Andrea Esuli, Anna Rogers, Giovanni Puccetti, Chiara Alzetta, F. Dell’orletta
12 of 17 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; 3 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 7 failures of our instrument; 5 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/2406.12128.json · badge: /api/ran/2406.12128.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 |
|---|---|---|
| gpucce/synthetic_llm_data | canonical (classifier label) classifier basis: census |
12 ran · 5 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| add_newline | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/data_generation/utils.py pointer only (licence: NONE) · get_code("943eedc90e8e6bc7") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| camoscio_preprocessing_function | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/data_generation/utils.py pointer only (licence: NONE) · get_code("f6146e20fb11a100") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| compute_loglikelihood | Ran ran, honoured the contract we drafted |
gpucce/synthetic_llm_data/src/synthetic_detection/detect_gpt/utils/detect_gpt_utils.py pointer only (licence: NONE) · get_code("2a148d835d745f22") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| compute_loss | Ran ran, honoured the contract we drafted |
gpucce/synthetic_llm_data/src/synthetic_detection/detect_gpt/utils/detect_gpt_utils.py pointer only (licence: NONE) · get_code("2e7fdfbb51f8c89a") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| cut_to_shortest | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/synthetic_detection/detect_gpt/dataset_lm_modification.py pointer only (licence: NONE) · get_code("39e8c5fc99f312a7") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| generate | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/data_generation/data_complete.py pointer only (licence: NONE) · get_code("e386851e40fd0d0e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| generate_synthetic | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/data_generation/data_complete.py pointer only (licence: NONE) · get_code("ed8e545820c2fa55") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| per_sequence_crossentropy | Ran ran, honoured the contract we drafted |
gpucce/synthetic_llm_data/src/synthetic_detection/detect_gpt/utils/detect_gpt_utils.py pointer only (licence: NONE) · get_code("95eed0750de95437") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| postprocess_record | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/clean_json.py pointer only (licence: NONE) · get_code("bde233f26f94d406") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| register_list_cleaner | Ran ran on a synthesized input |
gpucce/synthetic_llm_data/src/clean_json.py pointer only (licence: NONE) · get_code("235d787a54e2e314") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| register_record_cleaner | Ran ran on a synthesized input |
gpucce/synthetic_llm_data/src/clean_json.py pointer only (licence: NONE) · get_code("1df59dccab26e34d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| split_by_full_stop | Ran ran; our contract draft was wrong, not the code |
gpucce/synthetic_llm_data/src/data_generation/utils.py pointer only (licence: NONE) · get_code("4aff19c47a533360") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| generate | Not yet run unverified (harvested, no recorded run) |
gpucce/synthetic_llm_data/src/data_generation/data_generate.py pointer only (licence: NONE) · get_code("e2954c86d261f558") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| generate_synthetic | Not yet run unverified (harvested, no recorded run) |
gpucce/synthetic_llm_data/src/data_generation/data_generate.py pointer only (licence: NONE) · get_code("71ab34fce0425525") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| get_model_and_tokenizer | Not yet run unverified (harvested, no recorded run) |
gpucce/synthetic_llm_data/src/data_generation/data_complete.py pointer only (licence: NONE) · get_code("18e76676f374297a") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| get_model_tokenizer_and_params | Not yet run unverified (harvested, no recorded run) |
gpucce/synthetic_llm_data/src/data_generation/data_generate.py pointer only (licence: NONE) · get_code("767de70809e6c45e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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. |
| tokenize_mask_extract_and_apply | Not yet run unverified (harvested, no recorded run) |
gpucce/synthetic_llm_data/src/synthetic_detection/detect_gpt/dataset_lm_modification.py pointer only (licence: NONE) · get_code("4c60a84182cba83c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gpucce/synthetic_llm_data 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 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 17 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.
Large Language Models (LLMs) are increasingly used as 'content farm' models (CFMs), to generate synthetic text that could pass for real news articles. This is already happening even for languages that do not have high-quality monolingual LLMs. We show that fine-tuning Llama (v1), mostly trained on English, on as little as 40K Italian news articles, is sufficient for producing news-like texts that native speakers of Italian struggle to identify as synthetic. We investigate three LLMs and three methods of detecting synthetic texts (log-likelihood, De-tectGPT, and supervised classification), finding that they all perform better than human raters, but they are all impractical in the real world (requiring either access to token likelihood information or a large dataset of CFM texts). We also explore the possibility of creating a proxy CFM: an LLM fine-tuned on a similar dataset to one used by the real 'content farm'. We find that even a small amount of fine-tuning data suffices for creating a successful detector, but we need to know which base LLM is used, which is a major challenge. Our results suggest that there are currently no practical methods for detecting synthetic newslike texts 'in the wild', while generating them is too easy. We highlight the urgency of more NLP research on this problem.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.12128")
get_code_for_paper("2406.12128")
have("2406.12128")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.12128.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.12128)
Connect an agent — have() is free.