active 2026-02-27 → 2026-08-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 166 days from 2026-02-27 to 2026-08-11. Pushes: 252 total, peak 32 in a day. Pull requests: 26 total, peak 6 in a day. Issues: 22 total, peak 8 in a day. Comments: 99 total, peak 38 in a day. Stars: 1 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 |
|---|---|---|---|---|
| mmcdermott | 180 | 69 | 14 | 56 |
| gkondas | 149 | 135 | 6 | 3 |
| payalchandak | 51 | 38 | 6 | 5 |
| Copilot | 41 | 10 | 0 | 22 |
| codecov-commenter | 12 | 0 | 0 | 12 |
| coderabbitai[bot] | 6 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#285gkondas2026-08-07 18:50Size the model from the data instead of ModernBERT's defaults
- Issue#273gkondas2026-07-14 22:08Simplify CLI workflow for training with tuning-loss + tuning macro-AUROC tracking
- Issue#208gkondas2026-06-18 17:58Stage 3: resolve prediction times, zip queries, write partitioned index
- Issue#204gkondas2026-06-17 19:23Artifact layout: two disjoint, never-nested roots + cleanup semantics
- Issue comment#172gkondas2026-05-01 04:30Stream predictions to parquet instead of buffering in memory
- Pull request#177gkondas2026-04-28 18:58
- Issue comment#175codecov-commenter2026-04-28 01:14Add prevalence metric to evaluation output
- Issue#171gkondas2026-04-28 01:08new feat: calculating prevalence
- Issue comment#172gkondas2026-04-28 01:08Stream predictions to parquet instead of buffering in memory
- Issue#169gkondas2026-04-28 00:01new feat: Get embeddings from predictions
- Issue comment#166codecov-commenter2026-04-25 04:03test: verify SSH commit signing setup
- Pull request#165payalchandak2026-04-25 03:46
- Issue comment#163codecov-commenter2026-04-24 22:55chore: add SessionStart hook to install gcloud for web sessions
- Pull request#162payalchandak2026-04-24 20:32
- Pull request#160gkondas2026-04-24 00:27
- Pull request#160gkondas2026-04-24 00:26
- Pull request#152mmcdermott2026-04-22 19:30
- Issue#148mmcdermott2026-04-22 19:05EQ_generate_evaluation_tasks: budget caps, focus codes, explicit tuples (subsumes #138)
- Pull request#141gkondas2026-04-22 02:01
- Pull request#141gkondas2026-04-22 02:01
- Releasemmcdermott2026-04-21 02:56v0.3.0
- Pull request#137mmcdermott2026-04-21 01:50
- Issue#130mmcdermott2026-04-20 11:02aces_to_eq: resolve unused `target_rows` parameter
- Issue comment#131mmcdermott2026-04-20 11:02Release candidate — refactor Phase 1 + 2.1/2.2 + partial 2.4 (roll-up)
- Pull request#96mmcdermott2026-04-19 23:35
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.