MaintainerPulse

temporal prediction of dependency maintenance risk

aiofiles Tinche/aiofiles ▲ high risk

77%
no release in the next 12 months
70%
new issues will go unanswered (30 days)
93%
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
0%50%100%2018-012020-072022-122025-06high risk

Repository activity, last 36 months

pushes issues PyPI release
025502023-072024-062025-052026-05

What drives this score

TreeSHAP contributions; raises risk / lowers risk
events, all time+releases, last 12mo+code reviews, 12mo-stars, all time+

Survival curve

P(still no release) m months ahead, discrete-time hazard model
0%50%100%036912

In plain words

Signals at the latest snapshot

days since last release 265 releases, last 12mo 1
people pushing, last 12mo 0 bus factor (top pusher share) -
issues opened, last 12mo 1 30-day response rate 0%
stars accumulated 3125 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).