Weighs evidence, doesn't count votes
Correlated sources don't get counted twice, and a curated feed naming an active C2 outweighs a lone scanner's hunch. The score asks who is saying it and how much to trust them.
The engine underneath
A score that reasons like an analyst.
The transparent, reproducible scoring that powers every verdict. It weighs sources by credibility, stays honest about uncertainty, and gets sharper as it learns what indicators truly became.
Honest about uncertainty
Severity and confidence are two different questions. A strong lead with thin corroboration reads 'leaning', not 'certain' — and absence of reports is never mistaken for a clean bill of health.
Explainable and reproducible
Every score decomposes to the evidence that produced it, and re-derives to the same number months later. No black box — a verdict you can stand behind in an audit or a courtroom.
Calibrated to reality
It checks its past calls against what indicators objectively became, surfaces its own blind spots, and sharpens over time. Not frozen expert intuition — a model that learns.
- Independence-weighted evidence aggregation
- Severity and confidence, reported separately
- Reproducible & fully decomposable verdicts
- Self-supervised calibration against real outcomes
See it on your data.
A 30-minute walkthrough on your indicators, your requirements, your controls.