Vladimir Ivanov, Richard Moulange, Arturs Kanepajs
2 of 3 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, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 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/2409.13708.json · badge: /api/ran/2409.13708.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 |
|---|---|---|
| akanepajs/multilingual | canonical (classifier label) classifier basis: classifier_2025 |
2 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| json_load | Ran ran; our contract draft was wrong, not the code |
akanepajs/multilingual/chatbot.py pointer only (licence: NONE) · get_code("0743da3de5e334af") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, akanepajs/multilingual 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. |
| wilson_score_interval | Ran ran, violated the contract we drafted |
akanepajs/multilingual/multilingual.py pointer only (licence: NONE) · get_code("771a5ef803a71b0d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, akanepajs/multilingual 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. |
| await_all | Not yet run unverified (harvested, no recorded run) |
akanepajs/multilingual/chatbot.py pointer only (licence: NONE) · get_code("ad2cda0456c2095d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, akanepajs/multilingual 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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.
Linguistically inclusive LLMs-which maintain good performance regardless of the language with which they are prompted-are necessary for the diffusion of AI benefits around the world. Multilingual jailbreaks that rely on language translation to evade safety measures undermine the safe and inclusive deployment of AI systems. We provide policy recommendations to enhance the multilingual capabilities of AI while mitigating the risks of multilingual jailbreaks. We examine how a language's level of resourcing relates to how vulnerable LLMs are to multilingual jailbreaks in that language. We do this by testing five advanced AI models across 24 official languages of the EU. Building on prior research, we propose policy actions that align with the EU legal landscape and institutional framework to address multilingual jailbreaks, while promoting linguistic inclusivity. These include mandatory assessments of multilingual capabilities and vulnerabilities, public opinion research, and state support for multilingual AI development. The measures aim to improve AI safety and functionality through EU policy initiatives, guiding the implementation of the EU AI Act and informing regulatory efforts of the European AI Office. * Research conducted as part of the ERA:AI Fellowship. 1 Jailbreaking can be defined as the process of circumventing the safety measures placed on LLMs and other AI systems [51]. Vulnerability to jailbreaks paired with powerful model capabilities, including offensive cyber capabilities, chemical, biological, radiological, and nuclear capabilities, contribute to systemic risks [78,31]. 2 Low-resource languages, which account for over 90% of the world's 7,000+ languages and are spoken by 1.2 billion people, have limited labeled and unlabeled data available [81,43]. In this paper we follow Bang et al. (2023) [11] and classify languages based on CommonCrawl corpus share: high-resource languages have over 1%, medium-resource languages 0.1-1%, and low-resource languages less than 0.1%. This method is responsive to the availability of digital language data, with the source data updated monthly. 2nd Workshop on Regulatable ML at NeurIPS 2024.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.13708")
get_code_for_paper("2409.13708")
have("2409.13708")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.13708.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.13708)
Connect an agent — have() is free.