Warden plan

28 - CR-08 (pending): Initiative attention gain

← eval suite index


tier: hermetic requires: []


28 - CR-08 (pending): Initiative attention gain

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-08 — Initiative attention gain - Statement: Initiative attention a_I improves Initiative-scoped retrieval over fitted Domain coefficients alone (a_I = 0). - Metric: nDCG@10 on Initiative-scoped held-out queries, attention arm vs a_I = 0 arm; paired bootstrap. - Dataset/inputs: ≥200 Initiative-scoped queries per workspace (~350 pooled held-out at 60% split across 3 workspaces); attention rule run with η = 0.2, γ = 0.1 over each Initiative's slow-path history. - Threshold: Positive and significant, design effect 0.02 absolute nDCG@10. If the pooled count falls short, the design effect is raised to what the count detects at 80% power and reported before scoring. - Drop condition: No significant lift removes the attention rule, leaving Initiatives as Domain groupings with a_I = 0. - Source: Anchor §10.4. - Tier: gated — requires Initiatives machinery, Dimensions, fitted coefficients.

Named precondition

Precondition: requires Initiatives machinery, Dimensions, and fitted coefficients. 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/). Fitted coefficients have 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 "'initiatives'" "$SCHEMA" || MISSING="$MISSING initiatives-tables"
grep -q "'dimensions'" "$SCHEMA" || MISSING="$MISSING dimensions-tables"

if [ -n "$MISSING" ]; then
  warden_skip "CR-08 — Initiative attention gain" "pending: requires Initiatives machinery, Dimensions, and fitted coefficients — gated criterion, precondition not built (probes missing:$MISSING)"
else
  warden_skip "CR-08 — Initiative attention gain" "schema probes now pass — upgrade this pending stub to a real plan before CR-08 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).