code & data of PoisonedRAG paper
active 2024-02-09 → 2026-05-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 820 days from 2024-02-09 to 2026-05-08. Pushes: 28 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 43 total, peak 2 in a day. Comments: 54 total, peak 11 in a day. Stars: 194 total, peak 5 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| sleeepeer | 83 | 28 | 0 | 36 |
| c0ding4ever | 7 | 0 | 0 | 4 |
| Zongdanyang | 6 | 0 | 0 | 3 |
| wzzanthony | 6 | 0 | 0 | 5 |
| young-her | 4 | 0 | 0 | 3 |
| try2love | 2 | 0 | 0 | 0 |
| TonyPeng-2018 | 2 | 0 | 0 | 1 |
| ShiJiawenwen | 2 | 0 | 0 | 1 |
| HuichiZhou | 2 | 0 | 0 | 0 |
| tamtakapanadze | 2 | 0 | 0 | 1 |
| ybdai7 | 1 | 0 | 0 | 0 |
| Day333 | 1 | 0 | 0 | 0 |
| GabHoo | 1 | 0 | 0 | 0 |
| sw0rd1ight | 1 | 0 | 0 | 0 |
| JLUsOrange | 1 | 0 | 0 | 0 |
| AndyShaw01 | 1 | 0 | 0 | 0 |
| Allencheng97 | 1 | 0 | 0 | 0 |
| dequeueing | 1 | 0 | 0 | 0 |
| FSL12345-f | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#23FSL12345-f2025-10-21 06:27恶意文本是如何制作的，恶意文本的质量会大幅度影响结果吗
- Issue comment#21sleeepeer2025-08-18 18:59Code for defense
- Issue#21sleeepeer2025-08-18 18:59Code for defense
- Issue#22ybdai72025-06-24 15:29args.orig_beir_results is None when evaluating msmarco
- Issue#20sleeepeer2025-05-24 01:53Could you provide the pip requirement file?
- Issue comment#20TonyPeng-20182025-05-07 14:16Could you provide the pip requirement file?
- Issue#20TonyPeng-20182025-05-07 12:29Could you provide the pip requirement file?
- Issue#19sleeepeer2025-03-30 00:29代码实现中是否每次都会计算输入的问题和数据集中的全量数据（包括正常的数据和注入的5个包含错误答案的数据）的相似度吗？
- Issue comment#19sleeepeer2025-03-23 19:17代码实现中是否每次都会计算输入的问题和数据集中的全量数据（包括正常的数据和注入的5个包含错误答案的数据）的相似度吗？
- Issue#19sw0rd1ight2025-03-20 07:43代码实现中是否每次都会计算输入的问题和数据集中的全量数据（包括正常的数据和注入的5个包含错误答案的数据）的相似度吗？
- Issue comment#18sleeepeer2025-03-15 23:51Missing files results/beir_results/{args.eval_dataset}-{args.eval_model_code}-cos.json
- Issue#18sleeepeer2025-03-15 23:51Missing files results/beir_results/{args.eval_dataset}-{args.eval_model_code}-cos.json
- Issue#18Day3332025-03-10 09:02Missing files results/beir_results/{args.eval_dataset}-{args.eval_model_code}-cos.json
- Issue comment#17sleeepeer2025-03-08 21:55Question about the similarity threshold in the experiment.
- Issue#17sleeepeer2025-03-08 21:55Question about the similarity threshold in the experiment.
- Issue#17dequeueing2025-03-08 04:46Question about the similarity threshold in the experiment.
- Issue#16sleeepeer2025-02-05 18:22Questions about the parts of the code in main.py
- Issue#16JLUsOrange2025-01-17 11:55Questions about the parts of the code in main.py
- Issue comment#15sleeepeer2024-12-30 20:33Cannot generate 100 malicious texts
- Issue#15sleeepeer2024-12-30 20:33Cannot generate 100 malicious texts
- Issue comment#15young-her2024-12-19 12:10Cannot generate 100 malicious texts
- Issue#13try2love2024-12-18 05:554.2.1 A straightforward solution is to use gradient descent-based methods [53, 78] to optimize R. WHY R???
- Issue comment#15sleeepeer2024-12-15 18:50Cannot generate 100 malicious texts
- Issue#14HuichiZhou2024-12-14 17:02About retrieved text
- Issue comment#15young-her2024-12-12 05:47Cannot generate 100 malicious texts
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 194 stars here means stars gained during the window, not the repo's star count.