When the Question Changes: Recoverable Evidence Under a Context Budget

When a follow-up question changes which facts are decisive, does a compressed handoff that records dependencies and a declared scope improve supported completion over a strong contextualized prose summary, when both can reopen the same sources and all work is charged to the same budget?

Studies a bounded handoff with supported facts, relations, a declared scope and source locators, and an explicit scope check when the question changes. Executed finite constructed diagnostics: 28 named checks, all 15 partitions of a four-world example, 60 deterministic recompressions, and twelve developer fixtures. E17-B is proposed, not run or preregistered; H17-1/H17-2/H17-3 are untested. No new language-model benchmark, Noetis performance gain, or deployment.

• Constructed example: a one-bit message that answers the release question perfectly leaves a 3/4 accuracy ceiling on a later test-status question under a stipulated uniform distribution. A possibility result, not model performance.
• Exact enumeration: 5, 2 and 1 of 15 partitions preserve every answer as the question family grows, needing at least 2, 3 and 4 message states. None of 60 deterministic recompressions restores a lost distinction.

• E17-A Exact finite constructed recoverability diagnostics Executed (diagnostic)
• E17-B Frozen-handoff question-change study (P0/P1/S0/S1) Proposed

• H17-1 Under the same explicit scope check, a structured record improves changed-question supported completion over strong prose without unacceptable damage or cost.
• H17-2 An explicit scope check recovers confident omissions on changed-question cases.
• H17-3 Reopening helps only when it supplies usable evidence.

Proposed protocol only. No Noetis behavior, inference, routing, billing, risk value, or collection-gate change.

• Does a structured record beat strong prose under the same explicit scope check at equal total cost?
• Does a scope check recover confident omissions beyond unrestricted discretionary lookup?
• Does reopening help only when it actually exposes usable evidence?

Builds on Round 16, Round 15, Round 14, Round 13, Round 10, Round 9. Continued in Round 20, Round 19, Round 18.