robbond/confidence-engine
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

experiment: capture live node-support semantic inputs

Browse Source
This commit is contained in:
robbond
2026-08-11 07:12:30 +01:00
parent d5db3c3cd6
commit 25f56d75e2
2 changed files with 148 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/current-handoff.md
+4
View File
@@ -377,3 +377,7 @@ Tested whether a single answer containing two independent evidence dimensions is
**What remains unproven:** Repeated-run stability; cross-domain generalisation; downstream investigation viability past Update 2+; implicit conjunction admission; whether `too_broad` conversation health eventually blocks later turns.
Configured Ollama: qwen-claude:latest at http://192.168.1.111:11434. No production code changed. Branch: `feature/user-supported-unknown-admission-v0.15`.
### Experiment 57J.28 — Live Node-Support Semantic Inputs Capture
**Classification: C — GATE BEHAVES AS EXPECTED.** On a fresh live run, both user-supported unknowns (savings realism + retention impact) were admitted with HTTP 200 at `update_applied`, zero validation errors. The answerMeaning correctly captured both dimensions. The semantic gate (`rawAnswerSupportsUnclassifiedMeaning`) passed for both via the token-count clause (5 shared content tokens >= 3), not overlap ratio. Structural fallback also valid for both nodes. Static helper evaluation agrees with actual gate behavior — live admission outcome fully explained by captured inputs. Configured Ollama: qwen-claude:latest at http://192.168.1.111:11434. Start: 7 nodes, Update 1: 9 nodes (+2). What remains unproven: token-count adequacy for paraphrased/low-overlap answers, downstream investigation viability past Update 2+, run-to-run start graph stability. No production code changed.