Ye Wang, Hongfu Liu, Yuxi Xie, Michael Shieh
4 of 7 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; 1 honoured the contract we drafted, 0 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/2408.14866.json · badge: /api/ran/2408.14866.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 |
|---|---|---|
| Waffle-Liu/DeGCG | canonical (classifier label) classifier basis: census |
4 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| expand_experiment_configs | Ran ran; our contract draft was wrong, not the code |
Waffle-Liu/DeGCG/eval_utils.py pointer only (licence: MIT); the stored copy get_code serves, from youai058/SlotGCG, is pointer only (licence: NONE) · get_code("6fa90dd36057918e") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from youai058/SlotGCG, 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. |
| get_nonascii_toks | Ran ran, honoured the contract we drafted |
Waffle-Liu/DeGCG/baselines/gcg/gcg_utils.py code served (permissive licence) · get_code("400ada600d105b0a") 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 Tensor, ndim 1, dtype family int, shape (44,) 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.
|
| parse_indexing_expression | Ran ran; our contract draft was wrong, not the code |
Waffle-Liu/DeGCG/eval_utils.py pointer only (licence: MIT); the stored copy get_code serves, from youai058/SlotGCG, is pointer only (licence: NONE) · get_code("914cce1bc1e0a0d8") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from youai058/SlotGCG, 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. |
| replace_model_parameters | Ran ran; our contract draft was wrong, not the code |
Waffle-Liu/DeGCG/eval_utils.py pointer only (licence: MIT); the stored copy get_code serves, from youai058/SlotGCG, is pointer only (licence: NONE) · get_code("0393dcd85dc803dd") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from youai058/SlotGCG, 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. |
| check_refusal_completions | Not yet run unverified (harvested, no recorded run) |
Waffle-Liu/DeGCG/baselines/check_refusal_utils.py code served (permissive licence) · get_code("d073e342e38af354") How it ranno invocation recorded. |
| load_model_and_tokenizer | Not yet run unverified (harvested, no recorded run) |
Waffle-Liu/DeGCG/baselines/model_utils.py code served (permissive licence) · get_code("5949ab432e811362") How it ranno invocation recorded. |
| sample_control | Not yet run unverified (harvested, no recorded run) |
Waffle-Liu/DeGCG/baselines/gcg/gcg_utils.py code served (permissive licence) · get_code("112080cc850b86b9") How it ranno invocation recorded. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 1 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 |
|---|---|---|---|
| expand_experiment_configs | 3 other papers 3 later |
2502.12970 (2025-02) Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking |
2605.08898 (2026-05) LLM-Agnostic Semantic Representation Attack 2606.05609 (2026-06) SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks |
| load_model_and_tokenizer | 3 other papers 3 later |
2501.01872 (2025-01) Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions ! WARNING: This paper contains model outputs that may be considered offensive in nature |
2502.12970 (2025-02) Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking 2605.08898 (2026-05) LLM-Agnostic Semantic Representation Attack |
| parse_indexing_expression | 3 other papers 3 later |
2502.12970 (2025-02) Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking |
2605.08898 (2026-05) LLM-Agnostic Semantic Representation Attack 2606.05609 (2026-06) SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks |
| replace_model_parameters | 3 other papers 3 later |
2502.12970 (2025-02) Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking |
2605.08898 (2026-05) LLM-Agnostic Semantic Representation Attack 2606.05609 (2026-06) SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks |
| get_nonascii_toks | 1 other paper 1 dated earlier |
2402.09154 (2024-02) Attacking Large Language Models with Projected Gradient Descent |
|
| sample_control | 1 other paper 1 dated earlier |
2406.10794 (2024-06) Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis |
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.
Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbreaking LLMs using the gradient-based search algorithm Greedy Coordinate Gradient (GCG). However, GCG struggles with computational inefficiency, limiting further investigations regarding suffix transferability and scalability across models and data. In this work, we bridge the connection between search efficiency and suffix transferability. We propose a two-stage transfer learning framework, DeGCG, which decouples the search process into behavioragnostic pre-searching and behavior-relevant post-searching. Specifically, we employ direct first target token optimization in pre-searching to facilitate the search process. We apply our approach to cross-model, cross-data, and self-transfer scenarios. Furthermore, we introduce an interleaved variant of our approach, i-DeGCG, which iteratively leverages selftransferability to accelerate the search process. Experiments on HarmBench demonstrate the efficiency of our approach across various models and domains. Notably, our i-DeGCG outperforms the baseline on Llama2-chat-7b with ASRs of 43.9 (+22.2) and 39.0 (+19.5) on valid and test sets, respectively. Further analysis on cross-model transfer indicates the pivotal role of first target token optimization in leveraging suffix transferability for efficient searching 1 . * Equal contribution.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.14866")
get_code_for_paper("2408.14866")
have("2408.14866")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2408.14866.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2408.14866)
Connect an agent — have() is free.