Tianyu Pang, Qian Liu, Wei Chen, Han Wang, Minfeng Zhu, Zhaorui Yang, Haozhe Feng
11 of 11 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, 5 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 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/2402.13669.json · badge: /api/ran/2402.13669.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 |
|---|---|---|
| sail-sg/sdft | canonical (classifier label) classifier basis: census |
11 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| check_magicoder | Ran ran, violated the contract we drafted |
sail-sg/sdft/eval/eval_magicoder.py pointer only (licence: NONE) · get_code("8e38a7f4c3b74f9f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| check_openfunction | Ran ran, violated the contract we drafted |
sail-sg/sdft/eval/eval_openfunction.py pointer only (licence: NONE) · get_code("26b2773e736f78dd") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| contains_keywords | Ran ran, violated the contract we drafted |
sail-sg/sdft/eval/eval_magicoder.py pointer only (licence: NONE) · get_code("b9d80359c50174e0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| eval | Ran ran, honoured the contract we drafted |
sail-sg/sdft/eval/keyword_eval_safety.py pointer only (licence: NONE) · get_code("c70eb4756e638ed0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| find_answer_key | Ran ran; our contract draft was wrong, not the code |
sail-sg/sdft/eval/gen_distilled_data.py pointer only (licence: NONE) · get_code("73cbe2d0163944c7") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| find_last_integer | Ran ran; our contract draft was wrong, not the code |
sail-sg/sdft/eval/utils.py pointer only (licence: NONE) · get_code("7d02bf0b46db03b1") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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_bleu4_array | Ran ran, honoured the contract we drafted |
sail-sg/sdft/eval/eval_bleu4.py pointer only (licence: NONE) · get_code("f4218ed8a7d62be1") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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_outputs | Ran ran; our contract draft was wrong, not the code |
sail-sg/sdft/eval/utils.py pointer only (licence: NONE) · get_code("b193dd7920d260e3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| is_safe | Ran ran, violated the contract we drafted |
sail-sg/sdft/eval/keyword_eval_safety.py pointer only (licence: NONE) · get_code("a1f7d6db520591f5") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| standardize_function_call | Ran ran; our contract draft was wrong, not the code |
sail-sg/sdft/eval/eval_openfunction.py pointer only (licence: NONE) · get_code("daf7c701c6269867") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
| starts_right | Ran ran, violated the contract we drafted |
sail-sg/sdft/eval/eval_magicoder.py pointer only (licence: NONE) · get_code("11c643b41155d018") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sail-sg/sdft 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. |
Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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.
The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instructionfollowing abilities. In this paper, we posit that the distribution gap between task datasets and the LLMs serves as the primary underlying cause. To address the problem, we introduce Self-Distillation Fine-Tuning (SDFT), a novel approach that bridges the distribution gap by guiding fine-tuning with a distilled dataset generated by the model itself to match its original distribution. Experimental results on the Llama-2-chat model across various benchmarks demonstrate that SDFT effectively mitigates catastrophic forgetting while achieving comparable or superior performance on downstream tasks compared to the vanilla fine-tuning. Moreover, SDFT demonstrates the potential to maintain the helpfulness and safety alignment of LLMs. Our code is available at https://github.com/sail-sg/sdft.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.13669")
get_code_for_paper("2402.13669")
have("2402.13669")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.13669.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.13669)
Connect an agent — have() is free.