Update eval_benchmarking.md

This commit is contained in:
PSBigBig 2025-09-05 10:48:49 +08:00 committed by GitHub
parent e722f1ed68
commit 547d9c6167
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -1,5 +1,22 @@
# Eval Benchmarking — Protocols, Targets, and Reporting
<details>
<summary><strong>🧭 Quick Return to Map</strong></summary>
<br>
> You are in a sub-page of **Eval**.
> To reorient, go back here:
>
> - [**Eval** — model evaluation and benchmarking](./README.md)
> - [**WFGY Global Fix Map** — main Emergency Room, 300+ structured fixes](../README.md)
> - [**WFGY Problem Map 1.0** — 16 reproducible failure modes](../../README.md)
>
> Think of this page as a desk within a ward.
> If you need the full triage and all prescriptions, return to the Emergency Room lobby.
</details>
This page defines a clean, repeatable way to benchmark your pipeline and prove that a fix actually improved behavior. It uses the same WFGY instruments as everywhere else: ΔS for semantic stress, λ\_observe for stability, and E\_resonance for coherence over long windows.
## Open these first