Bridge-Card Sign-Off Procedure — Plan v3

Date: 2026-05-12 Status: ready for pilot Target schema version on adoption: v0d.7 Pilot scope: the 5 proposed bridge cards in wiki/.audit/weave-pass3-run3-2026-05-08.md

v3 changes from v2: integrates adversarial reviewer findings (Reviewer X, Reviewer Y; both reports in wiki/.audit/bridge-card-signoff-plan-review-{X,Y}-2026-05-12.md). Pushback rationale documented inline in the relevant sections.

1. Background

The wiki's bridge-card layer (introduced in schema v0d.5, 2026-05-08) stages typed cross-page relations as "proposed" audit artifacts. Each card has 10 fields plus an Approved by maintainer: line that must carry a date before apply-mode writes are authorized. Schema v0d.5 is silent on (a) who the maintainer is, and (b) what discipline sign-off requires.

This document specifies a procedure for Claude-as-maintainer sign-off that is structurally non-rubber-stamping. The core load-bearing insight: the procedure must protect against bias not only at the per-card reviewer level (math-olympiad's dual context isolation) but also at the adjudication seam (where two adversarial reviewers independently identified the highest-severity defect in plan v2 — main-thread adjudicator collapse).

2. Architecture

2.1 Three reviewer roles + one pre-step interpretation-check + one adjudicator subagent

Stage Role Stance Method
Pre-step I — interpretation-checker (1 subagent for the batch) reading-pluralist per card, generates 2-3 alternative readings (different Primary home, Bridge type, relation specification); marks trivial-vs-non-trivial; output read by A/B/C
Per-card A — gate-applier supportive structural applies the 7-test schema gate (§3)
Per-card B — adversarial-attacker hostile / math-olympiad-style probes against the 16-pattern failure-mode taxonomy (§4) with MP-scholarship-context briefing
Per-card C — evidence-tracer empirical verifies anchors against extraction notes, source pages, and raw, including the General Rule 18 local-context check
Adjudication D — adjudicator subagent (1 subagent for the batch) mechanical-decisional reads the 3 reports per card + card text + taxonomy + dependency map; produces a per-card recommendation under the quorum rule

For a 5-card batch: 1 interpretation-checker + 2 agents per role × 3 reviewer roles + 1 adjudicator = 8 agent invocations. Each per-card reviewer agent handles 2-3 cards. Each card receives 1 interpretation map + 3 reviews (one A, one B, one C) + 1 adjudicator recommendation.

All agents: Opus 4.7, read-only tools (Read, Grep, Glob, Write — Write scoped to per-agent subdirectory).

Note on pre-step interpretation check. Adapted from math-olympiad §1 ("Interpretation check, catches 50/63 of one class of errors"). The interpretation map is adversarial context, not pro-card reasoning — it expands the question (what are the alternative readings) without answering it. A/B/C reviewers see the map alongside their card; their job is then to evaluate the card's stated reading against the alternatives the interpretation-checker named.

2.2 Dual context isolation

Each subagent receives only:

  • The bridge card's text (with strip-pass applied for Roles B and C; see §3.5)
  • The interpretation map (output of the pre-step)
  • Permission to read cited anchors (silent-keys report, extraction notes, source pages, raw — with discipline; see §6)

No subagent receives:

  • The framing prose of the Pass 3 report that motivated the card
  • The silent-keys Phase 2 verdict prose
  • Other reviewers' outputs (in this run or prior runs)
  • This plan document (bridge-card-signoff-plan-2026-05-12.md) or its review reports

Subagent prompt language (replacing v2's "you are the only reviewer"): "You are reviewing this bridge card independently. You have no information about whether or how this card has been reviewed elsewhere. Do not speculate about other reviews; reason from the card and the cited anchors." This is operational honesty about isolation rather than a contestable claim of singularity.

Subagent definitions are self-contained: the schema gate, the pattern taxonomy, and the verdict format are embedded in the prompt, NOT loaded from weave/SKILL.md. See §17 for the skill-loading discipline.

2.3 File-path isolation, not worktrees

Each agent writes to a dedicated subdirectory. No agent reads peer directories.

wiki/.audit/bridge-card-signoff/run-N/
  interpretation-map.md             # single output from the pre-step
  role-A/agent-1/card-1.hypothesis.md
  role-A/agent-1/card-1.report.md
  ...
  role-C/agent-2/card-5.report.md
  adjudication/per-card-recommendations.md   # output of adjudicator subagent
  adjudication.md                            # main-thread's ratification log

3. The schema gate (Role A — 7 tests)

  1. Anchor traceability. Every evidence anchor traces to silent-keys report / extraction note / source page / verified raw passage.
  2. Counterpressure has a counter-test. A specific empirical or textual check that, if executed, could falsify the bridge.
  3. Apply-as specificity. Each apply-as item names target page, target section, target relation type, and the attestations cited.
  4. Single-source promotion blocker present where applicable.
  5. Primary home selection justified, especially where the silent-keys report left it ambiguous.
  6. Counterpressure field present and specific. The card's Counterpressure field states at least one objection that names a check that could be performed (rather than gesturing at "could be wrong"). (Replaces v2's "Adversarial restatement (light)" framing; adversarial work is fully Role B's job per X-D6.)
  7. Apply-as wikilinks resolve. Every wikilink in the Apply-as list resolves to an existing wiki page (per Glob over wiki/{sources,concepts,entities,questions}). Wikilinks in the Note-on-Primary-home paragraphs are checked separately and flagged if they would seed apply-mode confusion. (New per X-D13. The wiki's existing dead-link risk is checked before sign-off, not after.)

3.5 Strip-bridge-prose pre-pass (Roles B and C only)

Per X-D4 (math-olympiad's #1 lever, "strip thinking before verifying"): Roles B and C receive a stripped version of the card. The strip removes reasoning trace and keeps structural content.

Strip what:

  • "What it makes visible" field (the polished claim-prose)
  • "Note on Primary home selection" paragraphs (the drafter's argument for primary-home choice)
  • Relation glosses (the prose after each relation bullet's [[page-A]] -> [[page-B]] type label)

Keep:

  • Status, Bridge type, Primary home, Secondary homes
  • Relation bullets (page → page → type label, but not the gloss)
  • Evidence anchors (the bare list)
  • Evidence status
  • Counterpressure (kept; it's adversarial content, not pro-card reasoning)
  • Counter-test
  • Apply-as items
  • Single-source promotion blocker (kept verbatim)

Role A receives the unstripped card — Role A's gate includes test #6 (Counterpressure specificity) and is checking the prose, so the prose is part of what Role A evaluates.

The strip is performed by main-thread before subagent spawn, written to a separate stripped-card file each subagent reads. The strip is mechanical (regex or section-header-based), not a judgment call.

Why it matters: the "What it makes visible" field opens with polished claims ("institution's mechanism is neither pure event nor pure residue — it is the verb-form déposer"); a reviewer reading that is reading the conclusion before checking the premises. Math-olympiad's strip-thinking discipline applies directly.

4. The adversarial taxonomy (Role B — 16 patterns)

Numbered for stable reference. Original 11 patterns from v2; pattern #1 split into #1a + #1b; 5 patterns added per reviewer findings.

v2-original patterns (refined)

  • #1a Lexical laundering. Secondary author's term presented as the primary author's term. Check: does any anchor cite the primary author's own text using this terminology, or only secondary commentary?
  • #1b Scaffolding promotion (new sub-pattern per Y missing-pattern C). Secondary author's organizing scaffolding (a term they coined to organize their reading of the primary author) presented as a stable primary-author-corpus register. Check: is the term's function in the cited secondary literature scaffolding (organizing the secondary author's reading) or attested (a stable corpus register)? Cards 1, 2, 4 in run3 are at risk.
  • #2 Single-source promotion creep. Card claims single-source with blocker but apply-as items upgrade to claim/motif moves. Check: does any apply-as item, executed as written, write a claims.md entry or a motifs.md HUB/STRUCTURAL upgrade?
  • #3 False genealogy. Typed connection asserts "is a middle term between" / "is a reformulation of" without chain attested. Check: does evidence attest the chain, or only the endpoints?
  • #4 Anchor-counterpressure inversion. Counter-test unfalsifiable, or bridge already fails it. Check: would the bridge survive its own counter-test if executed?
  • #5 Primary home arbitrariness. Home-selection rationale could equally support another home. Check: does the justification appeal to features unique to the selected home?
  • #6 Apply-as scope creep. Apply-as exceeds evidence. Check: does each apply-as item have a directly-warranting evidence anchor?
  • #7 Bridge-type conflation. Mechanism / modal-temporal / mechanism-attitudinal mismatched with evidence. Check: do anchors attest the claimed type or a different one?
  • #8 Hovering register. Vague typed-connection language papers over absent specifics. Check: is each typed connection specific enough that a maintainer could write the corresponding concept-page subsection?
  • #9 Fabricated-citation pattern (per General Rule 16 / Faul incident). Check: does every cited source / page / line exist in the wiki's source inventory and raw corpus?
  • #10 "Would settle longstanding controversy" (math-olympiad pattern #4 translated). Check: does the bridge's general form encroach on a contested interpretive question? Applied with the MP-scholarship-context briefing (§4.5).
  • #11 Too-clean-bridge / extract-the-general-lemma (math-olympiad pattern #40 translated). Check: extract the general claim; look for a counterexample in MP corpus or adjacent. If general form falsifiable, what makes THIS instance special?

New patterns (per adversarial reviewer findings)

  • #12 Motifs-weight tipping (per X-D7). Check: would the bridge's typed-connection additions, combined with existing typed connections on the same Primary/Secondary-home pages, tip an existing motifs.md THEME entry to STRUCTURAL or STRUCTURAL to HUB? Construct the post-apply attestation graph for the relevant motif; compare to current weight class. If it tips, the bridge requires motifs-delta authorization, not bridge-card sign-off.
  • #14 MP-period miscoding (per Y missing-pattern B). Check: If the bridge crosses MP-period boundaries (PoP 1945 / 1953-55 transition / V&I-era 1959-61 / institution-lectures 1954-55 / late notes), does the bridge name the periodization explicitly, and does the relation language acknowledge the chronology? A bridge that asserts enacts across periods without naming the periodization is mishandling the corpus. Cards 2 and 4 in run3 are at risk.
  • #15 Claim-status laundering via subsection-write carve-out (per Y missing-pattern D). Check: does any apply-as item write content whose epistemic force matches a live or supported claim, without the claim-promotion gate being run? If yes, either downgrade the apply-as item to Open Questions framing, or require the claim-promotion gate before sign-off. Cards 1, 3, 4 in run3 are at risk.
  • #18 Anchor underdetermination (per X adversarial card). Check: For each cited anchor, construct the most parsimonious reading of what the anchor attests. Does the bridge's claimed relation require interpretive moves beyond the parsimonious reading? If yes, the bridge is anchor-underdetermined and either needs a different anchor that does the work, or is over-claiming. Catches the "real-but-generic phrase used as bridge anchor" failure mode.
  • #19 Saturation-bridge / over-glossed-phrase (per Y adversarial card). Check: is the bridge's primary phrase heavily glossed in secondary literature (≥3 distinct interpretive schools deploy it as a heading-level or chapter-organizing term)? If yes, the bridge is in saturation territory and must either (a) take an explicit position in the dispute with extra counterpressure work, or (b) downgrade from "mechanism" or "structural" to "vocabulary-track" — a different and lighter bridge type. Distinct from #10: #10 catches the bridge encroaching on a dispute by taking a position; #19 catches the bridge declining to take a position when the phrase requires one.

Deferred to post-pilot

Patterns #13 (philological inversion), #16 (wiki-internal terminology collision), #17 (false-friend evasion via bridge-card route) — flagged by reviewers but deferred. #13 fires only on bilingual cards; #16 is mostly structural (fits Role A's gate better); #17 overlaps with #15. Add post-pilot if pilot reveals their need.

4.5 Role B prompt addition — MP-scholarship-context briefing

Role B's prompt includes a briefing paragraph naming major MP-scholarship schools and famously contested points, sourced where Role B applies #10 and #19. (Per my pushback on Y break 5: keeping #10 at Role B requires sourcing scholarly context where it's probed, rather than moving #10 to the adjudicator subagent which would have even less context.)

Briefing content (to embed in Role B subagent prompt):

MP-scholarship context. Major scholarly schools and famously contested points to factor when applying patterns #10 (longstanding controversy) and #19 (saturation-bridge):

  • Status of "flesh" / chair / Fleisch: element (Dillon) vs. ontology (Barbaras) vs. metaphor vs. structural register (Saint Aubert). Bridges that pair [[chair]] / [[flesh]] with structural-mechanism claims encroach.
  • Continuity vs. rupture between Phenomenology of Perception (1945) and The Visible and the Invisible (1959-61): continuity reading (Carbone, Vallier in some moods) vs. rupture reading (Barbaras, Toadvine). Bridges spanning PoP and V&I take an implicit position.
  • Husserl ↔ MP relationship: where MP extends vs. departs from Husserl (esp. on Lebenswelt, Stiftung, passive synthesis). Bridges that route through Husserlian terms (Sichten, Wesensschau, Stiftung) without explicit position-taking encroach.
  • Hegel ↔ MP via Hyppolite: the 1953-55 transition zone is known to involve Hegel reception. Bridges in this period have a periodization tax.
  • Late-MP and Marxism: the Adventures of the Dialectic / institution-of-the-proletariat status is contested between political-philosophical reading (Coole) and ontological reading (Caraus, Larison in M-C 2026). The "haunting / obsessive presence" register sits inside this dispute.
  • "Hyper-dialectic" as positive vs. critical move: is it MP's positive method (Lawlor) or a critique-of-dialectic (Saint Aubert)? Bridges to [[hyper-dialectic]] should name which reading they're presuming.
  • The 1953-55 transition zone is positionally load-bearing (CLAUDE.md: "is a middle term between [Earlier] and [Later]"). Bridges that ignore the transition zone in cross-period claims mishandle MP-corpus chronology.

When Role B finds the bridge encroaches on or declines a position in any of these without explicit acknowledgment, fire #10 or #19 with the relevant school named.

5. Evidence-tracer protocol (Role C)

  1. List every evidence anchor in the card.
  2. For each anchor, locate it (extraction note line, source page passage, raw file).
  3. Verify the anchor says what the card claims it says. Include a 1-paragraph philological gloss: "the passage says X; the card claims it says Y; X and Y match because Z." (Per Y-Scenario 4: the interpretive sub-check is added to Role C rather than splitting Role C into empirical/interpretive — the lighter integration.)
  4. For multi-source cards, check whether the cited convergence is genuine or post-hoc.
  5. For single-source cards, check whether the cited single source actually carries the weight the card assigns it (i.e., the cited passage is load-bearing, not incidental).
  6. If a cited anchor is unreachable or doesn't say what's claimed: DEFECT FOUND with location.
  7. (New per Y Improvement 10.) Rule 18 local-context check. For any anchor that originates in an extraction note ingested before the bridge's primary motivating source, perform a General Rule 18 local-context check: read the cited passage in raw, with paragraph context, and verify that the passage carries the cross-source weight the bridge assigns. If the older extraction note extracted a phrase that perfectly matches the bridge's claim while the surrounding context is not about the bridge's relation, the anchor is stale and the card should be flagged with Stale-Anchor concern.

Role C may exceed the §6 raw-read cap of 5 specifically when item 7's Rule 18 check requires additional paragraph-context reads. Cap rises to 8 reads/card in that case; over 8 still triggers the self-flag.

6. Raw-access discipline

Reviewers may read /raw/, bounded by:

  • Cited anchors only, in the first instance — verify cites by reading the cited location.
  • Adjacent local context — paragraph before/after a cited line (per General Rule 18).
  • Counter-example probes for patterns #11 and #19 — bounded look-elsewhere, capped at ~3 raw reads beyond cited anchors per card.

All raw reads recorded in the hypothesis note: file, location, purpose, finding.

Hard cap: 5 raw reads per card per reviewer (raised to 8 for Role C when Rule 18 check applies; §5 item 7). Over-budget triggers a self-flag: "this card needs a fresh ingest pass, not a sign-off review."

Disallowed: free-form re-ingest, reading whole chapters, exploratory search beyond the card's cited scope.

7. Hypothesis-note discipline

Each reviewer, for each card, writes a working hypothesis note BEFORE writing the report. The note structure includes an explicit convergence-update field per Y-Scenario 6:

# Card N — Role X — Agent K — hypothesis note

## Initial reading
[first impression after reading card only, before checking anchors]

## Anchor checks
[per cited anchor: what was checked, what was found]

## Raw reads (if any)
[per raw read: file, location, purpose, finding]

## Hypothesis revisions
[as evidence accumulates: revise hypothesis, note what changed]

## What changed between initial reading and convergence
[explicit field. If nothing changed, explain why the anchor checks did not move the impression. A reviewer consistently writing "nothing changed" across cards is a calibration signal.]

## Convergence
[final reasoning leading to verdict]

## Verdict (preview)
[APPROVED / DEFECT FOUND / UNCLEAR-{subtype} — to be formalized in the report]

Two-tool-call enforcement (per X-D11 option b): each subagent prompt structures hypothesis-note-then-report as a two-stage sequence. Stage 1: write hypothesis note to its file path. Stage 2: write report to its file path. The prompt explicitly forbids editing the hypothesis-note file after writing the report. If the reviewer needs to revise the hypothesis-note based on report writing, the revision is appended as a "Revision after verdict" subsection rather than rewriting earlier sections. Two-tool-call enforcement is prompt-based, not harness-enforced.

8. Verdict format

# Card N — Role X — Agent K — report

**Card slug:** [card title from Pass 3 report]
**Reviewer role:** A (gate-applier) | B (adversarial-attacker) | C (evidence-tracer)
**Verdict:** APPROVED | DEFECT FOUND | UNCLEAR-{UNDER-SPECIFIED | CANNOT-DETERMINE | OUT-OF-ROLE-SCOPE}
**Confidence:** high | medium | low

## Tests applied
[Role-specific. For Role A: per-test (1-7) result. For Role B: per-pattern (1a, 1b, 2-12, 14, 15, 18, 19) probed/skipped/fired. For Role C: per anchor verified/unverified/contested.]

## If DEFECT FOUND
- Location: [card field / line]
- Pattern or test: [#N from taxonomy, or test K from gate, or "other"]
- Why it breaks: [specific reasoning]
- Fixable: yes-with-X | no-fundamental

## If UNCLEAR
- Subtype: UNDER-SPECIFIED | CANNOT-DETERMINE | OUT-OF-ROLE-SCOPE
- Reason: [why cannot determine]
- What would resolve: [e.g., re-reading anchor, raw check, re-roled reviewer, card rewrite by drafter]

## If APPROVED with high confidence
[Required sentence per Y math-break 1: explain *why* confidence is high — what evidence specifically warrants high vs. medium. Without this, "high confidence" is uncalibrated.]

## Notes
[anything else; reference hypothesis note for trace]

UNCLEAR subtype semantics (per X-D5):

  • UNDER-SPECIFIED-CARD: the card itself is too vague to evaluate; needs rewrite by drafter (not by reviewer or adjudicator).
  • CANNOT-DETERMINE: the evidence is ambiguous; a specific check (named in the report) would resolve.
  • OUT-OF-ROLE-SCOPE: this card's defect is for a different role's lens (e.g., Role C sees the empirical anchors check out but is reading a card whose problem is editorial-frame laundering — Role B territory).

9. Quorum rule (asymmetric, 3 reviewers)

A B C Decision
APPROVED APPROVED APPROVED adjudicator subagent confirms sign-off
2 APPROVED + 1 DEFECT (any confidence on DEFECT) — but DEFECT is Confidence: high BLOCK (per X-D1: high-confidence single dissent is closer in informational content to a 2-of-3 medium block)
2 APPROVED + 1 DEFECT (DEFECT is medium or low confidence) adjudicator subagent recommendation; sign-off requires explicit rebuttal of the DEFECT's named pattern in the recommendation
1 APPROVED + 2 DEFECT BLOCK — revise or retire
3 DEFECT RETIRE (or major rewrite)
Any UNDER-SPECIFIED return to drafter; do not adjudicate. Card status remains proposed with rewrite-required annotation.
2-of-3 OUT-OF-ROLE-SCOPE on the same card role assignment was wrong; re-spawn fresh reviewers with appropriate roles
Any CANNOT-DETERMINE without sufficient APPROVED to clear adjudicator subagent commissions targeted check (re-read anchor, raw probe) or recommends BLOCK pending resolution

Asymmetric because: DEFECT FOUND is a strong signal cheap to investigate; rubber-stamping is expensive to undo once apply-mode writes have landed.

10. Batch-level "same-gap-twice" check

After all 18 reports (15 reviewer + 3 interpretation/adjudication) are written, main-thread Claude reads them in aggregate and checks: did 3+ cards fail the same pattern? If yes, pause sign-off for the entire batch.

The pause requires diagnosing which of three options (per Y-Scenario 2):

  • (a) The schema has a systematic bug.
  • (b) The upstream artifact (silent-keys report) has a systematic bug.
  • (c) The taxonomy is mis-tuned for this card cohort — pattern over-firing on cards that are actually well-formed (e.g., pattern #1 firing on Cards 1, 2, 4 when those cards genuinely operate at the editorial-register-but-MP-anchored level acknowledged in their counterpressures).

Main-thread writes a diagnostic note in adjudication.md naming which of (a)/(b)/(c) the pause reflects, with rationale. Without explicit choice, do not re-run; doing so risks rewriting upstream reports that aren't broken or further mis-tuning the taxonomy.

11. Adjudicator subagent + main-thread ratification

(Replacing v2 §11 per X-D2 and Y-Scenario 1 — the highest-severity convergent finding.)

After all per-card reviewers return, main-thread spawns a single adjudicator subagent (Role D) with:

  • The 3 reports per card (A, B, C)
  • The card text (unstripped)
  • The interpretation map from the pre-step
  • The schema gate (§3), the taxonomy (§4), the quorum rule (§9)
  • The cross-card dependency map (which cards reference which other cards in their apply-as items)

The adjudicator subagent does NOT receive:

  • This plan document
  • The reviewer hypothesis notes
  • The Pass 3 motivating prose
  • Session memory of who drafted the Pass 3 cards
  • The two adversarial-plan-reviewer reports

Adjudicator's job per card:

  1. Apply the quorum rule (§9) mechanically.
  2. For 2-APPROVED + 1-DEFECT (non-high-confidence) cases, write an explicit rebuttal of the DEFECT's named pattern (e.g., "Pattern #1 fired by Reviewer B; rebuttal: the card's Counterpressure §3 explicitly names this risk and the apply-as scope is bounded to subsection-only writes that don't promote the editorial frame to MP register").
  3. Recommend: SIGN-OFF / SIGN-OFF-WITH-NARROWING / BLOCK / ESCALATE-TO-USER.
  4. Write recommendation to adjudication/per-card-recommendations.md.

Main-thread Claude then mechanically ratifies:

  • SIGN-OFF → main-thread writes Approved by maintainer: line on the Pass 3 card.
  • SIGN-OFF-WITH-NARROWING → main-thread narrows the apply-as scope per adjudicator's rationale, then writes sign-off line.
  • BLOCK → main-thread writes block rationale; escalates to user for confirmation before retire-or-revise decision.
  • ESCALATE-TO-USER → main-thread surfaces the case to user without acting.

Main-thread is forbidden from reasoning into the adjudicator subagent's recommendation. Main-thread's role is mechanical ratification of the recommendation, not adjudication of the adjudicator.

Main-thread writes adjudication.md summarizing all 5 card outcomes, with adjudicator-recommendation-plus-ratification per card.

11.5 Cross-card dependency reconciliation

(New per X-D9 and Y-Scenario 3.)

After all per-card adjudications but BEFORE writing any Approved by maintainer: line: main-thread re-reads all SIGN-OFF / SIGN-OFF-WITH-NARROWING cards' apply-as items. For each apply-as item that cross-references another card by slug or by the déposer-style mechanism name:

  • If the referenced card was BLOCKED or RETIRED: narrow the apply-as item to remove the cross-reference, OR downgrade the entire approved card to held-pending-other-card-revision.
  • If the referenced card was also signed off: proceed.

Documented in adjudication.md under "Cross-card reconciliation."

Concrete example for run3: Card 5's apply-as items 2 and 3 cross-reference Card 1's déposer. If Card 1 is BLOCKED, Card 5's items 2 and 3 are struck (Card 5 still applies item 1 on [[transtemporality]] and item 4's promotion deferral, which don't cross-reference Card 1).

11a Revise-and-resubmit pathway

(New per Y-Scenario 9.)

A BLOCKED card whose DEFECT report carries Fixable: yes-with-X may be revised in-place by main-thread once per run, then re-submitted to a fresh-context A/B/C round (not the same agents — the prior verdicts are stale).

  • Revision must address the specific DEFECT (named pattern, named location).
  • Revision is documented in adjudication.md under "Revise-and-resubmit log."
  • Re-submission spawns fresh A/B/C agents with the revised card.
  • Cap: 1 revise-and-resubmit per card per run. If the second round also BLOCKS, card retires until the next Pass 3 run.

Main-thread may NOT revise a card whose DEFECT carries Fixable: no-fundamental — that's a retire.

12. Carve-out — what sign-off authorizes

Sign-off authorizes apply-mode writes for:

  • Subsection writes on concept pages under Open Questions (always), under What the Concept Does or Stakes (only if §12a / §12c constraints are met)
  • Open-question additions (always)
  • Typed-connection additions (subject to §12d motifs-weight check)
  • Bridge-card-anchored cross-references

Sign-off does NOT authorize:

  • Promotion of bridge to a claims.md entry at supported status (the 5-test claim-promotion gate applies; supported promotions halt for human review per existing CLAUDE.md rule)
  • Promotion to motif HUB/STRUCTURAL weight
  • Deletion or retirement of existing wiki content

12a Epistemic-force constraint on subsection writes

(New per Y-Scenario 5.)

Single-source-blocker cards (or cards whose adjudicator-recommendation narrows them to single-source-equivalent scope) may write subsections under Open Questions only, not under What the Concept Does or Stakes. The subsection prose must use provisional framing:

  • Acceptable (provisional): "Larison reads X as Y; the claim is not yet corroborated outside M-C 2026 and awaits a second-source anchor."
  • Unacceptable (declarative): "X is Y."

Multi-source cards may write under What the Concept Does or Stakes, but the subsection prose must annotate when the cross-source convergence is secondary-author-mediated (per #1b pattern's domain).

12b Apply-as-flag vs. apply-as-write distinction

(New per Y Improvement 7.)

Apply-as items that flag future promotion (Possible motifs.md candidate, flag for second-source confirmation, candidate claims.md slug X) authorize the flag itself, not the future promotion. Apply-mode writes implementing such items write only the flag (e.g., a one-line entry in the relevant Open-Questions section noting "candidate motif: hauntology-in-MP; flag for next motifs-delta sweep when second non-M-C-2026 anchor lands"), not the promotion.

Apply-mode agents must treat language like "Possible motifs.md candidate" as "do not write a motifs.md entry," not as "write a motifs.md entry at BRIDGE weight."

12c HUB-page apply-as escalation

(New per Y math-break 2.)

Cards whose Primary home or Secondary home is a HUB-weight concept page (per motifs.md weight class) require:

  • 3/3 APPROVED for apply-as items targeting What the Concept Does or Stakes on the HUB page (no adjudication path to APPROVE these specific items)
  • Normal quorum (per §9) for apply-as items targeting Open Questions on the HUB page

HUB pages have downstream impact disproportionate to the card's local stakes — apply-mode writes on [[institution]], [[transtemporality]], [[good-ambiguity]], [[indirect-ontology]] propagate to claims, paper drafts, downstream concept pages. Raise the bar.

In run3: Cards 1 (Primary [[institution]]), 2 (Primary [[institution-of-the-proletariat]], Secondary [[transtemporality]] and [[depth-of-time]]), 3 (Primary [[good-ambiguity]]), 4 (Primary [[indirect-ontology]]), 5 (Primary [[transtemporality]]) all touch HUB pages. The escalation applies to apply-as items targeting non-Open-Questions sections on those pages.

12d Motifs-weight tipping check

Per pattern #12: if Role B fires #12 on a card, the card's apply-as items affecting motifs are deferred to a motifs-delta sweep, which is its own audit phase. Bridge-card sign-off authorizes only the non-motifs-tipping apply-as items in this case.

13. Pilot success criteria

(New per X-D8 and Y-Scenario 7. Replaces v2's empty "if pilot fails, revise; if pilot succeeds, codify.")

Pilot SUCCESS = all of the following:

  1. At least one DEFECT FOUND across the 5 cards. A 5-for-5 silent sign-off is evidence the taxonomy lacks bite, not evidence the cards are clean. (per X-D8 #1.)
  2. Every DEFECT FOUND fires a specific pattern from the taxonomy (not "other"). If reviewers keep firing "other," the taxonomy is under-specified. (per X-D8 #2.)
  3. At least one Role C raw-budget self-flag fires OR is explicitly noted as adequate in the hypothesis notes. Silence about the budget means the budget wasn't actually checked. (per X-D8 #3.)
  4. §10 same-gap-twice check either does not fire, or fires with a non-taxonomy diagnosis (schema bug or upstream bug). Taxonomy mis-tuning diagnosis triggers pilot REVISE, not pilot success. (per X-D8 #4 + Y-Scenario 2 + Y-Scenario 7 (ii).)
  5. No 1-of-3 DEFECT-high-confidence adjudication produced a silent APPROVE. Every such case routes to BLOCK per §9 quorum rule; if any was approved, §9 is being bypassed. (per X-D8 #5.)
  6. ≥3 of 5 cards reach a verdict (SIGN-OFF, BLOCK, or RETIRE) without escalation-to-user during adjudication. (per Y-Scenario 7 (i).)
  7. Human user reviewing the final adjudication.md does not override any per-card decision. (per Y-Scenario 7 (iv).)

Pilot FAILURE = any of the above fails. Pilot AMBIGUOUS = a mixed outcome (e.g., 1 card escalates but 4 reach verdict cleanly; or 5-of-5 silent APPROVE which violates criterion 1). In ambiguous cases, do NOT codify; revise the relevant component (taxonomy / gate / quorum) and re-pilot.

14. Cards-that-reference-each-other

Handled by §11.5 (cross-card dependency reconciliation). Per-card adjudication remains independent; reconciliation runs after all adjudications complete.

15. What this plan does NOT do

  • Does not authorize apply-mode writes for the 5 Pass 3 cards. Sign-off and apply-mode are separate steps; apply-mode follow-up branch is separately authorized.
  • Does not modify CLAUDE.md or weave/SKILL.md or schema-changelog.md. Those updates land at the v0d.7 codification step, after pilot succeeds.
  • Does not retire or modify the existing v0d.5 bridge-card layer. This extends it.

v0d.7 codification will additionally add (anticipated, not specified here):

  • wiki/.audit/bridge-cards-applied.md provenance register (per Y Concern 1)
  • Lint check flagging concept-page subsections anchored to bridge cards not in the register (per Y Concern 1)
  • 11th bridge-card field: confidence (medium / low / speculative) (per Y Concern 4; see §20)
  • Cohort-fingerprint discipline (source-report type, card count, bridge-type distribution, primary-home overlap) for tracking drift between pilot and live use (per Y-Scenario 8)
  • Schema-changelog entry acknowledging the math-olympiad analogy's transfer limits: "bridge-card sign-off is a calibrated probability of philosophical defensibility, not a proof of correctness" (per Y math-break 1)
  • Retrospective audit baseline (after 3-6 months of bridge-card-applied writes, audit a sample for "did the apply-mode writes hold up under subsequent ingest and audit?" to calibrate confidence labels) (per Y math-break 4)

16. Agent-teams escape hatch (documented for v0d.7, not for pilot)

When main-thread ratification of an adjudicator recommendation cannot resolve cleanly within 2 reasoning passes (e.g., adjudicator recommends APPROVED but main-thread finds the DEFECT report uniquely persuasive on re-read), main-thread MAY promote the card to a 1-round agent-teams debate:

  • Reviewer A, B, C re-spawned as Claude Code teammates (requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1)
  • Each teammate receives all 3 prior reports
  • One round of cross-challenge exchange via the agent-teams mailbox
  • Each teammate writes a re-verdict
  • Adjudicator subagent re-runs on the re-verdicts

Used for adjudication-deadlock cases only. Documented for v0d.7; not implemented for pilot. Pilot operates on subagent isolation only, with main-thread escalating deadlocks to user.

17. Subagent vs teammate skill-loading discipline

Subagent definitions for the four reviewer roles (I, A, B, C) and the adjudicator (D) MUST use a tools: allowlist excluding the Skill tool. Reason: prevents auto-loading of weave/SKILL.md, which would leak procedure metadata (existence of co-reviewers, asymmetric quorum, batch-level check) and break dual isolation.

Allowed tools per subagent: Read, Grep, Glob, Write (Write scoped via prompt to per-agent subdirectory).

If we later add the agent-teams debate escape hatch (§16), the teammate prompt must explicitly say "Do not invoke any skills regardless of activation suggestions" because Claude Code teammates auto-load skills from project/user settings, ignoring subagent tools: restrictions (per the agent-teams doc note on subagent-definitions-as-teammates).

18. Pre-step interpretation-checker (one subagent for the batch)

(New per X "Interpretation pass" missing-pattern; adapted from math-olympiad §1.)

Before the per-card reviewer agents launch, a single interpretation-checker subagent runs against all 5 cards. Its job per card:

  1. Generate 2-3 alternative readings: different Primary home choice, different Bridge type classification, different relation specification.
  2. Mark the card's stated reading as one of the alternatives.
  3. For each alternative: is it TRIVIAL (any reading any reviewer would assent to) or NON-TRIVIAL (substantive claim)?
  4. If the card's stated reading is the trivial one and another reading is non-trivial: flag as INTERPRETATION-AT-RISK. The card may be mis-stated.
  5. Output: interpretation-map.md with per-card alternative readings + trivial/non-trivial assessment + risk flag if applicable.

The interpretation map is adversarial context — it expands the question of what the card claims rather than answering it. A/B/C reviewers read the map alongside their card; their job is to evaluate the card's stated reading against the interpretation-checker's named alternatives.

Tools: Read, Grep, Glob, Write (Write scoped to interpretation-map.md). No Skill tool.

Subagent prompt embedding the same dual-isolation language as A/B/C: "You are the only interpretation-checker reviewing this batch. You have no information about other reviews."

19. Retry policy

(New per X math-olympiad §2 analog.)

If any subagent (I, A, B, C, D) fails or times out:

  • One retry with the same prompt.
  • If retry fails too: drop the card from this run, mark in adjudication.md as "subagent unavailable — manual review required," and proceed with other cards.
  • A card that drops from the run is not signed-off and not retired; it stays at proposed for the next run.

20. 11th bridge-card field — confidence

(New per Y Concern 4; v0d.7 codification will add this to the v0d.5 bridge-card template.)

Bridge cards gain an 11th field: confidence: medium | low | speculative.

  • Set at draft time (Pass 3).
  • Re-verified at sign-off (adjudicator subagent may recommend lowering).
  • Single-source-blocker cards default to low or speculative.
  • Multi-source cross-author-convergence cards default to medium.
  • Subsection writes implementing low-confidence cards must annotate the subsection prose with provisional framing (per §12a).

For the pilot, the 5 cards in run3 do not carry this field. Pilot procedure infers confidence from evidence-status field + counterpressure for adjudication purposes; v0d.7 codification adds the field to the template for future Pass 3 runs.

v3 changelog (summary of changes from v2)

Critical (architecture):

  • §11 main-thread adjudicator replaced with fresh-context adjudicator subagent + mechanical main-thread ratification + user-escalation on BLOCK/UNCLEAR (X-D2 / Y-Scenario 1)
  • §9 quorum: 1-of-3 DEFECT-high-confidence triggers BLOCK (X-D1)
  • §13 pilot success criteria: explicit 7-criterion conjunction (X-D8 + Y-Scenario 7)
  • §4 taxonomy: 11 → 16 patterns (#1 split + #12, #14, #15, #18, #19; deferring #13, #16, #17)
  • §12c HUB-page apply-as escalation (Y math-break 2)
  • §12b apply-as-flag vs apply-as-write distinction (Y Improvement 7)

High (procedure):

  • §3.5 strip-bridge-prose pre-pass for Roles B and C (X-D4)
  • §8 UNCLEAR split into 3 subtypes with quorum actions (X-D5)
  • §11.5 cross-card dependency reconciliation (X-D9 / Y-Scenario 3)
  • §11a revise-and-resubmit pathway (Y-Scenario 9)
  • §12a epistemic-force constraint on subsection writes (Y-Scenario 5)
  • §7 hypothesis-note "what changed" field + two-tool-call enforcement (Y-Scenario 6 + X-D11)
  • §10 third diagnostic option: taxonomy mis-tuning (Y-Scenario 2)
  • §4.5 MP-scholarship-context briefing in Role B prompt (my pushback on Y break 5)
  • §5 item 7 Rule 18 local-context check (Y Improvement 10)
  • §3 test #6 rewrite + test #7 dead-link check (X-D6 + X-D13)
  • §16 agent-teams escape hatch
  • §17 subagent skill-loading discipline
  • §18 pre-step interpretation-checker (my modification of X improvement)
  • §19 retry policy (X math-olympiad §2)
  • §20 11th confidence field on bridge cards (Y Concern 4)

Medium (v0d.7 codification, anticipated in §15):

  • Bridge-cards-applied register + lint check (Y Concern 1)
  • Cohort fingerprint discipline (Y-Scenario 8)
  • Retrospective audit baseline (Y math-break 4)
  • Calibrated-defensibility caveat in schema-changelog (Y math-break 1)

Pushback (rejected or modified):

  • Moved #10 to adjudication (Y break 5) — kept #10 at Role B with §4.5 scholarship briefing instead
  • Interleaved card-batch assignments (X-D12) — deferred; subagents are independent
  • Explicit "bridge-card-author ≠ adjudicator" rule (X Improvement 16) — fresh-context adjudicator subagent addresses this structurally
  • Step 0 interpretation pass by main-thread (X option) — moved to dedicated subagent (§18)
  • All 8 new taxonomy patterns (both reviewers) — 5 patterns for pilot; deferred #13, #16, #17 to post-pilot
  • Bridge-cards-applied lint check at plan stage (Y Concern 1) — deferred to v0d.7 codification