1 of 7 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; 0 failures of our instrument; 6 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/2407.02855.json · badge: /api/ran/2407.02855.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 |
|---|---|---|
| thu-coai/safeunlearning | canonical (classifier label) classifier basis: census |
1 ran · 6 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| extract_label | Ran ran, honoured the contract we drafted |
thu-coai/safeunlearning/evaluation/score_shieldlm.py pointer only (licence: NONE) · get_code("470eb9f49a78b466") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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. |
| compute_crossentropy_loss | Not yet run unverified (harvested, no recorded run) |
thu-coai/safeunlearning/ft_code/trainers.py pointer only (licence: NONE) · get_code("1c8fe0b0c5d4cdfb") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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. |
| create_ipt | Not yet run unverified (harvested, no recorded run) |
thu-coai/safeunlearning/evaluation/score_shieldlm.py pointer only (licence: NONE) · get_code("0167a92e1796ec51") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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_all_asr | Not yet run unverified (harvested, no recorded run) |
thu-coai/safeunlearning/evaluation/attack_metrics.py pointer only (licence: NONE) · get_code("913ee0ffe96363d5") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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_subbatch_loss | Not yet run unverified (harvested, no recorded run) |
thu-coai/safeunlearning/ft_code/trainers.py pointer only (licence: NONE) · get_code("44d5a6df5684b32b") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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_top5_bleu | Not yet run unverified (harvested, no recorded run) |
thu-coai/safeunlearning/ft_code/construct_training_data.py pointer only (licence: NONE) · get_code("600736770de25e61") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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. |
| parse_query | Not yet run unverified (harvested, no recorded run) |
thu-coai/safeunlearning/evaluation/score_shieldlm.py pointer only (licence: NONE) · get_code("b229552f255f2c73") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-coai/safeunlearning 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 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.
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses that are rooted in the same harmful knowledge (e.g., detailed steps to make a bomb). Consequently, unlearning-based approaches have been proposed to mitigate jailbreak attacks by directly removing harmful knowledge from the model. In this paper, we identify a novel ripple effect of unlearning, wherein LLMs can implicitly unlearn harmful knowledge that was not explicitly introduced during the unlearning phase (e.g., a model unlearning the steps for theft may also implicitly unlearn the steps for making a bomb). Through over 100 experimental runs spanning multiple models, attack strategies, and defense methods, we empirically validate this phenomenon, which makes unlearning-based methods able to decrease the Attack Success Rate on unseen data from more than 70% to less than 10% with only 100 training samples. Further analysis reveals that the strong generalization ability of unlearning may stem from the intrinsic relatedness among harmful responses across harmful questions (e.g., response patterns, shared steps and actions in response, and similarity among their learned representations in the LLM). We also discuss the potential limitations of unlearning and the observed ripple effect. We hope our research could contribute to a deeper understanding of unlearning. Our code is available at https://github.com/thu-coai/SafeUnlearning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.02855")
get_code_for_paper("2407.02855")
have("2407.02855")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2407.02855.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2407.02855)
Connect an agent — have() is free.