Freeze the E001 three-ring observation chamber#5
Conversation
There was a problem hiding this comment.
Pull request overview
This PR formalizes experiment E001 (Three-Ring Bounded Flow) as a frozen, implementation-independent specification (E1), and records a reversible Stage A runtime decision (ADR 0001) to ensure the upcoming simulator work can be evaluated deterministically against a stable comparison contract.
Changes:
- Adds a standalone E001 v0.1 specification covering hypotheses, scenarios, invariants, determinism rules, trace contract, metrics, and the canonical 72-run matrix.
- Introduces ADR 0001 selecting Python 3.13 + standard library only as a reversible Stage A trial runtime for E001.
- Updates repository/docs indices and readiness checklists to reflect E001’s transition from Planned (E0) to Specified (E1), and adds results/observations directory READMEs to define evidence organization.
Reviewed changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
tests/README.md |
Adds a rule requiring E001 tests to map to the ten hard invariants in the frozen spec. |
src/README.md |
Links implementation expectations to ADR 0001 and the frozen E001 spec; clarifies Python as a reversible trial runtime. |
REPOSITORY_READINESS.md |
Marks governance/readiness items as completed and updates the critical path to the post-spec implementation sequence. |
registry/CONCEPT_REGISTRY.md |
Updates E001 status from Planned (E0) to Specified (E1) with a clarified description. |
experiments/README.md |
Updates E001 status to “Specified — E1” and links to the frozen spec. |
experiments/E001/results/README.md |
Defines the expected on-repo evidence layout and immutability rules for generated results. |
experiments/E001/observations/README.md |
Establishes a process and structure for capturing emergent observations separately from directed evidence. |
experiments/E001/EXPERIMENT__E001__THREE_RING_BOUNDED_FLOW__v0.1__2026-07-13.md |
Adds the full E001 frozen experiment specification (workload scenarios, equivalence contract, trace schema, metrics, invariants, run matrix, exit rules). |
docs/decisions/README.md |
Adds a “Current decisions” index linking ADR 0001. |
docs/decisions/ADR__0001__PYTHON_STANDARD_LIBRARY_FOR_E001__2026-07-13.md |
Records the reversible decision to use Python 3.13 stdlib-only for E001 Stage A and the reversal criteria. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 996727ca1a
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| event_type | ||
| loop_id | ||
| interlock_id | ||
| work_id |
There was a problem hiding this comment.
This canonical trace contract records only work_id, but the linked Minimal Interlock Contract requires proposal_id as the idempotence and causal-correlation key (specs/CBF__SPEC__MINIMAL_INTERLOCK_CONTRACT__v0.1__2026-07-10.md:19). In S7/S8 replay and duplicate cases, a trace that lacks proposal identity cannot distinguish a replayed proposal from another event for the same work item, so H3 and invariant 10 cannot be audited deterministically even if the simulator behaves correctly.
Useful? React with 👍 / 👎.
|
|
||
| ### Evidence supporting the local CBF hypothesis | ||
|
|
||
| E001-H2 receives support if C3 has a smaller fault radius or more healthy-progress ticks than C2 in S4 or S5, while preserving all invariants and avoiding permanent starvation. |
There was a problem hiding this comment.
The H2 hypothesis requires both more healthy-loop progress and fewer affected healthy loops during slow or failed-neighbor intervals, but this support rule accepts either metric in either S4 or S5. That can mark C3 as supporting the local-fault-containment claim even when it only improves one disturbance case or improves progress while increasing fault radius, which would corrupt the aggregate interpretation after the frozen 72-run matrix.
Useful? React with 👍 / 👎.
Purpose
Freeze E001's hypotheses, comparison contract, deterministic run matrix, invariants, evidence format, and reversible runtime choice before simulator implementation.
Research identity
SW.EXPERIMENT.E001What this adds
Scope boundary
This PR does not implement the simulator, produce results, activate pneumatic dynamics, import the recovered Biological Pneumatic Engine, or select a permanent Superloop substrate.
Validation
git diff --checkpassesFalsification boundary
A hard-invariant violation invalidates a run regardless of favorable aggregate metrics. A safe result with no containment or progress advantage is preserved as a negative result rather than reinterpreted as success.
Review focus