Warden plan

28 - CR-12 (pending): Fast/slow compounding

tier: hermetic requires: []

28 - CR-12 (pending): Fast/slow compounding

Pending stub — GATED criterion. The precondition below is not built; this plan reports the criterion as pending (skip, never fail) until it lands. When it does, replace this stub with a real plan in the shape of 25-cr-18 / 26-cr-25 / 27-cr-20.

Criterion implemented (verbatim from the register)

Register: ~/.studio/master.withrobin.ai/project/rfc.one/criteria-register.md (status there: PENDING OWNER ACCEPTANCE; accepted by the 2026-08-31 proxy screen).

### CR-12 — Fast/slow compounding - Statement: Accumulated slow-path work improves the fast path over time on a frozen corpus. - Metric: Primary: fast-path nDCG@10 gain from m = 0 to m = 20 on the clean replay series, paired bootstrap over N queries. Secondary: no checkpoint significantly below its predecessor; HyDE escalation rate falls; p95 latency does not rise. - Dataset/inputs: Clean replay series per workspace from a fresh Signals-only copy; m artifact requests and N ≥ 60 read queries per workspace (180 pooled) taken from one logged window in logged order (author-labeled → artifact runs, retrieve-labeled → reads); checkpoints m = 0, 5, 10, 20; coefficients fit once at final checkpoint; post-replay pooling/judging pass for new Claims. - Threshold: Gain positive and significant, design effect 0.03. - Drop condition: No significant gain by m = 20 means slow-path outputs are not reused — the compounding claim fails (feeds CR-19). - Source: Anchor §10.5. - Tier: gated — requires full stack (Claims, slow path, fast path) plus the replay harness.

Named precondition

Precondition: requires the full stack (Claims, slow path, fast path) plus the replay harness. Not built at HEAD 7f379974 (verified 2026-08-31: no 'claims', 'dimensions', or 'initiatives' tables in server/src/db/schema.ts, and no conflicts_with edges anywhere in server/src or packages/). The replay harness has no code marker to probe.

Skip guard

set -uo pipefail
source "$WARDEN_LIB/assert.sh"
cd "${PROJECT_ROOT:-$(git rev-parse --show-toplevel)}"

SCHEMA=server/src/db/schema.ts
MISSING=""
grep -q "'claims'" "$SCHEMA" || MISSING="$MISSING claims-tables"

if [ -n "$MISSING" ]; then
  warden_skip "CR-12 — Fast/slow compounding" "pending: requires the full stack (Claims, slow path, fast path) plus the replay harness — gated criterion, precondition not built (probes missing:$MISSING)"
else
  warden_skip "CR-12 — Fast/slow compounding" "schema probes now pass — upgrade this pending stub to a real plan before CR-12 can bind (probes are heuristic, not proof)"
fi

Shape (note for the next author)

Pending stub, hermetic on purpose: the guard reads the checkout only and emits skip in every branch, so this plan can never red a run — the criterion surfaces in every summary as pending with its precondition named. The probes are heuristic activation bells, not proof: quoted table names (and conflicts_with where the contradiction check is a precondition) flip the detail text when the machinery lands. The real plan must quote the criterion verbatim, turn its thresholds into warden_pass/warden_fail gates, and follow the conventions the three runnable plans set: machine-local fixtures (25-cr-18), NLI probe and versioned judge prompts (26-cr-25), data-keyed guard activation (27-cr-20).