rubric-graded-long-context-tasks-most-gain-context-compilation-harness-comes-extracting
mechanismsingle paperpending review

On rubric-graded long-context tasks, most of the gain from a context- compilation harness comes from extracting the context's rules, exact terms and output spec into an explicit checklist placed in the prompt, not from the executable verifiers built on top of it — and the gain appears only on rule-dense tasks and on models with enough capacity, disappearing or reversing on open-ended tasks and on a small-activation model.

Ingested from a paper but not yet reviewed by a human. It is deliberately inert: it does not move any technique’s standing, does not count toward the backtest, and is excluded anywhere a claim would carry weight. Read the source before relying on it.

Capability: Losing information in long inputs

Observed on

Long novel contexts (median 20K characters) graded against 5-20 all-or-nothing rubric criteria; four large open models; gains concentrated in rule/procedure-heavy categories and ab.

Sources

  • Ablation on 1,899 CL-bench tasks, one model (Kimi K2.5), temperature 0, single GPT-5.1 judge: full pipeline 21.40% vs vanilla 15.40%; removing checklist injection -3.07pp, removing correction loop -1.28pp, verifier execution alone ~0.53pp. Component isolation not repeated on the other three models. LongBench-v2 probe shows aggregate accuracy below vanilla, supporting the scope limit. Absolute pass rates are low throughout, so deltas are on a small base.
Status: pending-reviewLast checked: 2026-09-07Evidence activity: not checked yet
Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

Notes

Ingested unreviewed on 2026-09-07 and deliberately inert until a human endorses it: it does not move a technique standing, does not count toward the backtest, and is excluded anywhere a claim would carry weight. Drafted confidence: low. Falsifier as drafted: An ablation on other models or benchmarks where removing the verifier/correction loop costs more pass rate than removing the checklist injection, or where the checklist gives similar gains on open-ended tasks. Proposed technique, not yet catalogued: Compile context into a typed rule IR and inject it as a checklist.