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

experiment: test known-vs-uncertain consequence structure

Browse Source
This commit is contained in:
robbond
2026-08-12 16:59:56 +01:00
parent c3c5351143
commit 8856e66147
2 changed files with 236 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/current-handoff.md
+21 -4
View File
@@ -345,15 +345,32 @@ The engine extracted all three semantic elements in userSupportedMeaning and cre
---
### Experiment 58B.2 — Verified Uncertainty Resolution
### Experiment 59A.3 — Known vs Uncertain Consequence Structure
**Objective:** When the user explicitly verifies a figure and states confidence in its realism, does the engine resolve the existing savings-realism uncertainty rather than merely changing its value?
**Branch:** `feature/question-formulation-v0.24`
**Date:** 2026-08-12
**Status:** Complete
**Following:** 59A.2 which showed partial decomposition but collapsed epistemic states into one unknown node. This isolates the known-vs-uncertain distinction without the £2m-resolution step.
**Classification: A — UNCERTAINTY CORRECTLY RESOLVED.** One update-only call. The engine correctly resolved `n_savings_realism` (status unknown→resolved), included it in `resolvedUnknownNodeIds`, preserved the £2m figure as "£2,000,000" with verification captured in the reason field ("User verified the projected annual savings including lease exit costs are realistic."). No duplicate uncertainty created. No next question produced — correctly reflecting that no consequential unresolved issue remains. Configured Ollama: qwen-claude:latest at http://192.168.1.111:11434. No production code changed.
**Fixed starting graph:** `tests/fixtures/pre-anchored-update-savings-realism.json`
**Fixed answer:** "We know that relocating would cause two senior engineers to leave. What I don't know is whether losing them would delay delivery, or by how many months."
**Execution:** qwen-claude:latest at http://192.168.1.111:11434. startCalls=0, updateCalls=1, totalCalls=1.
**Result:** UPDATE 422 rejected at `proposal_compatibility` — "selectedQuestion must be a single non-compound question". No selectedQuestion was produced (null).
**Rejected proposal snapshot assessment:**
- Known engineer loss: SEPARATE KNOWN STRUCTURE (dedicated observation node n_talent_departure, kind=observation)
- Delivery impact: SEPARATE UNRESOLVED STRUCTURE (dedicated unknown node n_delivery_delay_impact, kind=unknown, status=unknown)
- Epistemic separation: CLEARLY SEPARATED — two distinct nodes with different kinds and statuses
- Relationship: TYPED / STRUCTURAL LINK (affects/depends_on fields + typed edge between the two nodes)
- Granularity: CORRECTLY SEPARATED — known consequence is an observation node; uncertain consequence is an unknown node
**Classification: A — CORRECT EPISMIC DECOMPOSITION.** The model created separate structural objects with distinct epistemic states (observation vs unknown), connected by typed edges. This directly improves on 59A.2 where both consequences were compressed into one unknown node. The rejection was caused by missing selectedQuestion, not by semantic reasoning failure — the rejected snapshot demonstrates correct structural decomposition. Full record in `docs/experiment-59a3.md`. Configured Ollama: qwen-claude:latest at http://192.168.1.111:11434. No production code changed.
---
### Experiment 57J.80 — Incremental Meaning on Existing Uncertainty (PRE-ANCHORED)
### Experiment 58B.2 — Incremental Meaning on Existing Uncertainty (PRE-ANCHORED)
**Objective:** When a savings-realism uncertainty already exists and the user supplies new concrete information relevant to it, does the model emit `structuralActionRequired=true`, preserve that new information structurally, and avoid creating a duplicate equivalent uncertainty?