a rubric driven prioritized replay rl algo to maximise continual learning - forked from tokenbender/infinite
active 2025-08-23 → 2025-09-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 31 days from 2025-08-23 to 2025-09-22. Pushes: 38 total, peak 10 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 5 total, peak 2 in a day. Comments: 5 total, peak 2 in a day. Stars: 4 total, peak 1 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 |
|---|---|---|---|---|
| tokenbender | 53 | 38 | 7 | 4 |
| stevenshinechen | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Pull request#14tokenbender2025-09-22 00:40
- Issue comment#10tokenbender2025-09-19 12:20[Planning] Plan of initial replay scheduler
- Issue#2tokenbender2025-09-19 08:50[Planning] Models, domains, datasets, evals for first iteration (P0)
- Pull request#13tokenbender2025-09-19 07:20
- Pull request#13tokenbender2025-09-19 07:20
- Pull request#12tokenbender2025-09-17 11:41
- Issue comment#2tokenbender2025-09-17 08:34[Planning] Models, domains, datasets, evals for first iteration (P0)
- Issue#10stevenshinechen2025-09-03 21:50[Planning] Plan of initial replay scheduler
- Issue comment#6tokenbender2025-09-03 21:37[Feature] Single-signal prioritized replay scheduler (acc_ema)
- Issue comment#6stevenshinechen2025-09-03 20:57[Feature] Single-signal prioritized replay scheduler (acc_ema)
- Issue comment#2tokenbender2025-09-02 23:27[Planning] Models, domains, datasets, evals for first iteration (P0)
- Issue#7tokenbender2025-09-01 09:44[Tooling] Contamination detector (train/eval overlap audit)
- Issue#3tokenbender2025-09-01 07:13add a markdown detailing out the problem statement for infinite and helps develop granular understanding of the work as standard vs infinite RL framework
- Pull request#4tokenbender2025-08-27 10:37
- Issue#2tokenbender2025-08-26 19:35pick model and domains, datasets, evals needed for first iteration
- Pull request#1tokenbender2025-08-26 19:07
- Pull request#1tokenbender2025-08-26 19:06
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 4 stars here means stars gained during the window, not the repo's star count.