Plan Records

plans / frontmatter · source

Frontmatter and status

---
status: draft
summary: Determine whether the effect survives two control families
next_action: Design the first pilot
owner: researcher
reviewer: collaborator
current_phase: Phase 1
created: YYYY-MM-DD
updated: YYYY-MM-DD
---

Required frontmatter is status, summary, next_action, created, updated. Optional fields are owner, reviewer, current_phase, gate, revisit_when, promote_when, superseded_by, abandoned_because. Use YYYY-MM-DD-lowercase-topic.md filenames. Status is draft, active, blocked, gated, backlog, superseded, completed, abandoned. The body records the objective, existing evidence, bounded phases with gates, risks and controls, and terminal conditions. next_action is one handoff pointer, not a task queue. A terminal plan leaves it empty. A completed plan adds a Completion report and Evidence; a superseded or abandoned plan adds Disposition and Evidence. Active plans live directly in plans/; other statuses live in matching subdirectories. Gated, backlog, superseded, and abandoned plans carry the status-specific reason and reconsideration fields. A plan that answered its question negatively is completed, not abandoned; the gate firing is the experiment working.

Legacy spellings complete (for completed), proposed (for draft) validate with a warning, and a plans/complete/ directory is accepted for them. Run the validator with --write-plan-index to regenerate plans/README.md. Use --format json as the stable diagnostics boundary for dashboards, editors, and external research tools.

plans / review gates

Phases and review gates

Review the plan twice at minimum: before execution and after evidence returns. At a phase gate, the human chooses whether to continue, revise, wait, or close. A gated follow-up pauses again before any new job is submitted. A gate is a testable external blocker: data, compute, a dependency, a collaborator decision. A plan that is viable and waiting for someone to start it is backlog with a revisit cadence.

plans / confirmation reserve · source

Confirmation reserve

A plan that will end in a confirmatory claim carries ## Confirmation reserve, written at creation and before any exploration, with both **Held back:** and **Decision rule:**. A reserve written after exploration is not a reserve, so this is the one plan section that cannot be added later.

## Confirmation reserve

**Reserved:** the draw-1 scene set (`DRAW_STRIDE = 1000`, as used by
[[EXP-211-second-architecture-replication]]) for every work package in this plan, and the `origin`
value domain from [[EXP-209-cross-domain-entity-transfer]]. A WP may not use either for design or
piloting. Each WP exposes its frozen analysis to draw 1 once for adjudication; an outcome-informed
repair spends that reserve and requires a new untouched pool.

**Decision rule:** a WP's mechanism claim is accepted only if, on the reserved draw-1 scene set, the
package's own pre-registered primary statistic keeps its sign with the 95% scene-clustered interval
excluding its registered null, and the sign is unanimous across at least 12 of 15 blocks. A WP that
clears on draw 0 and fails this on draw 1 is recorded as draw-specific and its claim is withdrawn, not
rescoped.

plans / completion · source

Completion report

The executing session writes ## Completion report before setting the terminal status: the disposition and the evidence that caused it, per-goal outcomes (met, unmet, void) linking the record that carries each, limitations, follow-ups with any successor plan named, and artifact status at closure. Numbers stay in experiments and findings; the report links them. Plans that predate the convention record the same thing under other headings, and the validator recognizes Completion report, Completion, Completion note, Completion audit, Outcome, Execution outcome, Execution result, Closed, Disposition by exact heading, case insensitively, without asking for a rename.

---
status: complete
updated: 2026-08-04
summary: "Reality leak in belief attribution is 0.682 under a bare continuation and 0.000 under an explicit question. EXP-167 shows that discourse placement and the number of examples explain the contrast, not query form. Under both controls, all three forms have zero reality leak. The causal test was therefore unnecessary and was not run."
next_action: null
---

## Outcome

Closed 2026-08-04 by [[EXP-167-belief-form-placement-kshot]] without running the causal test.

- **No residual query-form effect.** Under a document-licensing preamble plus k=8 demonstrations, the
  three query forms span **0.000**: all at 1.000. The apparent form main effect (0.789 vs 1.000) is
  produced entirely by the single uncontrolled cell.
- **Either control alone repairs the continuation.** 0.325 with neither; 0.831 with a preamble only;
  1.000 with demonstrations only.
…
What survives is a methods note for Paper 2, not a mechanism claim …

plans / retraction · source

Retraction notice

When an experiment later corrects a value a terminal plan stated as its outcome, the plan keeps the original text and gains a notice beneath it beginning **Retracted YYYY-MM-DD., giving the corrected values, the retracting record, and the date the correction was applied. Annotate, never rewrite; point, do not restate. Write the notice when the correction is applied, not when it is reported, and let the retracting experiment state the superseded values and sweep the notebook for them.

plans / agent plans

Native agent plans and notebook plans

Use Claude Code plan mode or Codex's task and multi-agent surfaces to reason about the immediate work. Pass the notebook plan's path and phase name to another executor instead of copying the contract into a prompt. The plan records scope and review decisions. Paid compute, destructive actions, publication, external writes, and unattended execution still require their own authorization.