Codex
d8a29bfbdd
Implement approved specification #32 and tickets #33-#37. Keep host authentication server-verified and pin session interaction language. Compile scoped base selectors for browser compatibility and retain full gutters during CSS pruning.
28 lines
1.3 KiB
Markdown
28 lines
1.3 KiB
Markdown
# Question rewriting technique
|
|
|
|
Adapted from the "rephrase question" step of AV-SQL: decompose the question into
|
|
explicit conditions, without losing information.
|
|
|
|
The rewritten question must:
|
|
|
|
1. Make the population explicit (who/what is counted or selected) using the data
|
|
model's terms (e.g. "distinct patients in dim_patient").
|
|
2. Make every condition an explicit, numbered clause: time window, included/excluded
|
|
events, thresholds, states.
|
|
3. Replace ambiguous terms with the concepts clarified in Phase 1, citing the
|
|
evidence that defines them when it exists (evidence id in parentheses).
|
|
4. Make the expected output explicit: count, list, aggregate, trend.
|
|
5. Write the persisted question document in the workspace language, in a form a second
|
|
reviewer would understand without having seen the conversation. Explanations and
|
|
choices addressed to the reviewer use the manifest's interaction_language; preserve
|
|
domain terms, identifiers and quoted values in either presentation.
|
|
|
|
Format of the proposal to the reviewer:
|
|
|
|
> **Rewritten question:** <text>
|
|
> **Conditions:** 1) ... 2) ... 3) ...
|
|
> **Assumptions used:** <list with reference to decisions>
|
|
> **Expected output:** <shape of the result>
|
|
|
|
Iterate based on corrections. Do not proceed to Phase 4 without confirmation.
|