SecondBrain
Ask the Brain

How confidence is scored

Most knowledge bases present every page with the same implied authority. This one doesn’t. Each thesis — every synthesis, comparison, and answered question — is graded on a transparent rubric so you know how much weight it can bear before you read it.

The two halves of a score

70% · LLM judge

Claude reads each thesis and the source pages it cites, then grades four dimensions — adversarially. Quotes are checked against sources; single-author dependencies and unsupported extrapolations cost points.

30% · Deterministic metrics

Computed mechanically from the wiki itself: how many sources the page cites, how many independent outlets they span, how recently it was updated. Fully reproducible.

The four judged dimensions

Evidence

How well are the page's claims supported by the cited sources? 5 means every major claim is traceable to a source; 1 means mostly unsupported assertion.

Triangulation

Do multiple independent sources converge on the key claims? 5 means three or more independent authors/outlets agree; 1 means everything rests on a single voice.

Reasoning

Is the logic sound — are caveats, counterarguments, and the limits of the evidence acknowledged? 5 means the page attacks its own argument; 1 means it's one-sided.

Groundedness

How far do conclusions extrapolate beyond what the sources actually say? 5 stays within the evidence; 1 presents speculative leaps as fact.

Reading the levels

85–100
High confidence

Multiply-sourced, claims verified against sources, self-critical. Safe to quote — with its stated caveats.

70–84
Corroborated

Well-evidenced with known, named gaps. Directionally reliable; check the rationale before leaning on specifics.

50–69
Emerging

A promising frame resting on thin or single-author sourcing. Treat as informed opinion, not established fact.

0–49
Exploratory

Early thinking. A hypothesis filed so it can compound — not a position.

Honest limits

  • The judge is an LLM. It verifies claims against the wiki’s own sources — not against the world. A page can score well and still be wrong if its sources are.
  • Many sources here are practitioner talks and videos, not peer-reviewed research. The triangulation dimension exists precisely to keep that visible.
  • Scores are regenerated when the wiki changes (last: 2026-07-03). A low score isn’t a defect — it’s an honest reading of where a thesis currently stands.