很有趣的分层循环架构，需要看看
Python · active 2025-07-21 → 2026-06-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 330 days from 2025-07-21 to 2026-06-15. Pushes: 3 total, peak 1 in a day. Pull requests: 24 total, peak 2 in a day. Issues: 56 total, peak 6 in a day. Comments: 94 total, peak 9 in a day. Stars: 7,104 total, peak 827 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 |
|---|---|---|---|---|
| imoneoi | 19 | 2 | 2 | 14 |
| kroggen | 8 | 0 | 0 | 8 |
| benman1 | 6 | 0 | 3 | 3 |
| wuttechadmin | 5 | 0 | 1 | 4 |
| alexander-rakhlin | 5 | 0 | 0 | 4 |
| narvind2003 | 5 | 0 | 0 | 4 |
| V1B3hR | 4 | 0 | 0 | 0 |
| xiezhipeng-git | 4 | 0 | 0 | 3 |
| Lorenzobattistela | 4 | 0 | 0 | 1 |
| johnnyZeppelin | 4 | 0 | 0 | 2 |
| labyrinthiasdev | 3 | 0 | 0 | 1 |
| s-1y | 3 | 0 | 0 | 3 |
| LeoRodrigues05 | 3 | 0 | 3 | 0 |
| BradKML | 3 | 0 | 0 | 3 |
| AlexiaJM | 2 | 0 | 0 | 1 |
| rhiz0matic | 2 | 0 | 0 | 2 |
| zbloss | 2 | 0 | 1 | 1 |
| TuananhCR | 2 | 0 | 0 | 1 |
| dywsy21 | 2 | 0 | 1 | 1 |
| yan4xi1 | 2 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#110LeoRodrigues052026-03-02 10:56
- Issue comment#10wuttechadmin2026-01-13 01:34arcprize.org leaderboard
- Pull request#107LeoRodrigues052026-01-11 14:02
- Issue#106tqandi2026-01-08 03:49Question about baseline CoT prompts and settings (o3-mini-high, DeepSeek R1, Claude 3.7 8K)
- Issue comment#46huskydoge2026-01-02 18:40The input to CastedSparseEmbedding is the index of the input in the overall data. What is the role of this embedding?
- Issue#104huangkaiyang2025-12-26 12:46How to use checkpoints tp predict?
- Pull request#103LeoRodrigues052025-12-26 11:19
- Pull request#102somdipto2025-12-24 02:22
- Pull request#99orbisai0security2025-12-07 07:48
- Issue comment#41bumi0012025-11-30 10:59import adam_atan2_backend ModuleNotFoundError: No module named 'adam_atan2_backend'
- Issue comment#96drawlinson2025-11-12 05:54Additional resources
- Issue comment#25alexander-rakhlin2025-11-01 14:07pip install adam_atan2 success then run code get No module named 'adam_atan2_backend'
- Issue comment#67myhub2025-10-31 03:32I would like to ask the model parameter 27, why does checkpoint have 2.2G?
- Issue comment#90Bejro2025-10-16 16:07Has anyone managed to run evaluate.py with the provided ARC-AGI-2 checkpoint?
- Issue comment#90jin-qq2025-10-16 07:04Has anyone managed to run evaluate.py with the provided ARC-AGI-2 checkpoint?
- Issue comment#80wuttechadmin2025-10-07 13:42Full-Scale Experiment with exact_accuracy 0
- Issue comment#80wuttechadmin2025-10-07 13:36Full-Scale Experiment with exact_accuracy 0
- Issue#95V1B3hR2025-10-04 22:54Optionally, arbitrary mean and fan-in scaling supported.
- Issue comment#89alexander-rakhlin2025-10-04 20:03feat: v0.1.0 Refactor & Packaging
- Issue#91V1B3hR2025-10-03 23:19Enhance Weight Initialization: Add Correct Truncated Normal with Variance Compensation
- Issue#95V1B3hR2025-10-03 23:19Optionally, arbitrary mean and fan-in scaling supported.
- Issue#93V1B3hR2025-10-03 23:19Variance after initialization matches requested std.
- Issue comment#89alexander-rakhlin2025-10-02 14:29feat: v0.1.0 Refactor & Packaging
- Issue comment#90alexander-rakhlin2025-10-02 09:37Has anyone managed to run evaluate.py with the provided ARC-AGI-2 checkpoint?
- Issue#90alexander-rakhlin2025-10-02 09:21Has anyone managed to run evaluate.py with the provided ARC-AGI-2 checkpoint?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 7,104 stars here means stars gained during the window, not the repo's star count.