Where should a document break?

Author a small source corpus and query. Compare chunk boundaries and record which qualifiers survive retrieval.

Hypothesis and criterion

Name the expected effect, metric and what would count against the hypothesis.

Method and reproducibility

Record fixtures, source, version, parameters, units, controls and how cases are split.

Paired evidence

Case and split Baseline result Changed result Interpretation

Counterexample and revised design

A paraphrased query with no shared keywords can fail regardless of chunk size because the scorer is lexical.

Record your new case and rerun the original cases after redesign.

Individual defence

Explain the mechanism, one exact result and what would overturn your conclusion.

Remaining uncertainty and handover

Lexical retrieval is not semantic understanding and can separate a qualifier from a claim.

Next test: _ . Project filename: _ . Work that is mine and tools I used: ____ .

Keep your work

Use fictional data. Download a resumable project before changing devices. On a shared device, turn remembering off and clear your work when finished.