Lei Yang, Yun Chen, Guanhua Chen, Zeguan Xiao, Lili Yang, Jiehui Zhao, Lang Mo
7 of 12 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; 6 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/2604.17396.json · badge: /api/ran/2604.17396.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 |
|---|---|---|
| sustech-nlp/ReGLU | canonical (classifier label) classifier basis: census |
7 ran · 5 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| canonicalize_command | Ran ran; our contract draft was wrong, not the code |
sustech-nlp/ReGLU/src/reglu/config.py pointer only (licence: NOASSERTION) · get_code("5c6aaa26ba4da8f5") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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_forget_quality | Ran ran; our contract draft was wrong, not the code |
sustech-nlp/ReGLU/src/reglu/eval/tofu_aggregate.py pointer only (licence: NOASSERTION) · get_code("56a07d47b6e22052") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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. |
| ensure_run_layout | Ran ran; our contract draft was wrong, not the code |
sustech-nlp/ReGLU/src/reglu/artifacts.py pointer only (licence: NOASSERTION) · get_code("f6deca5ef8ff6fd0") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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_peft_adapter_dir | Ran ran, violated the contract we drafted |
sustech-nlp/ReGLU/src/reglu/trainers/common.py pointer only (licence: NOASSERTION) · get_code("3001fab9d6933f0f") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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_rol_bases | Ran ran; our contract draft was wrong, not the code |
sustech-nlp/ReGLU/src/reglu/methods/reglu/cache.py pointer only (licence: NOASSERTION) · get_code("358c38266644a1cb") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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. |
| normalize_public_command | Ran ran; our contract draft was wrong, not the code |
sustech-nlp/ReGLU/src/reglu/config.py pointer only (licence: NOASSERTION) · get_code("b709f503d9bc1c3e") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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. |
| resolve_torch_dtype | Ran ran; our contract draft was wrong, not the code |
sustech-nlp/ReGLU/src/reglu/trainers/common.py pointer only (licence: NOASSERTION) · get_code("02d72d5d2bb5fb16") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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_model_utility | Not yet run unverified (harvested, no recorded run) |
sustech-nlp/ReGLU/src/reglu/eval/tofu_aggregate.py pointer only (licence: NOASSERTION) · get_code("8bbb93f072f28c60") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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_spec | Not yet run unverified (harvested, no recorded run) |
sustech-nlp/ReGLU/src/reglu/models/registry.py pointer only (licence: NOASSERTION) · get_code("e9e263fa340ec666") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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. |
| main | Not yet run unverified (harvested, no recorded run) |
sustech-nlp/ReGLU/src/reglu/validation.py pointer only (licence: NOASSERTION) · get_code("1045e5778dc8f70b") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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. |
| run_check | Not yet run unverified (harvested, no recorded run) |
sustech-nlp/ReGLU/src/reglu/validation.py pointer only (licence: NOASSERTION) · get_code("30e8be9704381c2e") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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. |
| run_manifest | Not yet run unverified (harvested, no recorded run) |
sustech-nlp/ReGLU/src/reglu/validation.py pointer only (licence: NOASSERTION) · get_code("a03daa2d300b61a7") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sustech-nlp/ReGLU (NOASSERTION). 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the forget-retain trade-off. This can be attributed to their reliance on parameter importance metrics to identify parameters that are important exclusively for forget set, which is fundamentally limited by the superposition phenomenon. Due to the polysemantic nature of LLMs parameters, such an importance metric may struggle to disentangle parameters associated with forget and retain sets. In this work, we propose Representation-Guided Low-rank Unlearning (ReGLU), a novel approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning. First, we develop a representationguided initialization for LoRA that identifies the optimal subspace for selective forgetting. Second, we introduce a regularization loss that constrains the outputs of the LoRA update to lie in the orthogonal complement of the retain set's representation subspace, thereby minimizing interference with the model's performance on the retain set. We evaluate ReGLU on the TOFU and WMDP benchmarks across multiple models. Our results demonstrate that ReGLU consistently outperforms state-of-the-art baselines, achieving superior unlearning quality while maintaining higher model utility.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2604.17396")
get_code_for_paper("2604.17396")
have("2604.17396")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2604.17396.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2604.17396)
Connect an agent — have() is free.