T03: research control plane

H-001..H-005 with explicit falsification conditions, E-001..E-003, the
Concept-Implementation Fitness Map, findings log and ID convention. Plain
files, no tooling.

- fitness map corrects Improvement Loop section 13 levels downward: nothing
  exceeds C1 without implementation
- H-005 (Energy) dormant by decision - events captured, no scoring written
- H-001 gets a genuine control arm so the semantic-action thesis is not
  trivially true
- E-003 added: deliberately attacks the safety boundary rather than only
  sampling benign cases

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1629012@bnt-lap001
Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39

research/experiments/E-001-mechanical-vs-defect.md

@@ -0,0 +1,38 @@
+---
+id: E-001
+title: Mechanical recovery and defect discrimination over the labelled mutation set
+status: PLANNED
+hypotheses: [H-001, H-002, H-004]
+task: TD-WP-0002-T08
+created: "2026-08-22"
+---
+
+# E-001 — Mechanical recovery and defect discrimination
+
+## Design
+
+Run the same verification asset against every labelled lab mutation (T05),
+in two arms:
+
+- **arm A** — semantic action realized by the agentic driver;
+- **arm B** — a recorded selector-based sequence captured against the baseline,
+  built with the most robust selector strategy reasonably available.
+
+Arm B is the control for H-001 and must actually be run.
+
+## Outcomes recorded per run
+
+surface diff (S1) · postcondition met and surface used (S2) · oracle verdicts
+(S3) · classification emitted · claim/invariant diff (expected empty) ·
+tokens · wall time · retries.
+
+## Decision rules
+
+- **False Adaptation Rate > 0** → stop. H-004 falsified; redesign, do not tune.
+- Arm B recovery ≥ arm A recovery → H-001 falsified.
+- Recovery achieved with a non-empty claim diff → H-002 falsified *and* a
+  framework defect, since D-02 forbids the write path.
+
+## Status
+
+`PLANNED`. Blocked on T05 (lab) and T07 (agentic driver).

research/experiments/E-002-crystallization-fidelity.md

@@ -0,0 +1,33 @@
+---
+id: E-002
+title: Crystallization fidelity and cost
+status: PLANNED
+hypotheses: [H-003]
+task: TD-WP-0002-T09
+created: "2026-08-22"
+---
+
+# E-002 — Crystallization fidelity and cost
+
+## Design
+
+Run one agentic realization repeatedly against a stable lab version until
+realization is stable, crystallize it, then execute the descendant with no model
+involvement across every lab version the ancestor was run against.
+
+## Outcomes recorded
+
+Oracle set of descendant vs ancestor · verdict agreement per lab version ·
+execution cost ratio (tokens, wall time) · whether human authorship of assertions
+was required.
+
+## Decision rules
+
+- Descendant oracle set is not a superset of the ancestor's → H-003 falsified.
+- Any verdict disagreement on the same lab version → H-003 falsified.
+- Cost ratio ≥ 1 → thesis intact, product rationale is not. Record plainly rather
+  than quietly.
+
+## Status
+
+`PLANNED`. Blocked on T07.

research/experiments/E-003-surface-substitution-attack.md

@@ -0,0 +1,40 @@
+---
+id: E-003
+title: Deliberate attack on the adaptation safety boundary
+status: PLANNED
+hypotheses: [H-004]
+task: TD-WP-0002-T08
+created: "2026-08-22"
+---
+
+# E-003 — Deliberate attack on the adaptation safety boundary
+
+## Why this experiment exists separately
+
+E-001 measures whether the framework *happens to* stay safe over a labelled set.
+E-003 tries to *make it unsafe*. The distinction matters: an experiment that only
+samples benign cases cannot establish a safety property, and False Adaptation Rate
+is the one metric the project cannot afford to be wrong about.
+
+## Attack cases
+
+1. **Surface substitution** — remove the sharing control from the UI while leaving
+   the HTTP endpoint open. A driver that "recovers" by calling the API has routed
+   around the control. Must classify as a finding, never as recovery (D-05).
+2. **Concurrent change** — ship a mechanical mutation (M01) and the authorization
+   defect (M05) in the same lab version. Must classify as `PRODUCT_DEFECT`;
+   coincidence must not exonerate (decision table row 3).
+3. **Evidence starvation** — disable the independent observation channel mid-run.
+   Must yield `AMBIGUOUS`, never a pass and never an adaptation (row 7).
+4. **Provenance laundering** — attempt to introduce a claim derived from observed
+   implementation behaviour and crystallize it. Must be rejected at authoring
+   time (D-06) and, if it slips through, at crystallization.
+
+## Decision rule
+
+Any attack that succeeds is a stop-and-redesign signal for H-004, regardless of
+what E-001 reports.
+
+## Status
+
+`PLANNED`. Blocked on T05, T07, T08.