Ivan Vulić, Anna Korhonen, Yaoyiran Li
7 of 10 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, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 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/2402.10024.json · badge: /api/ran/2402.10024.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 |
|---|---|---|
| cambridgeltl/sail-bli | canonical (classifier label) classifier basis: census |
7 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| apply_template | Ran ran; our contract draft was wrong, not the code |
cambridgeltl/sail-bli/src/util.py code served (permissive licence) · get_code("e76df3c849e328e1") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| count_parameters | Ran ran, honoured the contract we drafted |
cambridgeltl/sail-bli/src/infer_seed_dic.py code served (permissive licence) · get_code("c7ba302927a96f85") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| evaluate_bli | Ran ran, honoured the contract we drafted |
cambridgeltl/sail-bli/src/openaigen.py code served (permissive licence) · get_code("8664c08247da77bc") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| get_best_template | Ran ran; our contract draft was wrong, not the code |
cambridgeltl/sail-bli/src/util.py code served (permissive licence) · get_code("4e758c201f0c3be2") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| get_templates | Ran ran; our contract draft was wrong, not the code |
cambridgeltl/sail-bli/src/util.py code served (permissive licence) · get_code("2edd13eb7a270d11") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| my_sorted | Ran ran; our contract draft was wrong, not the code |
cambridgeltl/sail-bli/src/extract_bli_test_data.py code served (permissive licence) · get_code("e5a4a12425cc40a8") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| normed_input | Ran ran, violated the contract we drafted |
cambridgeltl/sail-bli/src/extract_bli_test_data.py code served (permissive licence) · get_code("01735bce9688a612") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| inference | Not yet run unverified (harvested, no recorded run) |
cambridgeltl/sail-bli/src/infer_seed_dic.py code served (permissive licence) · get_code("14544d1761941516") How it ranno invocation recorded. |
| inference | Not yet run unverified (harvested, no recorded run) |
cambridgeltl/sail-bli/src/openaigen.py code served (permissive licence) · get_code("11030caebb5b7dcd") How it ranno invocation recorded. |
| return_definition_wn | Not yet run unverified (harvested, no recorded run) |
cambridgeltl/sail-bli/src/extract_bli_test_data.py code served (permissive licence) · get_code("ce64f9a3237c454f") How it ranno invocation recorded. |
Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| my_sorted | 1 other paper 1 dated earlier |
2310.13995 (2023-10) On Bilingual Lexicon Induction with Large Language Models |
|
| normed_input | 1 other paper 1 dated earlier |
2310.13995 (2023-10) On Bilingual Lexicon Induction with Large Language Models |
|
| return_definition_wn | 1 other paper 1 dated earlier |
2310.13995 (2023-10) On Bilingual Lexicon Induction with Large Language Models |
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.
Recent work has shown that, while large language models (LLMs) demonstrate strong word translation or bilingual lexicon induction (BLI) capabilities in few-shot setups, they still cannot match the performance of 'traditional' mapping-based approaches in the unsupervised scenario where no seed translation pairs are available, especially for lower-resource languages. To address this challenge with LLMs, we propose self-augmented in-context learning (SAIL) for unsupervised BLI: starting from a zero-shot prompt, SAIL iteratively induces a set of high-confidence word translation pairs for in-context learning (ICL) from an LLM, which it then reapplies to the same LLM in the ICL fashion. Our method shows substantial gains over zero-shot prompting of LLMs on two established BLI benchmarks spanning a wide range of language pairs, also outperforming mapping-based baselines across the board. In addition to achieving state-of-the-art unsupervised BLI performance, we also conduct comprehensive analyses on SAIL and discuss its limitations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.10024")
get_code_for_paper("2402.10024")
have("2402.10024")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.10024.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.10024)
Connect an agent — have() is free.