marius/Open_Ultra_SAST
1
0
Fork 0
mirror of https://github.com/norandom/OpenUltraSAST.git synced 2026-10-16 03:49:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

spec/steering: the decision strategy corrected: software features do not decide safety; the trace does, the pool measures and never trains

Browse Source 
Maintainer's finding of 2026-10-14 recorded in hunter-learning-loop (a dated section that overrides the shape
annotations as the model's input), its design (amendment pointing to the prover's trace) and the steering
overview's current state.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
Marius Ciepluch
2026-10-14 19:40:12 +02:00
co-authored by Claude Fable 5.1
parent 03b114cbeb
commit 03d925fffa
3 changed files with 46 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.kiro/specs/hunter-learning-loop/design.md
+7
View File
@@ -1,5 +1,12 @@
# Design: hunter-learning-loop
> **Amendment 2026-10-14.** The feature table below is the shape of the first round and is superseded as the
> model's input by the ordered trace of `access-control-prover` (design sections "trace: the ordered
> serialisation" and "cfg and CfgDominance"). The feature table remains the screen's instrument and the
> ablation's bookkeeping; the decision strategy is the one stated in requirements.md, "Decision strategy,
> corrected 2026-10-14": a rule over the trace, a zero-shot judge for the residual question, the pool for
> measurement only.
## Overview
**Purpose**: turn the LLM hunter from a hand-written prompt into a measured search stage whose inputs are an
engineered feature table and whose prompt is optimised by a program runtime, judged on held-out folds.