4 of 4 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; 3 failures of our instrument; 0 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/2410.05451.json · badge: /api/ran/2410.05451.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 |
|---|---|---|
| facebookresearch/secalign | canonical (classifier label) classifier basis: census |
4 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| apply_repetition_penalty | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
facebookresearch/secalign/advprompter/utils.py pointer only (licence: NONE); the stored copy get_code serves, from zhxieml/remiss-jailbreak, is pointer only (licence: NONE) · get_code("298878ca905883f4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, facebookresearch/secalign 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. |
| get_nonascii_toks | Ran ran, honoured the contract we drafted |
facebookresearch/secalign/advprompter/utils.py pointer only (licence: NOASSERTION) · get_code("6ee64cc227326973") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/secalign (NOASSERTION). 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. |
| hit_rate_at_n | Ran ran; our contract draft was wrong, not the code |
facebookresearch/secalign/advprompter/utils.py pointer only (licence: NOASSERTION) · get_code("710027cf3cb03f53") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/secalign (NOASSERTION). 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. |
| jload | Ran ran; our contract draft was wrong, not the code |
facebookresearch/secalign/struq.py pointer only (licence: NOASSERTION) · get_code("331e906ad5e247b9") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/secalign (NOASSERTION). 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| apply_repetition_penalty | 2 other papers 2 dated earlier · 1 only as an assembly brick |
2404.16873 (2024-04) AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs |
2406.14393 (2024-06) Jailbreaking as a Reward Misspecification Problem |
| jload | 2 other papers 2 dated earlier |
2309.00237 (2023-09) Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes |
2402.06363 (2024-02) StruQ: Defending Against Prompt Injection with Structured Queries |
| get_nonascii_toks | 1 other paper 1 dated earlier |
2404.07981 (2024-04) Manipulating Large Language Models to Increase Product Visibility |
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 becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advanced language understanding. To accomplish these tasks, the LLM often uses external data sources such as user documents, web retrieval, results from API calls, etc. This opens up new avenues for attackers to manipulate the LLM via prompt injection. Adversarial prompts can be injected into external data sources to override the system's intended instruction and instead execute a malicious instruction. To mitigate this vulnerability, we propose a new defense called SecAlign based on the technique of preference optimization. Our defense first constructs a preference dataset with prompt-injected inputs, secure outputs (ones that respond to the legitimate instruction), and insecure outputs (ones that respond to the injection). We then perform preference optimization on this dataset to teach the LLM to prefer the secure output over the insecure one. This provides the first known method that reduces the success rates of various prompt injections to <10%, even against attacks much more sophisticated than ones seen during training. This indicates our defense generalizes well against unknown and yet-to-come attacks. Also, SecAlign models are still practical with similar utility to the one before defensive training in our evaluations. Our code is at https://github.com/facebookresearch/SecAlign
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.05451")
get_code_for_paper("2410.05451")
have("2410.05451")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.05451.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.05451)
Connect an agent — have() is free.