test-driver/research/experiments/E-001-mechanical-vs-defect.md
tegwick bec7fdc465 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
2026-08-22 23:11:21 +02:00

1.2 KiB

id title status hypotheses task created
E-001 Mechanical recovery and defect discrimination over the labelled mutation set PLANNED
H-001
H-002
H-004
TD-WP-0002-T08 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).