Jingzhao Zhang, Tianxing He, Shi Chen, Qingyu Shi, Siyuan Liu, Minrui Luo, Haoming Wen
7 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2606.07970.json · badge: /api/ran/2606.07970.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 |
|---|---|---|
| haomingwen/patcher | canonical (classifier label) classifier basis: census |
7 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| augment_collate_fn | Ran ran; our contract draft was wrong, not the code |
haomingwen/patcher/datasets/utils.py pointer only (licence: NONE) · get_code("a40f0ca59af58f78") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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. |
| evaluate_harmfulness | Ran ran; our contract draft was wrong, not the code |
haomingwen/patcher/evaluate/generate.py pointer only (licence: NONE) · get_code("3543c8662f1fc5db") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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_score | Ran ran, honoured the contract we drafted |
haomingwen/patcher/evaluate/gpt_evaluate.py pointer only (licence: NONE) · get_code("1e9b2b7a8f925a69") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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. |
| inf_collate_fn | Ran ran; our contract draft was wrong, not the code |
haomingwen/patcher/datasets/utils.py pointer only (licence: NONE) · get_code("4ef713909d5b68b2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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. |
| judge_one_pair | Ran ran, honoured the contract we drafted |
haomingwen/patcher/evaluate/gpt_evaluate.py pointer only (licence: NONE) · get_code("88657d79f160e411") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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. |
| make_collate_fn | Ran ran; our contract draft was wrong, not the code |
haomingwen/patcher/datasets/utils.py pointer only (licence: NONE) · get_code("15add638a49d50a2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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. |
| make_collate_fn | Ran ran; our contract draft was wrong, not the code |
haomingwen/patcher/datasets/utils_multiturn.py pointer only (licence: NONE) · get_code("d4ec479d6d805878") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, haomingwen/patcher 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. |
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.
Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with only a few steps of supervised finetuning (SFT) on poisoned datasets. Existing alignment-stage defenses are primarily designed to defend against attacks that use parameter-efficient finetuning methods. However, they fail to defend against stronger attacks that use full-parameter finetuning. In this paper, we propose Patcher, a method inspired by adversarial training and bi-level optimization, to combat such attacks. Patcher strengthens the simulated attack by scaling up the optimization steps in the adversarial loop, thus forcing the defender to find model parameters that are insensitive to stronger attacks. Furthermore, we propose an efficient parallel algorithm to implement Patcher, decreasing the wall-clock time of training while preserving Patcher's performance. Extensive experiments show that Patcher substantially improves the model's robustness compared to vanilla SFT alignment, and transfers to diverse attack scenarios and model sizes. Code is available at https:// github.com/haomingwen/patcher.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2606.07970")
get_code_for_paper("2606.07970")
have("2606.07970")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2606.07970.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2606.07970)
Connect an agent — have() is free.