Chris Wendler, Giovanni Monea, Veniamin Veselovsky, Robert West
3 of 5 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, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 2 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/2402.10588.json · badge: /api/ran/2402.10588.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 |
|---|---|---|
| epfl-dlab/llm-latent-language | canonical (classifier label) classifier basis: census |
3 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| load_pickle | Ran ran; our contract draft was wrong, not the code |
epfl-dlab/llm-latent-language/utils.py pointer only (licence: NONE) · get_code("59d98037d0355da4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, epfl-dlab/llm-latent-language 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. |
| plot_ci_plus_heatmap | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
epfl-dlab/llm-latent-language/utils.py pointer only (licence: NONE) · get_code("2ab9ad6901869028") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, epfl-dlab/llm-latent-language 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. |
| yaml_to_dict | Ran ran; our contract draft was wrong, not the code |
epfl-dlab/llm-latent-language/utils.py pointer only (licence: NONE) · get_code("0557332cc65ac319") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, epfl-dlab/llm-latent-language 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. |
| load_tokenizer_only | Not yet run unverified (harvested, no recorded run) |
epfl-dlab/llm-latent-language/llamawrapper.py pointer only (licence: NONE) · get_code("aa16d4a0d7373a3a") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, epfl-dlab/llm-latent-language 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. |
| load_unemb_only | Not yet run unverified (harvested, no recorded run) |
epfl-dlab/llm-latent-language/llamawrapper.py pointer only (licence: NONE) · get_code("990785dbe8cf6698") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, epfl-dlab/llm-latent-language 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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.
We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot languagea question of key importance for understanding how language models function and the origins of linguistic bias. Focusing on the Llama-2 family of transformer models, our study uses carefully constructed non-English prompts with a unique correct single-token continuation. From layer to layer, transformers gradually map an input embedding of the final prompt token to an output embedding from which next-token probabilities are computed. Tracking intermediate embeddings through their high-dimensional space reveals three distinct phases, whereby intermediate embeddings (1) start far away from output token embeddings; (2) already allow for decoding a semantically correct next token in middle layers, but give higher probability to its version in English than in the input language; (3) finally move into an input-language-specific region of the embedding space. We cast these results into a conceptual model where the three phases operate in "input space", "concept space", and "output space", respectively. Crucially, our evidence suggests that the abstract "concept space" lies closer to English than to other languages, which may have important consequences regarding the biases held by multilingual language models. Code and data is made available here: https://github.com/ epfl-dlab/llm-latent-language.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.10588")
get_code_for_paper("2402.10588")
have("2402.10588")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.10588.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.10588)
Connect an agent — have() is free.