diff --git a/REVIEWED.md b/REVIEWED.md index 32ff777..c379700 100644 --- a/REVIEWED.md +++ b/REVIEWED.md @@ -1872,3 +1872,56 @@ What does not change. The doctrine paragraph as ratified. Point 9's H3 disclosur re-dispositioned — L926 and L1551 stand as at REVIEWED-118 and REVIEWED-119. ratio_A_to_B remains VOID, still awaiting PENDING-137 and all dispositions (REVIEWED-116 point 5). Tag follow-on commits REVIEWED-121-A1. +## REVIEWED-122 — PENDING-142 — The open/closed criterion answers a question adjacent to the one it is asked +**Date:** 2026-08-17 +**Decision:** AUTHORIZED — option (d) as the frame, with (a) and (b) inside it, on five conditions. Two legs severed and dispositioned separately below. + +**Notes:** The item's own recommendation is adopted as written, and the reasoning behind it survives challenge: (a) and (b) each close a class, and neither can close Class A, which is unclosable by construction rather than by defect. Only (d) lets the instrument report the case it cannot decide. Constitutional Constraint #4 requires a system to report its own limits; an instrument whose subject is governance state is the last place that requirement may be relaxed. + +1. CONDITION — **the acceptance check is a pre-registration, and its ordering is load-bearing.** The item warns that the acceptance check may not be a count. That is raised from warning to requirement, with an ordering the item does not specify: the per-item disposition answer key over all 69 filtered items is **hand-read and committed before the implementation exists**, with the commit hash recorded. A key written after the fix inherits the fix's reading of what closure means, and would pass by construction. This is the pre-registration discipline already operating in the Fool trials, applied to an instrument rather than a model. If the key and the implementation disagree on any item, the disagreement is the finding and is reported — never reconciled by amending the key. + +2. CONDITION — **(b) defaults to not-closed on any unrecognized decision verb, and the enumeration is not the executor's alone.** The item names this trap and must not walk into it: an unlisted verb yields UNDETERMINED, never CLOSED. The list of closing verbs is drafted by the executor and ruled here before it is wired, because the enumeration decides what the instrument can see and is therefore a gate-design claim, not an implementation detail. + +3. CONDITION — **(a) resolves by title only on a unique match, and every title-resolution is visible in the output.** Where normalized-title matching supplies a closure the id-match could not, the digest marks it as title-resolved rather than reporting it indistinguishably from an id-matched closure. Two or more candidates yields UNDETERMINED. The risk the item names — joining two genuinely distinct items sharing a title — is not eliminated by this, only made legible. + +4. CONDITION — **UNDETERMINED is enumerated, never merely counted.** Every item in that bucket is listed by id and header with the reason it could not be decided. A three-valued report whose third value is an opaque number replaces a wrong answer with an unreadable one, which is the same failure in a better costume. + +5. CONDITION — **the reader is fixed; the placed records are not silently amended.** REVIEWED-78, -81 and -82 are placed rulings and are not to be edited to satisfy the current parser. Fixing the record to please the instrument inverts which of the two is authoritative. Should the steward decide the headers are worth normalizing, each amendment carries a dated note stating what was changed and why, per no-silent-revision — but that is a separate steward act and is not authorized here. + +6. **The docstring correction is severed and authorized now as [FIX], not gated on the mechanism.** `ruled_pendings`'s docstring records REVIEWED-78/-81/-82 as 'like-numbered rulings … concerning other matters'; REVIEWED-78's own Notes say they were like-numbered *on purpose*, to satisfy the closure rule as it then stood. The docstring is a substrate-contradicted claim and its falsity does not depend on which option is built. Two requirements on the correction: it records the true history rather than merely deleting the false sentence, and the executor checks whether anything else in the script relies on the discarded reading. Removing a claim is not the same as removing the reliance on it. + +7. **Class C is a live correctness problem and is dispositioned ahead of the mechanism.** PENDING-121 is certain — REVIEWED-110 reads 'DESIGN GATE PASSED WITH CONDITIONS (1-4), then HELD OPEN', an item held open by its own ruling and hidden by the tool — and it is restored to the open list by hand at once, not when the fix lands. PENDING-124 and -128 are flagged UNDETERMINED pending a steward read; the item's refusal to assert their status is correct and is preserved rather than resolved here. That a design gate could read as closed is the dangerous direction of this defect: it means the taxonomy's distinction between passing a gate and receiving authorization was invisible in the instrument that reports what awaits authorization. + +8. **Class A is a steward matter, and its consequence outlives the fix.** Three-valued reporting makes the two unclosable items honest; it does not make them closable. Renumbering their headers touches `PENDING.md` and is the steward's act, not the executor's. Recorded because it survives whatever is built: **`PENDING — ICP-19 Remit Expansion (Observer Problem)` will report open whether or not the steward–reviewer conversation it gates has taken place.** Its persistence in the open list is not evidence about the state of that conversation, and has not been since the item was written. The Observer Problem gate's status is steward testimony and reachable no other way. + +9. …**The family is raised to a named ladder entry rather than a running count.** ⚠ AMENDED 2026-08-17, before execution, on the executor's surfacing of PENDING-141: the ladder's contents are a variable in a live pre-registered trial that cannot be e-run, and this condition would change the measured object. **The ladder entry is DEFERRED until that trial is graded at 84 transcripts, or until PENDING-141 is ruled otherwise.** The condition is not withdrawn — the family is real and the entry is owed. Two parts of condition 9 are severed: the lineage addition to this item's kin list touches PENDING-142 and not the ladder, and proceeds now; only the ladder entry waits. Recorded here rather than dropped, because a deferred entry with no record is how the family came to be rediscovered five times as a fresh coincidence. + +10. **Scope of this ruling, stated rather than assumed.** I read PENDING-142 verbatim via `governance_item`, and independently observed `governance_state()` reporting PENDING-81 open against an AUTHORIZED REVIEWED-81 — one datum consistent with Class B, obtained from the instrument under review. Everything else — the census figures, the class memberships, the 39 stale `Awaiting:` lines, the docstring's wording — is executor testimony from a script I cannot run. That is precisely why condition 1 requires a hand-read key: the ruling cannot verify the census, and the acceptance check is the only instrument that can. + +11. **A follow-on item is owed and is not folded in.** The drift-check covers `~/CLAUDE.md` and reads no script. The docstring at condition 6 was a substrate-contradicted claim living outside anything that checks for them, inside the instrument that reports governance state. Whether script-resident claims warrant coverage is a [HARDENING] question larger than this item and is to be filed separately rather than absorbed here. + +**If AUTHORIZED:** Draft and commit the hand-read answer key first, with its hash recorded. Submit the (b) decision-verb enumeration for ruling before wiring. Then implement (d) with (a) and (b) inside it, per conditions 2–5. Apply the condition-6 docstring [FIX] independently and immediately; restore PENDING-121 by hand on the same pass. Tag commits with REVIEWED-122. Report the key-versus-implementation comparison in full, including agreements, rather than reporting only the delta. + +## REVIEWED-123 — PENDING-141 — Ladder contents are a variable in a live trial, and the freeze needs a scope the item does not give it +**Date:** 2026-08-17 +**Decision:** AUTHORIZED — option (a), HOLD, on six conditions. (b), (c) and (d) declined, with reasons recorded. + +**Notes:** The item's core reasoning survives challenge and is strengthened by an argument it does not make. Its own honest caveat — that per-entry reach as a function of ladder length is untested on *both* sides — reads as a weakness and is not one. Consider the payoff either way. If ladder size does not affect retrieval, holding costs four weeks' delay on rows the item correctly says are not decaying. If it does, appending destroys the only instrument standing behind REVIEWED-95's causal claim, and that instrument cannot be re-run. An un-rerunnable measurement against a delay on non-decaying rows is not a close call, and it does not require the untested assumption to be resolved in either direction. **(a) is correct under both branches**, which is a stronger warrant than the item claims for itself. + +1. CONDITION — **the freeze is general, not S2-specific, and covers contents as well as size.** The item is titled and argued around the 41 S2 rows, but a single entry from an unrelated ruling was caught by it within hours of filing, correctly. The scope is hereby stated rather than left to inference: **no additions, rewordings, removals or reorderings of `reference-verification-ladder.md` while this hold is in force**, from any source, whatever its authorization. The `/wake-up` skill already froze its own trial line for this reason; the ladder is frozen on the same footing and for the same trial. + +2. CONDITION — **report N-now, and bound the hold.** 'Until graded at 84 transcripts' is not a date, and a hold with no expiry and no visible distance to expiry is how a temporary freeze becomes a permanent one. The executor reports the current transcript count at the next wake, and this item carries a **review point at 30 days** — not an automatic lift, a requirement to state where the count stands and whether the trial is still tracking. If N-now proves near 84, the steward may elect (b) on that fact; that election is not made here, because the fact is not in the record. + +3. CONDITION — **entries earned during the freeze accumulate in this item as an owed-entries list.** A freeze without a queue is a silent loss, and the wrong-subject family now under REVIEWED- is already the standing example of what recurs unrecognised. They are queued **here** rather than in a new file: a separate holding document is one a reader might reach *instead of* the ladder, which is the same uncontrolled variable one layer along. Each queued entry names its authorizing ruling so the freeze lift is mechanical. + +4. CONDITION — **grading does not authorize the append.** The item's second-order risk — that a tripled ladder may be a *worse* ladder, degrading per-entry reach even as the wake line raises the odds of opening the file — is real and is not resolved by grading the trial. On grading, the S2 batch **returns for a ruling**, not for execution, and that ruling addresses per-entry reach as its own question. Read as 'hold then append', (a) merely moves the problem four weeks and arrives with the same measurement still unmade. + +5. CONDITION — **the `MEMORY.md` amendment is retired when the hold is.** The index line was amended at filing to remove the execute-now reading, which was correct. A hold-notice that outlives its hold is the same trap in the opposite direction — a later session reading 'held pending trial' for a trial graded months earlier. Retiring it is part of the freeze lift, not a follow-on. + +6. ⚠ **A standing limit on what this trial can conclude, named because it is not fixable and must not be discovered at grading.** The party whose retrieval is being measured has read the pre-registration, the item, and this ruling. The trial therefore measures whether an executor *who knows the trial exists* reaches the ladder after a wake line is added — which is not the same claim as REVIEWED-95's. This does not weaken the case for protecting the instrument: a bounded measurement is worth more than a destroyed one. It bounds the **conclusion drawn at grading**, and the grading write-up states it rather than inferring a clean causal result. This is the observer condition at instrument scale and no design available here escapes it. + +7. **Options declined.** **(c)** is the tempting one and the item's own objection holds: a recorded confound on a design of this power is close to no result, and would leave REVIEWED-95's causal claim appearing to rest on a graded trial while resting on nothing — worse than an ungraded claim, because it launders the gap. **(d)** is illusory for the reason given; the wake line names the ladder as a whole, so no subset of additions leaves the reader's encounter unchanged. **(b)** is not rejected on the merits but on the record: it trades power for speed and nobody has stated how much power there is to trade. Condition 2 makes that fact available; the option is revisitable on it, which is why this is a decline and not a rejection. + +8. **Scope of this ruling.** I read PENDING-141 verbatim via `governance_item`. The trial's design, the 14%/77%/83%/0% retrieval figures, the 64-session base and the transcript count are executor testimony from instruments I cannot run. The ruling does not depend on their precise values — it depends on the asymmetry in Notes above, which holds across a wide range of them. Where it would depend on them is condition 2's election of (b), which is deferred until the count is in the record. + +**If AUTHORIZED:** (a) is already the null action and remains in force; nothing needs doing to start it. Report N-now at the next wake. Open the owed-entries list on this item and queue the wrong-subject ladder entry deferred under REVIEWED-123 condition 9 as its first row. Set the 30-day review. Tag nothing — no commit follows from this ruling except the queue and the count.