test-driver/research
tegwick 4ddb2f896c T05: the lab and its labelled mutation catalogue
lab/app.py (users, tenants, auth, resources, sharing, read/write, revoke,
audit), lab/http_api.py (JSON API + browser UI, stdlib only), 20 labelled
composable version-stamped mutations, ground-truth matrix. 48 tests pass.

Detection against the reference scenario: MECHANICAL 0/10 flagged (correct),
DEFECT 6/6, SEMANTIC 2/4 with both inert cases declared.

- F-0002: M16 and M18 initially escaped detection entirely. A use case
  protects exactly what it asserts. Resolved by adding two claims already
  stated as intent in INTENT.md; the six-mutation catalogue would never have
  surfaced this.
- test-id axis added: stable selectors survive most UI mutations, which would
  make H-001 trivially false. Mutations now vary on preserves_test_ids so the
  hypothesis is analysed split by that axis rather than rigged.
- M12 (semantic deferred revoke) and M19 (defect race) are behaviourally
  identical and asserted as such - the discrimination problem as a test.

lab/minimal.py removed; superseded by lab/app.py.

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 23:31:22 +02:00
..
concepts T05: the lab and its labelled mutation catalogue 2026-08-22 23:31:22 +02:00
decisions T03: research control plane 2026-08-22 23:11:21 +02:00
experiments T03: research control plane 2026-08-22 23:11:21 +02:00
findings T05: the lab and its labelled mutation catalogue 2026-08-22 23:31:22 +02:00
hypotheses T03: research control plane 2026-08-22 23:11:21 +02:00
README.md T03: research control plane 2026-08-22 23:11:21 +02:00

Research Control Plane

Deliberately small. This directory exists so that claims about test-driver can be falsified rather than accumulated. It is plain files — no CLI, no schema, no tooling — until there are enough readings to justify tooling.

research/
├── hypotheses/   H-NNN — a claim with a falsification condition
├── experiments/  E-NNN — a planned or executed test of a hypothesis
├── findings/     F-NNNN — findings about test-driver itself
├── concepts/     the Concept ↔ Implementation Fitness Map
└── decisions/    pointers to decisions recorded in State Hub

Identifier convention

Prefix Scope Example
H-NNN Hypothesis H-001
E-NNN Experiment E-001
F-NNNN Framework Finding F-0001
C-<slug> Concept in the fitness map C-actor-isolation
D-NN Decision, scoped to its design note D-07
TD-WP-NNNN-TNN Workplan task (State Hub) TD-WP-0002-T04

Identifiers are stable and never reused. A rejected hypothesis keeps its number.

Hypothesis lifecycle

PROPOSED → EXPERIMENTING → SUPPORTED → PRACTICALLY_VALIDATED → ARCHITECTURAL
                  └──────→ REJECTED

A hypothesis may be reopened if later evidence contradicts it. Reopening is recorded in the file, not by creating a new identifier.

Rules

  1. Every hypothesis states what would falsify it, in terms of an observable outcome, before any experiment runs. A hypothesis with no falsification condition is an opinion.
  2. Concepts with no supporting evidence are marked as such, not quietly retained. The fitness map is expected to contain unsupported entries; hiding them defeats its purpose.
  3. Subtraction counts as progress. A rejected hypothesis or a removed abstraction is a result, not a setback.