governance: seven rulings that existed only in a narrative are now in the register
REVIEWED.md ended at 86 while seven decisions had been reached and never written down. The count of rulings owed could not be answered from the register: it was 23 never-ruled, not the 26 the wake digest reported, and three of the difference were AUTHORIZED items whose headings simply omit their PENDING number. Placed: REVIEWED-87 (verbatim from its filed ruling) through -93, plus -94, the jurist's ruling on the PENDING-106 scope objection. Five of the seven were RECONSTRUCTED from a session record because the INC-2026-07-28-01 package has no filed ruling document — every other jurist gate this cycle filed one. The jurist read all seven against its own account and confirmed them; three (88, 92, 93) now carry a Provenance line recording that they are checked reconstructions and naming what was NOT recovered. PENDING-101's reasons for striking two of three findings are gone and no line recovers them. Closed: PENDING-99, -105, and -106. 106 was closed by SPLIT rather than whole — its own text named an open half (the kind-(a) census), and marking it done would have retired authorized work by bookkeeping. Filed: PENDING-108 (the ruling document is filed only when someone remembers — 12 of 13 packages did, and the one that did not is the package touching Constraint #1), -109 (that census, carrying its evidence, needing a date not an authorization), -110 (REVIEWED-N and PENDING-N are independent sequences that now collide; REVIEWED-89's own text says "DOCKETED on PENDING-89" meaning two different things). Corrected, jurist-caught: three claims of "eight days" came from reading a date out of an external incident identifier. One day, and for the reconstruction, the same day — which makes PENDING-108 worse, not better: one day was enough to lose four things permanently. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AB3Kryoy6b1pm2Nz1DYdLh
This commit is contained in:
David F Glidden
co-authored by
Claude Opus 5
Claude Opus 5
parent
f6fc59017a
commit
6cde9ad7c5
+122
-8
@@ -908,7 +908,7 @@ The verdict mark was tightened by the same logic: `✓ warranted` beside a silen
|
||||
|
||||
---
|
||||
|
||||
## PENDING-99 — The quoted tier accepts 3 of 17 human-verified citations, and the largest single cause is a full stop
|
||||
## PENDING-99 — The quoted tier accepts 3 of 17 human-verified citations, and the largest single cause is a full stop (CLOSED 2026-08-06 — REVIEWED-87 placed; @3 built and governing; Q2 carried to PENDING-100)
|
||||
**Date:** 2026-08-05
|
||||
**Tag:** [PROPOSAL] — routes to the **jurist**: `fidelity_equivalence@N` bumps require jurist ratification (V0 Ruling §2.2), and the fold-list is closed by construction.
|
||||
**Summary:** Run against the phase-2 Mauss gold — 17 citations a human read, cited and audited in March, 0 fabricated — the ratified quoted tier verdicts `GUARANTEED` on **3 of 17**. The failures are almost entirely ordinary scholarly quotation practice, not corpus defects; the single largest contributor is a **terminal full stop the citing human added when truncating**, worth 5 of the 17 on its own.
|
||||
@@ -945,7 +945,7 @@ The four causes are not one kind of thing, and that is the substance of the ask:
|
||||
|
||||
**Files affected:** none touched. Evidence reproducible from `chamber-library` canonical `essai-sur-le-don-mauss.md` (sha `2889709555f2…`) + the phase-2 round files in the vault + `engine/verify_quote.py`, `engine/fidelity.py`.
|
||||
**Jurist package:** `studium-engine/docs/quoted-tier-acceptance-JURIST-PACKAGE-2026-08-05.md` (commit `c67586d`) — self-contained, five gate questions Q1–Q5 with executor leans. Verbatim containment proven mechanically before filing: **16/16 quoted clauses contained · 9/9 inversion-built controls absent · INSTRUMENT VERIFIED**. Every cited path re-verified in session.
|
||||
**Awaiting:** Steward routing to the jurist. **Filed ≠ sent** — this line is the send-state marker; update it when relayed.
|
||||
**Awaiting:** Nothing. **RULED 2026-08-06 — REVIEWED-87 placed** (ruling filed verbatim, `studium-engine/docs/quoted-tier-acceptance-JURIST-RULING-2026-08-05.md`). Q1 authorized on engine grounds + functional analogy, explicitly NOT chamber alignment; `fidelity_equivalence@3` built, governing, 22 checks. Q2 carried to the chamber side as **PENDING-100**, which remains open. This line still read *"Filed ≠ sent"* the day after the item was ruled on — the send-state marker was never advanced, which is the PENDING-108 class in its smallest form. *(Corrected 2026-08-06: first written as "eight days", from the executor misreading the external incident identifier `INC-2026-07-28-01` as our own filing date. One day. See the correction note under PENDING-108.)*
|
||||
|
||||
---
|
||||
|
||||
@@ -1035,7 +1035,7 @@ Three findings from 2026-08-03/04/05 sit squarely inside Q1 and Q4 and are alrea
|
||||
- **Census 01/02** (`~/dotfiles/claude/governance/fool/`): the firing record divides by **whether a human is in the invocation path**. `resolve_archived_source` is healthy 349/349 with **zero** log entries; `verify-before-compose` fired exactly twice; studium `verify-quote` had **no production caller at all** until 2026-08-05. Directly Q1(a)-vs-(b).
|
||||
|
||||
**Files affected:** none — read-only pass by construction.
|
||||
**Awaiting:** Executor dispatch is given; the **Phase 1.5 blocker** needs the steward. Findings return here as new PENDING items for jurist ruling.
|
||||
**Awaiting:** Nothing on the brief itself. **RULED 2026-08-06 — REVIEWED-88 placed:** findings (1) and (3) STRUCK, finding (2) STANDS. ⚠ The jurist's *reasons* for striking (1) and (3) are not preserved in any record and were not recoverable at reconstruction — if they carry precedent they must be re-elicited, not inferred. The brief's larger yield was the steward's reframe (design-transfer, not repo-audit), which belongs to the L2 design note and is tracked there, not here.
|
||||
|
||||
## PENDING-102 — The brief hardened the report's hedged hypothesis into fact, and both AI parties did it in the same direction
|
||||
**Date:** 2026-08-05
|
||||
@@ -1058,7 +1058,7 @@ Three findings from 2026-08-03/04/05 sit squarely inside Q1 and Q4 and are alrea
|
||||
|
||||
**Recommendation:** no mechanism proposed here. The checkable question for the jurist: should a claim relayed from an external primary source carry a **modality-preservation requirement** — the hedge quoted verbatim or the claim marked as strengthened-by-the-relay?
|
||||
**Files affected:** none.
|
||||
**Awaiting:** jurist ruling; docket entry on PENDING-89.
|
||||
**Awaiting:** ⚠ **One thing, and it is not a ruling.** RULED 2026-08-06 — REVIEWED-89 placed: Q1 (modality preservation on relayed external claims) AUTHORIZED narrowly; Q2 docketed on PENDING-89, with the (c) disposition recorded as NOT established. **The Q1 requirement is now in force and lives nowhere** — it is a standing obligation whose only home is a REVIEWED entry, which no reader consults before relaying a claim. That is precisely the doc-only-control shape PENDING-106 measured and PENDING-109 will census. It needs a home in doctrine (`~/CLAUDE.md` §Epistemic Discipline is the natural site, which makes it `[ESCALATE]`, steward's hand) or it will be a rule nobody meets.
|
||||
|
||||
---
|
||||
|
||||
@@ -1104,11 +1104,11 @@ Three findings from 2026-08-03/04/05 sit squarely inside Q1 and Q4 and are alrea
|
||||
|
||||
**Recommendation.** Not a lock. The cheap, honest first move is **detection**: have the wake compare each governance file's tail against what the previous wrap recorded writing, and report divergence. Silence about a concurrent writer currently reads as absence of one.
|
||||
**Files affected:** none — read-only pass.
|
||||
**Awaiting:** steward direction on whether detection is wanted before any mechanism is designed.
|
||||
**Awaiting:** A **date**, not an authorization. **RULED 2026-08-06 — REVIEWED-93 placed:** authorized to proceed to a design brief, detection before mechanism — establish whether and how often collisions occur before any guard is sized. ⚠ Reconstructed disposition: the record confirms *authorized-to-proceed* but does not independently confirm that the detection-first ordering was ruled rather than carried over from this item's own recommendation. Treat the ordering as the executor's, not the jurist's, until confirmed.
|
||||
|
||||
---
|
||||
|
||||
## PENDING-105 — Q5 (a question Q1–Q4 do not cover): our compactor is the actor
|
||||
## PENDING-105 — Q5 (a question Q1–Q4 do not cover): our compactor is the actor (CLOSED 2026-08-06 — REVIEWED-92: withdrawn by the executor; G15's binary stands)
|
||||
**Date:** 2026-08-05
|
||||
**Tag:** [PROPOSAL]
|
||||
|
||||
@@ -1122,11 +1122,11 @@ Three findings from 2026-08-03/04/05 sit squarely inside Q1 and Q4 and are alrea
|
||||
|
||||
**Prior art it joins, not duplicates.** The 2026-08-05 limit written on the containment instrument — *containment verifies that what you quoted is accurate; it cannot verify that you quoted what matters* — is the same defect on the selection axis rather than the modality axis. Both are the actor grading its own summary.
|
||||
**Files affected:** none.
|
||||
**Awaiting:** jurist. This one touches the authorization model's evidence base, hence PROPOSAL.
|
||||
**Awaiting:** Nothing. **WITHDRAWN 2026-08-06 — REVIEWED-92 placed.** Conceded by the executor on inspection: the condition the proposal rested on was derived from PENDING-103, and PENDING-103 does not exemplify the class — `writer.ts` ships and does not perform the check, making it an undocumented gap under G15's existing binary, not a deferral. A category derived from a misclassified instance is a laundering slot. Do not revisit without an instance that genuinely exemplifies the class.
|
||||
|
||||
---
|
||||
|
||||
## PENDING-106 — Documents describe our gates as stronger than the gates describe themselves
|
||||
## PENDING-106 — Documents describe our gates as stronger than the gates describe themselves (CLOSED 2026-08-06 — instance applied + verified; the class carved out to PENDING-109, not buried)
|
||||
**Date:** 2026-08-05
|
||||
**Tag:** [HARDENING]
|
||||
|
||||
@@ -1156,6 +1156,14 @@ Three findings from 2026-08-03/04/05 sit squarely inside Q1 and Q4 and are alrea
|
||||
|
||||
**Bearing on the open half (kind (a) census):** this is now **one document, three overclaims, one of them the load-bearing clause** — a materially stronger prior than the single instance the item was filed on. It does not settle instance-vs-pattern; it raises the expected yield of the census.
|
||||
|
||||
### CLOSED 2026-08-06 — steward-directed, and closed by SPLIT rather than whole
|
||||
|
||||
**Verified against the substrate, not the ledger.** The Symmetria ledger's line *"PENDING-106 — doc FIX applied"* is a record; it was checked rather than believed. The clause in `~/_Dev/chamber-library/CLAUDE.md:90` now reads *"the read is a PROTOCOL, and the hook is a speed-bump under it, not an enforcement of it"*, carries the `⚠ CORRECTED 2026-08-06 (PENDING-106, jurist-authorized FIX)` marker, and enumerates all three overclaims plus the once-per-file mechanism finding. Landed in `bb68e3f`, *"[FIX] CLAUDE.md: the verify-before-compose clause overclaimed the hook three ways"*. **Unpushed at time of closing** (chamber-library ahead 1).
|
||||
|
||||
**Why split rather than closed whole.** This item's own text names an *"open half"* — the kind-(a) fleet census, authorized under the INC package's Q4 and never run, with no date. Marking the whole item CLOSED would have retired authorized work by bookkeeping, which is the failure PENDING-4 above documents in the opposite direction (an item advertising itself as open for 4½ months because its completion lived in the body, not the header). The instance is done; the class is carried to **PENDING-109** with its evidence intact, so that exactly one item is open for exactly the work that remains.
|
||||
|
||||
**Ruling record:** the Q4 authorization and the item split are drafted as **REVIEWED-91** in `~/dotfiles/claude/governance/REVIEWED-drafts-2026-08-06.md`, awaiting steward placement. The wider-than-authorized scope of the applied FIX (three overclaims corrected where one was named) is flagged above for objection and is **not** absorbed by this closing.
|
||||
|
||||
---
|
||||
|
||||
## PENDING-107 — Constitutional Constraint #1 says "cannot" and there is no mechanism; the executor's restraint is the only thing enforcing it
|
||||
@@ -1195,3 +1203,109 @@ Three findings from 2026-08-03/04/05 sit squarely inside Q1 and Q4 and are alrea
|
||||
**Awaiting:** steward + jurist. Independent verification requested before any action.
|
||||
|
||||
---
|
||||
|
||||
## PENDING-108 — A jurist ruling is filed as a document only when someone remembers; the one that was not is the most constitutional of the set
|
||||
|
||||
**Date:** 2026-08-06
|
||||
**Tag:** [HARDENING]
|
||||
|
||||
**Summary:** `/jurist-package` mandates that a returned ruling be filed verbatim as its own `*-JURIST-RULING-<date>.md`; across the 13 packages authored since the skill existed, 12 were and one was not — the INC-2026-07-28-01 cross-repo package, whose rulings had to be **reconstructed the same day they were ruled**, from a session memory, in the executor's wording, for the steward to check.
|
||||
|
||||
> **CORRECTED 2026-08-06, jurist-caught, and the correction strengthens the item.** This summary first read *"reconstructed eight days later."* False. `INC-2026-07-28-01` is the **UK AI Security Institute's own incident identifier** — an incident of 2026-07-28 — and the executor read a date out of an **external identifier** and used it as our timeline anchor. The package's own footer gives the real sequence: report published 2026-08-04, read in full 2026-08-05, package filed 2026-08-05, ruling acted on 2026-08-06, reconstruction 2026-08-06. **Same day, not eight.** Three instances propagated from the single misread (here, PENDING-99's `Awaiting:` line, and the drafts file); all corrected, none silently. Per `removing-a-claim-is-not-removing-the-reliance`, the test is not whether the phrase is gone but whether the conclusion still needs it: **it does not, and the corrected fact is worse for us.** "Eight days" was carrying an argument about *decay over time*. What actually happened is that **one day was enough** to make five of seven blocks reconstructions with four gaps that could not be recovered at all — the jurist's reasons for striking PENDING-101's findings (1) and (3) among them. The unfiled ruling does not degrade slowly; it is unreconstructable almost immediately.
|
||||
|
||||
**How this was found.** The steward asked why no jurist package had been filed for the INC work. The premise was wrong — a package *was* filed, and it is among the most rigorous in the set (432 lines, G1–G16 grounding, consequence-trace, scope boundary, containment proof of its own quotations). What is missing is the **return leg**: the ruling document. `~/.claude/skills/jurist-package/SKILL.md:73` prescribes it in as many words — *"When the jurist's ruling returns (steward-relayed), file it verbatim as its own `*-JURIST-RULING-<date>.md`, then append to the package"* the Addendum.
|
||||
|
||||
**The measurement, and it refuted the executor's first two framings.**
|
||||
|
||||
| Set | Packages | Ruling record exists | No record |
|
||||
|---|---|---|---|
|
||||
| `FOR-JURIST` convention (2026-07-03 → 07-20, before the skill) | 23 | 5 | **18** |
|
||||
| `JURIST-PACKAGE` convention (2026-07-20 → 08-05, after the skill) | 13 | **12** | **1 — the INC package** |
|
||||
|
||||
Method: every `*JURIST-PACKAGE*.md` / `*FOR-JURIST*.md` under `~/dotfiles/claude/governance`, `chamber-library/docs`, `studium-engine/docs`, stem-matched against every `*JURIST-RULING*.md`, with unmatched packages then re-checked for an in-package `Addendum` recording the ruling. 45 packages, 31 ruling documents, 5 Addendum-only, 19 with no ruling record anywhere.
|
||||
|
||||
**Two executor errors, both caught by measuring, both recorded rather than quietly dropped.**
|
||||
1. **Asserted a fleet-wide pattern from n=5.** The executor told the steward that "every ruling that got filed had a build waiting on it" and that the INC case was the anomaly — generalised from five items, before running any fleet check. The first check returned **24 unpaired packages**, refuting the fleet-wide claim outright. This is `ATTRIBUTED-A-CAUSE-WITHOUT-RUNNING-THE-AVAILABLE-COUNTERFACTUAL` from 2026-08-06, recurring the same day it was banked, in the item that reports it.
|
||||
2. **The refutation was then itself too coarse.** 24 unpaired split into 5 Addendum-only and 19 with no record — and the 19 stratify almost perfectly by naming convention, i.e. by whether the skill existed yet. Only the second cut showed what was actually true.
|
||||
|
||||
**What survives, stated at the strength the evidence supports.**
|
||||
- **Checked:** post-skill, 12 of 13 packages filed the ruling. The skill works; this is a *prevention* instance, not only a failure report.
|
||||
- **Checked:** the single post-skill exception is the cross-repo constitutional package — the one whose rulings touch `~/CLAUDE.md` Constraint #1, the differently-biased-checkers doctrine, and the modality-preservation requirement.
|
||||
- **NOT established:** why. The executor's conjecture — that a ruling gets filed when a *build* consumes it, and the INC rulings authorized mostly decisions rather than artifacts — is now an n=1 story about a single case. It is recorded as a conjecture and **must not** be used as the rationale for a mechanism.
|
||||
- **Bounded historical loss, not a backlog:** for the 18 pre-skill packages the verdict survives in `~/REVIEWED.md`; what is gone is the *reasoning*. Not proposed for repair.
|
||||
|
||||
**Why this is worth a mechanism despite the unknown cause.** The detector's value does not depend on knowing why the step is skipped. It fires on the condition — package with no ruling record — regardless of mechanism, and the condition is exactly what makes a ruling unreconstructable later. It also already **has its demonstrated negative instance**: the check above was run before this item was filed, on real data, and it found the INC case plus 19 historical ones. Per the standing L2 requirement, a bound that ships without a demonstrated firing is documentation.
|
||||
|
||||
**Options.**
|
||||
- **(a) Nothing; rely on the skill's prescription.** Rejected on the evidence: the step was prescribed, proven, performed twice in the same directory days earlier, and still skipped on the most important item.
|
||||
- **(b) A detector in `governance-drift-check.py`.** Report any `*JURIST-PACKAGE*.md` older than N days with no matching `*JURIST-RULING*.md` and no in-package Addendum. Runs at every wake, in the invocation path that does **not** require a human to remember — the census-02 property that distinguishes a gate that fires from a gate that is merely available.
|
||||
- **(c) File-before-act.** The ruling document is written before any act the ruling authorizes. The say–do seam applied to rulings.
|
||||
- **(d) Make placement the forcing function** — no PENDING item may be marked CLOSED without a REVIEWED reference. Rejected as filed: it enforces bookkeeping order, not record existence, and PENDING-106 was closed today with its REVIEWED entry still only drafted.
|
||||
|
||||
**Recommendation: (b) with (c).** (b) is mechanical, needs no judgement, costs milliseconds, and is honest about being a *detector* — it makes an absence visible, it does not prevent one. Say so at the point of use, per Constraint #4 and PENDING-107's lesson: this is detection, not enforcement, and it must never be described as the latter. (c) is the discipline (b) surfaces the breach of. Detection needs no authorization; changing the skill's prescribed order does.
|
||||
|
||||
**Pre-registered falsifier.** If, over the next 10 packages, the detector fires zero times *and* no ruling is later found missing by other means, the check is measuring a fixed historical incident rather than a live class, and should be retired rather than kept as reassurance. Record the count; do not let a silent check accumulate into evidence of health.
|
||||
|
||||
**Files affected:** `~/dotfiles/scripts/governance-drift-check.py` (new check); `~/.claude/skills/jurist-package/SKILL.md` (the (c) ordering); none if DEFERRED — the finding above stands on its own.
|
||||
**Awaiting:** Steward authorization for (b) and (c). The measurement is already done and needs none.
|
||||
|
||||
---
|
||||
|
||||
## PENDING-109 — The kind-(a) doc-vs-mechanism fleet census: authorized under Q4, never scheduled
|
||||
|
||||
**Date:** 2026-08-06
|
||||
**Tag:** [HARDENING]
|
||||
|
||||
**Summary:** The class half of PENDING-106, carved out so that closing the applied instance did not retire authorized work by bookkeeping — a fleet-wide comparison of each gate's own header/docstring against the document that advertises it, bounded to kind (a).
|
||||
|
||||
**Provenance.** PENDING-106 measured one instance and found the doc over-claiming against an honest mechanism. Its Q4 was put to the jurist in `INC-2026-07-28-01-cross-repo-findings-JURIST-PACKAGE-2026-08-05.md` Part VIII and **authorized 2026-08-06** — recorded as drafted **REVIEWED-91**, `~/dotfiles/claude/governance/REVIEWED-drafts-2026-08-06.md`, awaiting steward placement. PENDING-106 is CLOSED as of 2026-08-06 on its applied instance only; this item carries the remainder.
|
||||
|
||||
**Scope, bounded explicitly and not to be widened silently.**
|
||||
- **In:** kind (a) — the document over-claims against a mechanism that describes itself honestly. Method: for each gate, compare its own header/docstring against the document that advertises it. Mechanical; needs no new instrument.
|
||||
- **Out:** kind (b) — doc and mechanism both over-claim. There is no honest party to compare against, so the method does not reach it. A different instrument is owed and is **not** authorized here.
|
||||
|
||||
**Prior, strengthened since filing.** The one document examined in full carried **three** overclaims about a single hook, not one — and the third (*"opens with a Grounding section that QUOTES the ratified sections it builds on"*) is both the clause that makes the requirement substantive **and** the clause with no mechanism behind it. That raises the census's expected yield. It does not settle instance-versus-pattern, and this item must not be written up as though it had.
|
||||
|
||||
**What this item needs and does not have:** a date. It was authorized-to-proceed and left as "later", which is the state PENDING-108 exists to make visible.
|
||||
|
||||
**Files affected:** none yet — read-only census; findings return as new items.
|
||||
**Awaiting:** Steward — a date, not an authorization. The authorization is given (Q4).
|
||||
|
||||
---
|
||||
|
||||
## PENDING-110 — `REVIEWED-N` and `PENDING-N` are independent sequences that now collide, and a bare number no longer identifies an item
|
||||
|
||||
**Date:** 2026-08-06
|
||||
**Tag:** [HARDENING]
|
||||
|
||||
**Summary:** The two registers were never tied to each other; they have drifted into a range where the same integer names two unrelated items, and today's placement of REVIEWED-88 through -93 made six such collisions at once — including a sentence in REVIEWED-89 that reads *"DOCKETED on PENDING-89"*, in which the number 89 appears twice meaning two different things.
|
||||
|
||||
**How it surfaced.** The steward read "REVIEWED-88 through -93" as `PENDING`-88 through -93 — items from late July, a long way back in the register — when the entries in question are the newest in the file, lines 921–951 of 960. The misreading was correct behaviour on an ambiguous reference. The executor had written the ambiguous reference repeatedly in the same session without noticing.
|
||||
|
||||
**Measured, not estimated.**
|
||||
- **88** numbered `REVIEWED` headings; **33** carry no `PENDING-N` on the heading line.
|
||||
- **6** of those 33 have a same-numbered `PENDING` in the register. For most (11, 12, 78, 81, 82) the numbers happen to name the *same* item — harmless. For **REVIEWED-86 / PENDING-86** they name entirely different items (*differently biased checkers* vs *the jurist cannot read the constitution it design-gates*) — a live collision.
|
||||
- **REVIEWED-88…93**, placed today, each *do* name their PENDING in the heading — but their numbers collide with **PENDING-88…93**, six unrelated open items (skill-harvest FIX lane · Q3 correlation review · first L2 transfer · Vignette 1a · idle ladder · `getChainsContainingSeq`).
|
||||
- **~140** bare `REVIEWED-N` citations exist in `chamber-library`/`studium-engine` code comments, docstrings and test names.
|
||||
- **3** bare headings (78, 81, 82) are the exact three `wake-digest.py` over-reports as unruled, because it matches on the literal string `PENDING-N` in the heading. One defect, two symptoms.
|
||||
|
||||
**Root cause.** `REVIEWED-N` was never defined as *the ruling on `PENDING-N`*. Early entries were coincidentally aligned (REVIEWED-11 ↔ PENDING-11, -12 ↔ -12), which taught the alignment as an expectation without ever making it a rule; the sequences diverged and never recovered. `~/CLAUDE.md`'s own template says `## REVIEWED-[N] — [Matches PENDING-N title]` — *matches the title*, not the number, which is precisely the gap.
|
||||
|
||||
**Options.**
|
||||
- **(a) Renumber so the sequences align.** REJECTED. It rewrites a historical record — one entry of which is GPG-sealed — to fix a legibility problem, and silently breaks every commit message, code comment and `engine/fidelity.py` citation pointing at a REVIEWED number.
|
||||
- **(b) Convention: never write a bare register number again.** Always `REVIEWED-89 (PENDING-102)`. Costs nothing, needs no migration, and most headings already do it.
|
||||
- **(c) Backfill the headings.** Bounded to those where the number names a *different* item, plus the three the digest miscounts — not all 33, most of which are unambiguous (REVIEWED-29 states outright it has no PENDING number).
|
||||
- **(d) Teach `wake-digest.py` to read the body, not only the heading,** for `PENDING-N`.
|
||||
- **(e) Migrate the ~140 code citations.** REJECTED. They sit in docstrings and comments where surrounding context disambiguates; the change is large, mechanical, touches gate code, and buys little.
|
||||
|
||||
**Recommendation: (b) + (c) + (d).**
|
||||
(b) is the rule. (c) is one-time and small, and is the steward's hand — `REVIEWED.md` is not the executor's file. (d) is the durable part and the reason to do all three: **it is the only one that does not depend on anyone remembering.** Per PENDING-108, filed hours earlier in this session, a prescribed-and-proven step still got skipped on the most important item — so of a convention, a backfill and a detector, weight the detector.
|
||||
|
||||
**Check that it worked.** After (c) and (d): `wake-digest.py`'s open-item count should fall from 21 to 18, matching the hand cross-reference already run today. If it does not, the digest is matching on something else again and (d) is incomplete.
|
||||
|
||||
**Also owed, same surface, not yet done.** The seven entries placed today carry no provenance marker; five are executor reconstructions from a session narrative, and `REVIEWED.md` presents all seven with equal authority. The one-line `**Provenance:**` addition drafted in `~/dotfiles/claude/governance/REVIEWED-drafts-2026-08-06.md` remains unplaced. Same class as this item: **the register does not say on its face what it is.**
|
||||
|
||||
**Files affected:** `~/dotfiles/scripts/wake-digest.py` (d — executor); `~/REVIEWED.md` (c + the provenance lines — steward's hand); `~/CLAUDE.md` §Steward-Jurist Interface template (b, if the convention is made doctrine — `[ESCALATE]`).
|
||||
**Awaiting:** Steward authorization. (b) is agreed in conversation 2026-08-06; this item records it and asks for (c) and (d).
|
||||
|
||||
---
|
||||
|
||||
+51
@@ -911,3 +911,54 @@ brief. No work is blocked meanwhile; `wake-digest.py --brief` remains the fallba
|
||||
- **Process note, corrected.** The convergence was not two independent readers reaching the same idea from a shared root — the steward shared the jurist's exchange with him directly with the executor, as context, before Document A was filed. That is a tighter loop than parallel derivation: one party's language, relayed, feeding the other's proposal, which now returns to the first party for review. It does not bear on whether the underlying principle is sound — that turns on the separation-of-powers reasoning itself, not on who phrased it first — but it does mean the jurist should weigh, more carefully than usual, whether what reads as correct in Part III is the argument holding up rather than the jurist's own words returning familiar. Noted because it changes the standard the jurist should apply to itself here, not because it changes the ruling.
|
||||
**If AUTHORIZED for drafting:** Land Part III (with the Q2 weld applied) beside Constraint 6, plus the companion `contamination-problem.md` note named as owed in Part V, amendment-first per that repo's own discipline. Docket the Q3 correlation review separately. Tag REVIEWED-86.
|
||||
**Awaiting:** the Q2 weld, then steward review of the woven text; the Q3 note's exact wording; the correlation-review docket entry; and — the one that actually matters here — the steward's own explicit act of authorizing application, which nothing above substitutes for.
|
||||
|
||||
## 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.
|
||||
|
||||
## REVIEWED-88 — PENDING-101 — Cross-repo research brief: structural implications of INC-2026-07-28-01
|
||||
**Date:** 2026-08-06
|
||||
**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.
|
||||
**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.
|
||||
|
||||
## 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.
|
||||
|
||||
## 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.
|
||||
|
||||
## 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.
|
||||
|
||||
## REVIEWED-92 — PENDING-105 — Q5: is "scheduled-not-yet-built" a legitimate third category?
|
||||
**Date:** 2026-08-06
|
||||
**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.
|
||||
**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.
|
||||
|
||||
## REVIEWED-93 — PENDING-104 — Q3: no concurrency guard exists on shared governance state, and the collision has already been observed
|
||||
**Date:** 2026-08-06
|
||||
**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.
|
||||
**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.
|
||||
|
||||
## 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.
|
||||
@@ -0,0 +1,219 @@
|
||||
# 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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.
|
||||
|
||||
```markdown
|
||||
## 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):
|
||||
|
||||
```markdown
|
||||
**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):
|
||||
|
||||
```markdown
|
||||
**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):
|
||||
|
||||
```markdown
|
||||
**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.*
|
||||
@@ -5,11 +5,15 @@ metadata:
|
||||
node_type: memory
|
||||
type: feedback
|
||||
originSessionId: 75d3a0a3-70eb-4286-92ab-0aa05d419f0c
|
||||
modified: 2026-08-06T14:05:31.088Z
|
||||
modified: 2026-08-06T15:03:21.078Z
|
||||
---
|
||||
|
||||
# Session Ledger — 2026-08-06
|
||||
|
||||
> **Session 2 opened 17:04 CEST** (8 min after the wrap). Same day, same ledger — entries below
|
||||
> this line belong to the second session unless timestamped earlier. Thread inherited and
|
||||
> confirmed: the chamber parse fix.
|
||||
|
||||
## Returns
|
||||
|
||||
- **2026-08-06T13:58 — the banked drift pattern fired within the first minute of the session.**
|
||||
@@ -92,8 +96,6 @@ metadata:
|
||||
|
||||
- None. No agents spawned.
|
||||
|
||||
## Sub-agent dialogues
|
||||
|
||||
## Bypasses
|
||||
|
||||
- **Applied PENDING-106's FIX wider than the ruling's words.** The jurist authorized correcting
|
||||
|
||||
Reference in New Issue
Block a user