6 of 9 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; 3 failures of our instrument; 3 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/2409.18169.json · badge: /api/ran/2409.18169.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 |
|---|---|---|
| git-disl/booster | canonical (classifier label) classifier basis: census |
6 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| adapt_dimension_b2a | Ran ran, honoured the contract we drafted |
git-disl/booster/loss_func/repnoise_loss.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from ChanLiang/VAA, is pointer only (licence: NONE) · get_code("175778f00233af46") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ChanLiang/VAA, and GitHub detected no licence in that repository 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. |
| coherence_check | Ran ran, violated the contract we drafted |
git-disl/booster/poison/evaluation/eval_sentiment.py code served (permissive licence) · get_code("1e9e4d30c8f0cc73") 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 bool, 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.
|
| extract_answer_number | Ran ran, honoured the contract we drafted |
git-disl/booster/gsm8k/pred_eval.py code served (permissive licence) · get_code("c9b7e712eaf8afe1") 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.
|
| jload | Ran ran; our contract draft was wrong, not the code |
git-disl/booster/utils.py code served (permissive licence) · get_code("d07d04439cd1d44f") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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.
|
| masked_token_ce_loss | Ran ran; our contract draft was wrong, not the code |
git-disl/booster/loss_func/repnoise_loss.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from ChanLiang/VAA, is pointer only (licence: NONE) · get_code("dbc0448520ee9257") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ChanLiang/VAA, and GitHub detected no licence in that repository 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_activation_hook | Ran ran; our contract draft was wrong, not the code |
git-disl/booster/loss_func/repnoise_loss.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from ChanLiang/VAA, is pointer only (licence: NONE) · get_code("c605efc9460b6c33") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ChanLiang/VAA, and GitHub detected no licence in that repository 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. |
| calculate_drift2first_embedding | Not yet run unverified (harvested, no recorded run) |
git-disl/booster/utils.py code served (permissive licence) · get_code("5f4323e1e87dc83b") How it ranno invocation recorded. |
| get_leaf_modules_with_grad | Not yet run unverified (harvested, no recorded run) |
git-disl/booster/trainer.py code served (permissive licence) · get_code("88c8a24923c625a1") How it ranno invocation recorded. |
| track_embedding | Not yet run unverified (harvested, no recorded run) |
git-disl/booster/utils.py code served (permissive licence) · get_code("bda772180d04ada3") How it ranno invocation recorded. |
Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 9 later) and 0 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 |
|---|---|---|---|
| jload | 46 other papers 34 dated earlier, 1 the same month, 8 later, 3 same year, order not determinable |
2302.13971 (2023-02) LLaMA: Open and Efficient Foundation Language Models |
2305.12870 (2023-05) Lion: Adversarial Distillation of Proprietary Large Language Models 2305.13068 (2023-05) Making Language Models Better Tool Learners with Execution Feedback and 43 more not named here |
| masked_token_ce_loss | 4 other papers 1 dated earlier, 3 later |
2405.14577 (2024-05) Representation Noising: A Defence Mechanism Against Harmful Finetuning |
2410.09760 (2024-10) Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation 2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation and 1 more not named here |
| adapt_dimension_b2a | 3 other papers 3 later |
2410.09760 (2024-10) Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation |
2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation 2506.03850 (2025-06) Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning |
| register_activation_hook | 3 other papers 3 later |
2410.09760 (2024-10) Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation |
2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation 2506.03850 (2025-06) Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning |
| extract_answer_number | 2 other papers 1 dated earlier, 1 later |
2408.09600 (2024-08) Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning |
2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation |
| get_leaf_modules_with_grad | 2 other papers 2 later |
2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation |
2503.00555 (2025-03) Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable |
| calculate_drift2first_embedding | 1 other paper 1 later |
2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation |
|
| coherence_check | 1 other paper 1 later |
2503.00555 (2025-03) Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable |
|
| track_embedding | 1 other paper 1 later |
2501.17433 (2025-01) Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation |
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 research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns: fine-tuning with a few harmful data uploaded from the users can compromise the safety alignment of the model. The attack, known as harmful fine-tuning attack, has generated broad research interests in both academia and industry. In this paper, we first systematically formulate the threat model and basic assumptions of harmful fine-tuning. Then, we provide a comprehensive review of harmful fine-tuning from three fundamental perspectives: attack setting, defense design, and evaluation methodology. First, we present the threat model of the problem and introduce the harmful fine-tuning attack and its variants. Next, we systematically survey representative attacks, defense methods, and mechanical analysis of adverse effects in the existing literature. Finally, we introduce the evaluation methodology and outline future research directions, which can serve as guidelines and crucial perspectives for the future development of the subject. We also maintain a curated list of relevant papers, which are made accessible at https://github.com/git-disl/awesome_LLM-harmful-fine-tuning-papers
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.18169")
get_code_for_paper("2409.18169")
have("2409.18169")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.18169.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.18169)
Connect an agent — have() is free.