press / to search

Small tools, built to explore.

A growing collection of small, focused tools.

001 · health
true weight
Filters out daily noise from scale readings. Uses a Kalman filter plus RTS smoother to show your real weight trend with a confidence range and rate of change.

True Weight uses a Kalman filter to find your real weight behind the daily noise. A moving average smooths data with a fixed window. This filter adapts to your data instead. It gives you a 95% confidence range around every estimate. It also shows your rate of change, with its own confidence band.

Why it beats a moving average:

  • Confidence range. Every estimate shows how reliable it is. A moving average gives you one number with no sense of trust.
  • Adaptive window. The filter sets its own smoothing level based on your measurement noise. No fixed 7-day or 14-day choice.
  • No lag. A moving average trails reality by half its window. This filter removes that lag using all your data.
  • Rate of change. The model estimates how fast your weight is trending, with its own confidence band.

Enter one reading a day and the chart shows your true weight with 95% confidence bands and rate of change.

open tool →