experiment: test decision-relative coherence

docs/current-handoff.md

@@ -58,7 +58,9 @@ Experiment 48 audited whether real graph updates populate usable unknown relatio
 
 Experiment 49 tested whether any sequence of real production updates creates two or more active unknowns referencing the same populated relationship anchor. Results: no shared anchor found in production update sequences (both Cases A and B returned separate_anchors or insufficient_data). Structural capability exists but triggering logic never produces coexisting anchors. Status closed.
 
-Experiment 50 tested whether shared edge topology from `buildInitialGraph` provides a usable coherence signal. Coherent and scattered inputs both produce identical edge topology — every unknown connects to the same summary node (kind=state) via depends_on edges, regardless of semantics. Conclusion: production edges provide only a generic shared anchor, not meaningful coherence. Status pending Rob's review.
+Experiment 50 tested whether shared edge topology from `buildInitialGraph` provides a usable coherence signal. Coherent and scattered inputs both produce identical edge topology — every unknown connects to the same summary node (kind=state) via depends_on edges, regardless of semantics. Initial shared edges are generic structural wiring, not coherence evidence. Closed (pending Rob's review).
+
+Experiment 51 tested whether decision-relative relevance distinguishes coherent from scattered unknowns better than graph topology does. Within its training vocabulary, the classifier classified all four coherent unknowns as relevant and three of four scattered unknowns as irrelevant — but one scattered question was incorrectly flagged due to identical phrasing. Outside its vocabulary (different domain or paraphrased language), the classifier could not generalise: all four coherent unknowns received `cannot_determine`. The decision target never provided semantic context, only a binary action-keyword gate. No production code changed; no active engine behaviour changed; 70 tests pass (45 new + 25 Exp 21 regression). Status pending Rob's review.
 
 ## 5. What Remains Open
 
@@ -112,7 +114,7 @@ Answer before continuing:
 
 ---
 
-*Created by Experiment 34. Updated by Experiments 38–50. Branch: `feature/user-workspace-ux-v0.7`.*
+*Created by Experiment 34. Updated by Experiments 38–51. Branch: `feature/user-workspace-ux-v0.7`.*
 
 ### Return-to-Work Note (Experiment 47)
 
@@ -122,4 +124,4 @@ Experiment 48 passively audited whether real graph updates populate usable unkno
 
 Experiment 49 tested whether production update sequences can produce a real shared anchor (two or more active unknowns sharing the same populated relationship node). Two sequential-update scenarios via `applyValidatedProposal` (Cases A and B in the new test file) consistently returned `separate_anchors` or `insufficient_data` — no coexisting active unknowns reference the same anchor. The structural capability exists (fields populate correctly via emergent reasoning), but the triggering logic never produces shared anchors within tested flows. Control cases (C–F, 20 tests) confirmed the diagnostic works correctly on controlled fixtures and all produced nodes pass schema validation. Total: 36 new tests, all passing. Branch: `feature/user-workspace-ux-v0.7`. First file to inspect: `tests/graph/shared-anchor-production-path.test.js` for results, then `docs/design-evolution-log.md` Experiment 49 section.
 
-Experiment 50 tested whether shared graph edges from `buildInitialGraph` provide a meaningful coherence signal. Two inputs — one coherent (North West expansion), one scattered (business feels stuck) — passed through identical production edge-building path. Both produced the same edge topology: four unknowns, each connecting via depends_on to the summary node (kind=state). Node-level relationship fields remain empty in both cases. Conclusion: shared-edge connectivity is structural plumbing, not coherence evidence. No structural difference exists between coherent and scattered inputs at the production graph level. Status pending Rob's review. First file: `tests/graph/initial-edge-coherence.test.js`.
+Experiment 51 tested whether the existing passive decision-relevance classifier distinguishes coherent from scattered unknowns better than graph topology did (Exp 50). Within its training vocabulary (European market entry), the classifier correctly classified all four coherent unknowns as relevant to the decision and three of four scattered unknowns as irrelevant — but one scattered question was incorrectly flagged as relevant due to identical phrasing. Outside its vocabulary (different domain: community events, or plain-English paraphrases), the classifier could not generalise: all four coherent unknowns were classified as `cannot_determine`. The decision target never provided semantic context — only a binary action-keyword gate for Rule 1 firing. No production code changed; no active engine behaviour changed; all 70 tests pass (45 new + 25 Exp 21 regression). What remains uncertain: whether phrasing-aware pattern matching or genuine semantic understanding is needed for coherence detection. Branch: `feature/user-workspace-ux-v0.7`. First file to inspect: `tests/graph/decision-relative-coherence.test.js` for the full test and results, then this handoff's Experiment 51 section.