TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

infrastructure

A Contiguous Window Repaired the Stale Cache

Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.

Published Updated Story ID: mp-2026-09-17-005
Read the complete editionStory JSON

Summary

Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.

Editing a retrieved document can invalidate downstream key-value states even when the change is local. Across three model families and a factual retrieval benchmark, a contiguous window around the edit recovered at least 0.94 of the post-edit answer margin at the primary budget. Attention, KV-deviation and structural selectors did worse because scattered positions inherited surrounding staleness during real recomputation. Repair ran 13–21 times faster than full re-prefill. The advantage largely disappeared when answer-bearing text moved farther downstream, defining a practical boundary for the method.

Why it matters

Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.

Limits and context

No additional limitation was separately recorded.

Key claims

  1. Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.

    Evidence: source-2026-09-17-005

Sources

  1. arXiv preprint 2609.17983arXiv · primary research

Corrections

No corrections have been recorded for this story.