绝对零：使用零数据强化自博弈推理
active 2025-05-05 → 2026-06-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 419 days from 2025-05-05 to 2026-06-27. Pushes: 17 total, peak 5 in a day. Pull requests: 13 total, peak 5 in a day. Issues: 35 total, peak 4 in a day. Comments: 56 total, peak 8 in a day. Stars: 1,470 total, peak 168 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 |
|---|---|---|---|---|
| Andrewzh112 | 53 | 10 | 5 | 27 |
| yiranwu0 | 9 | 5 | 3 | 1 |
| kekePower | 5 | 0 | 0 | 5 |
| jbdatascience | 5 | 0 | 0 | 5 |
| basicv8vc | 4 | 0 | 0 | 2 |
| TongLiu-github | 4 | 0 | 0 | 2 |
| Winston-Yuan | 3 | 0 | 0 | 1 |
| LeapLabTHU | 3 | 1 | 0 | 1 |
| HaFaZhang | 3 | 0 | 0 | 2 |
| ftshortt | 3 | 0 | 1 | 1 |
| KevinH48264 | 2 | 0 | 1 | 1 |
| huanhuan6666 | 2 | 0 | 0 | 0 |
| nickduck1 | 2 | 0 | 0 | 0 |
| PolarisDane | 2 | 0 | 2 | 0 |
| a-antoniades | 2 | 0 | 0 | 1 |
| ypwang61 | 2 | 0 | 0 | 1 |
| MoreiraP12 | 2 | 0 | 0 | 1 |
| fuzzall | 1 | 0 | 0 | 0 |
| mrthedubey | 1 | 0 | 0 | 1 |
| goney3 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#35DianxingShi2026-03-27 04:06a recommand list of batchsize, minibatchsize, etc. to run AZR 14B in 4x A100
- Issue comment#33a-antoniades2025-09-26 23:55invalid uids get full reward=1.0?
- Issue#33a-antoniades2025-09-26 23:55invalid uids get full reward=1.0?
- Pull request#32PolarisDane2025-09-17 03:58
- Pull request#32PolarisDane2025-09-17 03:58
- Issue comment#27Andrewzh1122025-08-26 17:40How to reproduce reported results on coder3b.
- Issue comment#142JAE222025-07-23 04:17code_pred_train_dataloader is empty when drop_last=True and dataset is filtered
- Issue comment#30Andrewzh1122025-07-10 23:58Questions about code evaluation
- Issue#311arka022025-07-07 17:07Failed build error
- Issue#30fuzzall2025-07-07 03:46Questions about code evaluation
- Pull request#29HackoAwesome2025-07-02 02:48
- Issue comment#23Andrewzh1122025-06-29 03:34A tip how to make it think in llama-cli - syntax
- Issue#23Andrewzh1122025-06-29 03:34A tip how to make it think in llama-cli - syntax
- Issue comment#22Andrewzh1122025-06-29 03:13Prevent insufficient data after filtering in _create_train_code_pred_…
- Pull request#22Andrewzh1122025-06-29 03:13
- Issue comment#14Andrewzh1122025-06-29 03:13code_pred_train_dataloader is empty when drop_last=True and dataset is filtered
- Issue#14Andrewzh1122025-06-29 03:13code_pred_train_dataloader is empty when drop_last=True and dataset is filtered
- Issue comment#16Andrewzh1122025-06-29 03:08Plans to support Qwen3-4B
- Issue#16Andrewzh1122025-06-29 03:08Plans to support Qwen3-4B
- Issue#28goney32025-06-25 16:32Exploring Synergy: Absolute Zero Reasoner Training with 1.58-bit Quantization (Inspired by BitNet)
- Issue comment#27HaFaZhang2025-06-24 08:03How to reproduce reported results on coder3b.
- Issue comment#27yiranwu02025-06-21 21:34How to reproduce reported results on coder3b.
- Issue comment#27HaFaZhang2025-06-21 04:29How to reproduce reported results on coder3b.
- Issue#27HaFaZhang2025-06-20 08:31How to reproduce reported results on coder3b.
- Pull request#26ftshortt2025-06-17 13:24
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,470 stars here means stars gained during the window, not the repo's star count.