Fisher Information
I_F(θ) — how much a measurement tells you about a parameter
Fisher information I_F(θ) quantifies how much an observation or sample tells you about an unknown parameter θ. High Fisher information → precise estimation possible; low Fisher information → fundamental limit on how well θ can be learned from that measurement alone.
Genesis uses it via the Cramér–Rao bound: no unbiased estimator can beat variance ≥ 1/I_F. Downstream processing can approach the bound but cannot exceed the information content of the original observation — the quality ceiling is set at capture, not at the model.
Corpus stance
A2 — working context: Statistical formalism for observation-limited trust; see What Information Theory Says.