Is the scope of a result part of the claim, or a qualification added afterward?
https://github.com/research-farm/construct/blob/main/notes/walkthrough/00_READING_A_LAB.md
A percentage can travel farther than the conditions that produced it. The corpus disappears. One model becomes models. A single draw becomes typical behavior. The result grows while the evidence stays the same size.
The complete sentence
A result and its bounds should remain together. One corpus, two engines, and one quality draw describe an observation from that setting. They do not establish a general property of agents or memory systems.
Some quantities are deterministic and can be replayed exactly. Model behavior is often stochastic and needs repeated measurement. The claim should distinguish them.
Questions to carry forward
What was held constant? How many times was behavior sampled? Which quantities can be replayed? Which depend on the model, prompt, corpus, or answer surface? What would a replication need to preserve?
Bounds do not weaken a result. They keep it from becoming a different claim.