledge, present the first practical method for restricting data learnability at LLM scale without requiring access to or modification of the training pipeline. Warning: This paper contains potentially harmful content.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.03401")
get_code_for_paper("2601.03401")
have("2601.03401")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2601.03401.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2601.03401)
Connect an agent — have() is free.