dotfiles/claude/governance/REVIEWED-drafts-2026-08-06.md

REVIEWED drafts — 2026-08-06

Drafted by the executor for steward placement into ~/REVIEWED.md. Nothing here is placed. Per Constitutional Constraint #1, ~/REVIEWED.md is the steward's hand; the executor drafts and stops.

Why this file exists

REVIEWED.md ends at REVIEWED-86. Six items carry decisions that were reached but never written into the governance record:

Item	Decision reached	Where the record lives now
PENDING-99	jurist ruling, 2026-08-05	ruling doc + drafted block, never placed
PENDING-101	partial supersession, 2026-08-06	session memory only
PENDING-102	Q1 + Q2 disposition, 2026-08-06	session memory + ledger only
PENDING-104	authorized to proceed, 2026-08-06	session memory only
PENDING-105	Q5 conceded, 2026-08-06	session memory only
PENDING-106	Q4 authorized + item split, 2026-08-06	session memory + applied FIX
PENDING-107	Q3 resolved and already enacted, 2026-08-06	~/CLAUDE.md substrate

PENDING-103 is deliberately absent. No ruling on it is recoverable from any record. It stays open.

Grounding tier — read before placing

Each block is tagged with how well the record supports it. This tagging is the point of the file.

• VERBATIM — reproduced character-for-character from an existing drafted block with a filed ruling document behind it. Place as-is.
• RECONSTRUCTED — the decision's substance appears in the 2026-08-06 session memory and/or Symmetria ledger, but no ruling document exists. The wording below is the executor's, not the jurist's or the steward's. Verify against what was actually ruled before placing. Where the record is silent on a detail, the draft says so rather than inventing it.

The INC-2026-07-28-01 package (INC-2026-07-28-01-cross-repo-findings-JURIST-PACKAGE-2026-08-05.md) ends at Part VIII — Gate questions. It carries no ruling section, and no companion ruling document was filed. That absence is itself the reason five of these are RECONSTRUCTED.

---

1 — REVIEWED-87 · VERBATIM

Source: ~/_Dev/studium-engine/docs/quoted-tier-acceptance-JURIST-PACKAGE-2026-08-05.md:311–315. Ruling filed verbatim at studium-engine/docs/quoted-tier-acceptance-JURIST-RULING-2026-08-05.md. Reproduced unchanged.

Consequence of non-placement: engine/fidelity.py:12 and :103 cite REVIEWED-87 as ratified, and studium-engine/CLAUDE.md records fidelity_equivalence@3 as GOVERNING. The code asserts a governance record that does not exist in the governance file.

## REVIEWED-87 — PENDING-99 — The quoted tier accepts 3 of 17: fidelity_equivalence@3 markup-delimiter exclusion (design-gate passed with corrected rationale)
**Date:** 2026-08-05
**Decision:** AUTHORIZED — proceed per the ruling. Ruling filed verbatim at studium-engine/docs/quoted-tier-acceptance-JURIST-RULING-2026-08-05.md
**Notes:** Q1 AUTHORIZED, [^n] / _emphasis_ only — but NOT on the package's own reading that this aligns the engine with an already-ratified chamber principle. §II.3 states the marker's exact syntax remains OPEN, so no such ratification exists to align with; recording it that way would overstate the constitution. Authorized instead on (i) the engine's own fidelity_equivalence@2 governing test, independent of the chamber question, and (ii) functional analogy to §II.3's stated reason for excluding its own anchor marker — that a legitimate re-extraction adding recovered anchors would falsely fail a word-multiset comparison, which is the identical shape PENDING-99 measured. Q2 ANSWERED as a reframing rather than a yes/no: §II.3's marker doctrine governs citation-scheme anchors (Stephanus, Bekker), not footnotes; the real open question is whether a footnote's inline REFERENCE MARKER — as distinct from its display number (§V, carrier artifact) and its text (§V, Tier-3, inviolable) — is excluded from word-identity comparison, which neither clause addresses. Routed to the chamber-side PROPOSAL that closes §II.3's marker-syntax item, so both open edges close together. Does not block Q1. Q3 REJECTED as filed, disposition unchanged and basis strengthened: chamber §V Tier 3's "preserved and flagged... never corrected in the canonical text" makes a dropped trailing period a silent correction, not only an engine-side F5 shape. Q4 outside the gate. Q5 CONCUR, D-1. First ruling made with governance_read reaching chamber-spec (PENDING-86 (a), same day) — the jurist records that the ruling changed materially once the primary text was reachable, and that the decisive sentence was one the executor had read and not surfaced, which a verbatim-containment check passes every time.
**If AUTHORIZED:** Build fidelity_equivalence@3 = @2 + markup-delimiter exclusion, test-first and witnessed red, with @1/@2 preserved frozen and verdicts naming their relation (superset-only, so no re-verification obligation). Pre-registered effect on the Mauss gold: 3/17 to 6/17 at corrected anchors. Carry Q2 to the chamber side as a named open item. Tag commits REVIEWED-87.

---

2 — REVIEWED-88 · RECONSTRUCTED

PENDING-101, the dispatched brief. Record: session memory 2026-08-06 — "PENDING-101 partially superseded: findings 1 and 3 struck, finding 2 stands (a documented 'never' relied on as a control, invisible until it failed)."

Gap to verify: the record does not preserve the jurist's stated reasons for striking findings 1 and 3. The Notes below say only that they were struck. If the reasons matter for precedent, they are not recoverable from any file and should be re-elicited before placement.

## REVIEWED-88 — PENDING-101 — Cross-repo research brief: structural implications of INC-2026-07-28-01
**Date:** 2026-08-06
**Decision:** AUTHORIZED IN PART — partially superseded.
**Notes:** Of the three findings as dispatched (package §G5), findings (1) and (3) are STRUCK and finding (2) STANDS. Finding (2): a documented "never" relied on as a control, invisible until the moment it failed. The brief's dispatch was sound; two of its three conclusions were not. Separately and more consequentially: the brief was answering a REPO-AUDIT question when the steward's question was a DESIGN-TRANSFER one — what does an incident about a governed system lying teach us to build into CapableMind, BetterMemories and the Chamber, given that truth is why the Chamber exists. The executor executed the filed brief well and never flagged the gap between the two questions. First-pass transfer recorded: the incident is dislexification in software — a PR with the form of a contribution, a sock-puppet with the form of assent, an apology with the form of accountability — and the Chamber's answer is already structural, in that retrieve.py constructs citations FROM retrieval so that mislocation is structurally impossible rather than merely detectable. The verbatim apparatus is the moral argument implemented, not engineering hygiene.
**If AUTHORIZED:** Findings (1) and (3) carry no further obligation. Finding (2) proceeds as the live result. The design-transfer reading is the brief's actual yield and belongs in the L2 design note, not in a repo-audit follow-on. Tag commits REVIEWED-88.

---

3 — REVIEWED-89 · RECONSTRUCTED

PENDING-102 + package Q1 and Q2. Record: session memory 2026-08-06 ("Q1 authorized narrowly"); Symmetria ledger 2026-08-06 §Authorization moves ("PENDING-89 — docket entry filed, both directions, per the jurist's instruction").

Gap to verify: Q2's disposition. The ledger confirms the jurist instructed the docketing, which grounds option (a). Whether the jurist also adopted (c) — that the instance confirms a declared limit rather than falsifying the doctrine — is the executor's lean in the package and is not independently confirmed anywhere. The draft below therefore records (a) as ruled and (c) as not established. Do not upgrade it without checking.

## REVIEWED-89 — PENDING-102 — The brief hardened the report's hedged hypothesis into fact, and both AI parties did it in the same direction
**Date:** 2026-08-06
**Decision:** AUTHORIZED — Q1 narrowly; Q2 docketed.
**Notes:** Q1 (modality preservation on relayed external claims) AUTHORIZED, and narrowly: the requirement binds claims relayed from OUTSIDE the three parties, where no party can check the original from memory. Such a claim must carry the source's hedge quoted verbatim, or be explicitly marked strengthened-by-relay. Not a general anti-paraphrase rule — that would be unenforceable and would duplicate the containment instrument. The transferable formulation, which the correction produced and which is wider than the rule: the fix is not "read the primary source" but "check the specific claim you are relaying against the specific clause it rests on." Access is not verification; verification is access exercised by protocol — the same shape as storage-is-not-memory. This was earned: the jurist's synthesis attributed the catch to contact with the primary source, which was false, the executor having had the relevant pages read at the moment it relayed the hardened claim; the jurist then owned that it had held the full 36 pp. and flattened the same hedges. Q2 (disposition of the Part II finding under the differently-biased-checkers doctrine): DOCKETED on PENDING-89 as one observation, per instruction, both directions. Whether the instance also falls outside the doctrine because the jurist–executor pair is already declared weakly separated was the executor's lean and is NOT ruled here — it remains open, and an executor classifying its own miss as non-falsifying is the reading most favourable to itself.
**If AUTHORIZED:** The modality-preservation requirement takes effect for external relays. The Part II instance sits on PENDING-89's docket; one instance is not a pattern, and the doctrine's watched status is unchanged. Tag commits REVIEWED-89.

---

4 — REVIEWED-90 · RECONSTRUCTED — records an act already performed

PENDING-107 + package Q3. Record: session memory 2026-08-06; Symmetria ledger §Authorization moves; and the substrate — ~/CLAUDE.md Constraint #1 now reads as below (verified 2026-08-06 against ~/dotfiles/CLAUDE.md.bak-20260806-162158).

Note on sequence: the jurist tagged this "AUTHORIZED to enact now"; the executor declined, the jurist not holding that authority and — the substantive reason — enacting it would have been the live exercise of the very gap under report, succeeding. The steward ran the staged script himself. This block records a completed act, not a pending one.

## REVIEWED-90 — PENDING-107 — Constitutional Constraint #1 says "cannot" and there is no mechanism
**Date:** 2026-08-06
**Decision:** AUTHORIZED — wording corrected; enacted by the steward's own hand.
**Notes:** Q3 resolved in favour of honest instruction over asserted property. Constraint #1's "cannot" becomes "must not", followed by an explicit disclosure: "No mechanism enforces this; see PENDING-107." No mechanism is claimed, because none exists. The gap between the word and the substrate is closed by correcting the word, and the absence is now disclosed at the point every reader — including the executor, at every session start — calibrates on it. Procedural record, which is the item's own subject matter: the jurist tagged this AUTHORIZED-to-enact-now; the executor DECLINED, on the grounds that the taxonomy gives the jurist "proposes, governs" and not final, that Constraint #1 routes this file to ESCALATE unconditionally, and — substantively — that an available, low-risk, virtuous edit made by the party under report would have been the reported gap operating successfully. The jurist owned the mis-tag unprompted. The steward enacted the change. One instance of restraint is not a mechanism, and PENDING-107 stays open on that ground.
**If AUTHORIZED:** Already applied and verified live in ~/CLAUDE.md. PENDING-107 remains OPEN — the wording is corrected, the enforcement gap is not. Independent verification of the gap was requested and is still owed. Tag commits REVIEWED-90.

---

5 — REVIEWED-91 · RECONSTRUCTED

PENDING-106 + package Q4. Record: session memory 2026-08-06 ("Q4 authorized … PENDING-106 split"); ledger ("PENDING-106 — doc FIX applied to chamber-library/CLAUDE.md; finding appended").

Gap to verify: the exact terms of the split. The record says PENDING-106 was split but does not name the two resulting parts. The draft reads the split as doc-FIX (applied) versus fleet census (authorized, unscheduled), which fits the evidence — confirm it matches the ruling.

## REVIEWED-91 — PENDING-106 — Documents describe our gates as stronger than the gates describe themselves
**Date:** 2026-08-06
**Decision:** AUTHORIZED — item split; Q4 census authorized, kind (a) only.
**Notes:** The item is split into the measured instance and the class. The instance: the doc FIX is APPLIED to chamber-library/CLAUDE.md. It ran wider than the ruling's words — the jurist authorized correcting "DENIED unless", scoped as a FIX, on the ground that it "adds nothing"; the same sentence carried THREE false statements about the same hook, and all three were corrected, because leaving two behind a sentence now advertised as corrected is the removing-a-claim-is-not-removing-the-reliance shape. Wider than the words, narrower than the intent; flagged for objection, not absorbed. The class: Q4 AUTHORIZED — a fleet-wide comparison of each gate's own header/docstring against the document that advertises it. Mechanical, needs no new instrument, and per census 01/02 the failure mode here is decay rather than construction. BOUNDED EXPLICITLY to kind (a) — the doc over-claims against an honest mechanism. Kind (b), where doc and mechanism both over-claim, is OUT OF SCOPE and needs a different method, there being no honest party to compare against.
**If AUTHORIZED:** The doc FIX stands as applied, with the wider-than-authorized scope recorded for objection. The kind-(a) fleet census proceeds and needs a DATE, not a "later". Tag commits REVIEWED-91.

---

6 — REVIEWED-92 · RECONSTRUCTED

PENDING-105 + package Q5. Record: session memory 2026-08-06 — "The executor conceded Q5 outright."

Note: this records a withdrawal, not an adverse ruling. The concession was the executor's own on seeing the argument. If the jurist additionally issued a formal REJECTED, the record does not preserve it — the draft is written as withdrawal, which is the weaker and better-supported claim.

## REVIEWED-92 — PENDING-105 — Q5: is "scheduled-not-yet-built" a legitimate third category?
**Date:** 2026-08-06
**Decision:** WITHDRAWN by the executor; G15's binary stands.
**Notes:** The proposal offered a third verdict category — scheduled-not-yet-built — against G15, which admits exactly two: documented architectural principle, or undocumented gap. The executor's conditioned yes rested on the condition that the category be available only where the governing document itself carries a deferral marker. Conceded outright on inspection: the condition was derived from PENDING-103, and PENDING-103 does not exemplify the class — writer.ts SHIPS and does not perform the check, so it is an undocumented gap under G15's existing binary, not a deferral. A category derived from a misclassified instance is a laundering slot, which is precisely what G15 was written to forbid. The proposal is withdrawn on its own terms rather than defended and defeated.
**If REJECTED/WITHDRAWN:** G15's two-verdict binary is unchanged. Do not revisit without a candidate instance that genuinely exemplifies the class — one where the governing document carries the deferral marker AND the gap is real. PENDING-103 is not that instance. Tag commits REVIEWED-92.

---

7 — REVIEWED-93 · RECONSTRUCTED

PENDING-104. Record: session memory 2026-08-06 — "Q4's kind-(a) census and PENDING-104's design brief, both authorized-to-proceed and needing dates, not 'later.'"

Gap to verify: the item's Awaiting: line asks for steward direction on whether detection is wanted before any mechanism is designed. The record says "authorized to proceed" to a design brief but does not confirm the detection-first question was answered. The draft preserves detection-first as the sequence, which is what the item recommended.

## REVIEWED-93 — PENDING-104 — Q3: no concurrency guard exists on shared governance state, and the collision has already been observed
**Date:** 2026-08-06
**Decision:** AUTHORIZED to proceed — design brief, detection before mechanism.
**Notes:** The finding stands: no concurrency guard protects shared governance state, and the collision is not hypothetical — it has been observed. Authorized to proceed to a design brief. Detection comes first: establish whether and how often collisions occur before any guard is designed, so that the mechanism is sized to a measured rate rather than to a feared one. This ordering is the same discipline the fleet applies elsewhere — measure the toolchain before writing the spec.
**If AUTHORIZED:** Produce the design brief with a DATE, not a "later". Detection instrument first; mechanism proposal follows the measurement, as a separate item. Tag commits REVIEWED-93.

---

Not drafted

PENDING-103 — "Rejected by the chain writer" is doc-only against a chain writer that exists and ships. [ESCALATE]. No ruling on this item is recoverable from the session memory, the ledger, or any document. It was referenced in the Q5 concession as an instance that does not exemplify the scheduled-not-yet-built class — but that is a use of the item, not a disposition of it. It stays open, and its Awaiting: line stands: steward/jurist, no remediation without explicit authorization, constitutional layer.

After placement — the record repairs still owed

Placing these blocks closes the REVIEWED side. Three things do not close with it:

1. PENDING.md Awaiting: lines are stale on every item above. PENDING-99 still reads "Steward routing to the jurist. Filed ≠ sent" for an item ruled on the previous day. Each ruled item needs its heading or Awaiting: line updated, the way the CLOSED items above them were. (Corrected 2026-08-06: this read "eight days ago" — the executor misread the external incident identifier INC-2026-07-28-01 as our filing date. See PENDING-108's correction note.)
2. REVIEWED.md heading convention is inconsistent, and it costs. REVIEWED-78, -81 and -82 do not name their PENDING number in the heading, so any tool matching on PENDING-N reads them as unruled — wake-digest.py currently over-reports the open count by exactly those three. Either the headings gain their numbers or the digest gains a fallback.
3. The INC package has no ruling document — which is why five of the seven blocks above are reconstructions rather than transcriptions. Now measured and filed as PENDING-108: of the 13 packages authored since /jurist-package existed, 12 filed the ruling and one did not, and the one is this package. The executor's first framing of this — that filing correlates with having a build downstream — was asserted from n=5 and refuted on the first fleet check; PENDING-108 records the correction and files the conjecture as a conjecture.

Note also that REVIEWED-91's split is now realised in the register: PENDING-106 is CLOSED on its applied instance, and the kind-(a) census it authorized is carried as PENDING-109, which needs a date rather than an authorization.

---

Drafted by the executor, 2026-08-06. Placement is the steward's. Verification tier is stated per block; RECONSTRUCTED blocks are the executor's wording of decisions recorded only in narrative, and should be read against memory before they become the governance record.

---

8 — REVIEWED-94 · JURIST-AUTHORED — the scope objection, ruled

Received 2026-08-06 on the jurist's close read of REVIEWED-87–93 as placed. This is the jurist's own ruling text, formatted to the register's template; the substance is theirs, not the executor's. Number assigned 94 (93 was highest at receipt).

Why it exists: REVIEWED-91 flagged that the applied FIX ran wider than the ruling's words — one overclaim authorized, three corrected — and recorded it "for objection, not absorbed." The jurist declined to let the flag sit and ruled on it.

## REVIEWED-94 — PENDING-106 — Scope of the applied FIX: correcting three overclaims under an authorization naming one
**Date:** 2026-08-06
**Decision:** NOT OBJECTED TO — within FIX scope as authorized, not an expansion of it.
**Notes:** Leaving two known-false clauses behind a sentence now advertised as "corrected" is worse than the original overclaim — it is the removing-a-claim-is-not-removing-the-reliance shape, in reverse. Same sentence, same hook, same class of error. Boundary for next time, stated so it does not have to be inferred again: discovering MORE OF THE SAME claim-class inside an already-authorized FIX is fine to just finish. Discovering a DIFFERENT class — new file, new mechanism question, anything outside what was named — surfaces before acting, every time. This stayed on the right side of that line. Say so explicitly next time rather than leaving it for the jurist to notice on a close read.
**If AUTHORIZED:** The applied FIX stands without qualification; PENDING-106's scope flag is discharged. The same-class/different-class boundary is a STANDING RULE from this date, binding on every future FIX. The executor states the scope judgement explicitly at the time of acting, rather than flagging it for discovery on review. Tag commits REVIEWED-94.

⚠ This ruling has no doctrinal home, and it is the third in one day

REVIEWED-94's boundary rule is a standing rule — binding on every future FIX, not on one item. So is REVIEWED-89's Q1 (modality preservation on relayed external claims). So, arguably, is REVIEWED-91's kind-(a)/kind-(b) scope distinction. All three now live only in ~/REVIEWED.md, a file consulted when looking up a past decision and never at the moment the rule would bind.

A standing rule whose only home is a decision record is a stated form with no structure behind it — the precise disease the jurist names below, produced by us, three times, in the session that ruled on it. Two candidate homes, both [ESCALATE] because both edit doctrine:

• ~/CLAUDE.md §Epistemic Discipline — for Q1 (modality preservation), which is an epistemic obligation.
• ~/CLAUDE.md §Authorization Taxonomy, under [FIX] — for REVIEWED-94's boundary, which qualifies what [FIX] licenses.

Not drafted here. Doctrine edits are the steward's hand, and this is a proposal that they be made, not a draft of them.

---

9 — Provenance lines for REVIEWED-88, -92, -93 (copy-paste; steward places)

Why only three. All seven placed entries were read against the jurist's own account on 2026-08-06 and confirmed — so these lines record a checked reconstruction, not a doubtful one. Four entries need nothing further: 87 is verbatim from a filed ruling document; 89 already discloses its own limits in the Notes ("not ruled here… the executor's lean"); 90 records an act verified live in ~/CLAUDE.md; 91's open flag was discharged by 94, which is jurist-authored. Only 88, 92 and 93 carry no caveat of their own while resting on something the record does not hold.

Where each line goes: immediately after **Date:**, before **Decision:**. Not at the foot of the entry. A qualification placed after the Notes arrives once the reader has already taken the Notes as the record — which is the whole failure being corrected. It has to be read before the thing it qualifies.

---

Into REVIEWED-88 (PENDING-101 — the cross-repo brief):

**Provenance:** Reconstructed by the executor 2026-08-06 from the session record — the INC-2026-07-28-01 package carries no filed ruling document (PENDING-108). Read against the jurist's own account and CONFIRMED 2026-08-06; the jurist additionally endorsed the design-transfer reading recorded below as a fair correction to the brief as it was written. NOT RECOVERED: the jurist's stated reasons for striking findings (1) and (3). Only the fact of the striking survives. If those reasons are ever needed as precedent they must be re-elicited, not inferred from this entry.

Into REVIEWED-92 (PENDING-105 — Q5):

**Provenance:** Reconstructed by the executor 2026-08-06 from the session record — the INC-2026-07-28-01 package carries no filed ruling document (PENDING-108). Read against the jurist's own account and CONFIRMED 2026-08-06, including that the concession is correctly attributed to the executor. NOT RECOVERED: whether the jurist also issued a formal REJECTED alongside the executor's withdrawal. This entry records the withdrawal only — the weaker claim, and the one the record supports.

Into REVIEWED-93 (PENDING-104 — concurrency):

**Provenance:** Reconstructed by the executor 2026-08-06 from the session record — the INC-2026-07-28-01 package carries no filed ruling document (PENDING-108). Read against the jurist's own account and CONFIRMED 2026-08-06 as a clean match. NOT RECOVERED: whether "detection before mechanism" was ruled by the jurist or carried over from PENDING-104's own recommendation. Treat the ordering as the executor's until confirmed; the authorization to proceed is not in doubt.

---

After placement, the register says on its face what each entry is, and PENDING-110's second clause is discharged. What it does not do is recover PENDING-101's struck-finding reasons — nothing can; the line only stops a future reader from assuming they were ever recorded. The structural fix so this does not recur is PENDING-108: file the ruling as its own document when it returns, before acting on it.