Reinforcement Learning Verifiers for Cybersecurity
active 2025-09-04 → 2026-03-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 186 days from 2025-09-04 to 2026-03-08. Pushes: 125 total, peak 14 in a day. Pull requests: 41 total, peak 9 in a day. Issues: 19 total, peak 14 in a day. Comments: 45 total, peak 11 in a day. Stars: 2 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 |
|---|---|---|---|---|
| intertwine | 182 | 125 | 41 | 10 |
| Copilot | 35 | 0 | 0 | 19 |
| detail-app[bot] | 14 | 0 | 0 | 0 |
| chatgpt-codex-connector[bot] | 12 | 0 | 0 | 7 |
| cursor[bot] | 9 | 0 | 0 | 6 |
| claude[bot] | 3 | 0 | 0 | 3 |
Recent activity
Latest issues, pull requests and releases
- Pull request#72intertwine2026-03-08 03:56
- Issue comment#71intertwine2026-03-07 19:01fix: add short-name package for E1 judge env
- Pull request#70intertwine2026-03-03 01:47
- Issue comment#70intertwine2026-03-03 00:44feat(WP3c): LLM-judge reward variant of E1 network-logs environment
- Pull request#69intertwine2026-03-03 00:36
- Issue comment#66claude[bot]2026-02-28 03:19feat: Migrate to Prime CLI v0.5.41 for hosted RL training
- Issue comment#63intertwine2026-02-09 15:04research: add SOAR investigation and experiment prototype
- Issue comment#62claude[bot]2026-02-07 20:51roadmap: add WP2.5 (Prime-RL 0.4.0 upgrade) and distillation baseline
- Pull request#62intertwine2026-02-07 20:47
- Issue comment#61intertwine2026-02-04 23:42Implement WP2 baselines and public mini sets
- Issue comment#56claude[bot]2026-02-02 04:29feat(WP1): add metrics contracts and report generator
- Pull request#57intertwine2026-02-02 04:05
- Pull request#57intertwine2026-02-02 03:54
- Issue comment#56intertwine2026-02-02 03:40feat(WP1): add metrics contracts and report generator
- Releaseintertwine2026-01-24 21:10v0.2.3
- Pull request#55intertwine2026-01-24 16:14
- Issue#43intertwine2026-01-23 15:36[Detail Bug] TP weighting uses predicted severity (not oracle) in score_detection(), inflating scores
- Issue#44intertwine2026-01-23 15:36[Detail Bug] get_response_text crashes when last list item is not a dict
- Issue#45intertwine2026-01-23 15:35[Detail Bug] Temporary file leak on tool exception in reward_config_auditing
- Issue comment#49intertwine2026-01-23 15:35[Detail Bug] Hardcoded Features schema in E1 loader drops extra fields, causing KeyError
- Releaseintertwine2026-01-23 15:31v0.2.2
- Pull request#52intertwine2026-01-23 15:08
- Issue#50detail-app[bot]2026-01-11 13:59[Detail Bug] apply_json_patch crashes on JSON Pointer paths with array indices
- Issue#50detail-app[bot]2026-01-11 13:59[Detail Bug] apply_json_patch crashes on JSON Pointer paths with array indices
- Issue#50detail-app[bot]2026-01-11 13:59[Detail Bug] apply_json_patch crashes on JSON Pointer paths with array indices
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2 stars here means stars gained during the window, not the repo's star count.