Claims › Coder agreement + Measurement artefact + Convergent paths › C020
C020
From the research log · Vertical Validation ¶11 · ¶11 · assumed
…The gap is the finding.
“Surface-level variance […] masks high semantic convergence.”
An LLM that produces thirty different textual responses to the same prompt is not thirty times unreliable; it may be converging on the same epistemic conclusion through thirty different linguistic paths. Distinguishing these two phenomena requires a framework. That is what this project provides.…
Thirty differently worded answers to the same prompt are not thirty disagreements: they can be one conclusion reached thirty ways. Measuring the wording instead of the conclusion makes a model look far less stable than it is.
The five layers, for this claim
The same core in the infographic, with the claims it touches.
Relations
- uses-method-in → C019 A machine-produced verdict counts here only after a person has recoded a sample by hand, without seeing what the machine decided, and the two agree above ninety per cent. The figure holds only if the verdict extraction passed the blind check.
- ← refines C005 Two independent findings pointing the same way is not evidence that they are connected. It is the measured gap itself that must not be joined to a representation-level finding without an experiment.
Notation
- Claim typeWhat kind of statement it is, so that the right test can be applied. Proposed until checked by hand.
- D1.2 · empirical-quantitative
- FunctionWhat a claim does for the programme: a conceptual tool, a working method, corrective evidence, a technical reference.
- corrective datum
- StanceHow the programme holds the claim: assumed, used, or contested.
- assumed
- Used in
- /lab/2026-02-28-vertical-validation-180-api-runs/ · /lab/2026-07-21-what-counts-as-a-verdict/
- Cite this
- claudiocammarano.com/en/claims/c020/