MaintainerPulse
temporal prediction of dependency maintenance riskhttpcore encode/httpcore ▲ high risk
72%
no release in the next 12 months
75%
new issues will go unanswered (30 days)
100%
maintainer activity collapse within 12 months
13%
chance of a release within 12 months (survival model)
Model risk over time
calibrated P(no release next 12mo) at each historical monthly snapshot
Repository activity, last 36 months
pushes
issues
PyPI release
What drives this score
TreeSHAP contributions; raises risk /
lowers risk
Survival curve
P(still no release) m months ahead, discrete-time hazard model
In plain words
- no PyPI release in 14 months
- no pushes to the repository in 15 months
- only 0% of recent issues get a response in 30 days
Signals at the latest snapshot
| days since last release | 433 | releases, last 12mo | 0 |
| people pushing, last 12mo | 0 | bus factor (top pusher share) | - |
| issues opened, last 12mo | 4 | 30-day response rate | 0% |
| stars accumulated | 662 | open vulns without fix | 0 |
Probabilities are isotonic-calibrated on a held-out validation year and evaluated on future snapshots the models never saw (PR-AUC 0.894, precision@50 = 1.00 on the headline target).