diff --git a/claude/memory/MEMORY.md b/claude/memory/MEMORY.md index 237f5a6..01da462 100644 --- a/claude/memory/MEMORY.md +++ b/claude/memory/MEMORY.md @@ -73,7 +73,8 @@ permalink: claude-memory/memory > ⚠ **THE FINDING: A CONTROL PASSED TRUTHFULLY AND LICENSED A FALSE CLAIM.** IV.1 said *"F10 is the only §5 row with a stratum-B admission clause"*, marked **verified**. Three rows carry one (F3/F7/F10) — **quoted intact in the package's own I.2 and reproduced in its own IV.2 table.** The script tested whether *quotes were present*; the claim was an *inference over the rows*. **A control whose subject differs from the claim's is not a weak check — it is not a check.** ⚠ And it **understated an objection to my own proposal**, inside the paragraph written to state it at full strength. > ⚠ **`test_legacy_indices_are_not_self_verified` DOES NOT EXIST** — one occurrence repo-wide, a docstring. Carried into a corpus file, a commit message and a steward report unopened. 4th cited-a-derived-label instance; fixed `966168b`. > ⚠ **PENDING-140 [ESCALATE] FILED 08-17 — a proposed THIRD axis for Constraint 6.** Jurist *without* keys (REVIEWED-116 pt 7) ruled on my testimony and its own A4 was false; *with* keys it returned **three defects in one sitting**. **Formation, role and incentive identical across both — only access changed.** ⇒ bias-difference is **necessary and radically insufficient**; a differently-biased reader with no access checks the *account*, not the *thing*. ⚠ n=1/condition, self-reported, and **authored by the party under discussion** — filed, not acted on. Also: `contamination-problem.md` is a theory of **glazing only**, while a crude probe puts our 235 drift-patterns at **86 literal-genie / 12 trickster / 8 glazing** (129 unclassified; classifier is the very defect PENDING-139 names). -> 📋 **STEWARD OWES, first act when this line resumes:** place `## REVIEWED-121 — AMENDMENT 1 (2026-08-14)` (draft in the 08-14 transcript). ⚠ **Only that heading form is visible** to the register check — `###` and `· ADDENDUM` are invisible (PENDING-139). Then executor lands A3's three counts, tagged REVIEWED-121-A1. **`ratio_A_to_B` VOID until BOTH REVIEWED-121 and PENDING-137 land.** +> ✅ **AMENDMENT 1 PLACED 08-17** (`~/REVIEWED.md` L1813) **and A3 EXECUTED** (`a3be778`, REVIEWED-121-A1) — the latch now carries `defeater_dispositions_recorded` + `defeater_population` (**named, not numbered**, on the amendment's instruction). Register check now sees **2 amendments** where it saw 1. +> 📋 **STEWARD OWES — THE PLACED AMENDMENT IS TRUNCATED**, ending at A3's YAML block. **Missing: A3's binding rule · A4 entirely · the disposition.** ⚠ **The transcript holding the full draft was cleared, so the ONLY surviving copy of the binding rule is the comment in `corpus/v2-stratum-tags.yaml`** — recorded there as the executor's draft awaiting placement, **not** as ratified text, and it must not be cited as ratified. **`ratio_A_to_B` VOID until PENDING-137 lands too.** - [Session 2026-08-14 — the controls tested the wrong property](session-2026-08-14-the-controls-tested-the-wrong-property.md) — PENDING-134 closed; REVIEWED-121 placed/executed; PENDING-137/138/139 + a PENDING-89 docket entry filed; three package defects jurist-caught, the addendum's own A4 false, the governance checker carrying two blind spots. **LITERAL Q (sharpens 08-13's): not regression-vs-discovery — was the control's SUBJECT the claim it was cited as verifying, or an adjacent property? Census the last ~10 sessions on that axis.** **+ CODA (post-wrap, 08-17 capture): the four-flavours reading → PENDING-140 [ESCALATE] — Constraint 6 names formation and role/information/incentive; the variable that actually decided whether the jurist caught me was SUBSTRATE ACCESS.** diff --git a/claude/memory/session-2026-08-14-the-controls-tested-the-wrong-property.md b/claude/memory/session-2026-08-14-the-controls-tested-the-wrong-property.md index d33c0ca..4c97865 100644 --- a/claude/memory/session-2026-08-14-the-controls-tested-the-wrong-property.md +++ b/claude/memory/session-2026-08-14-the-controls-tested-the-wrong-property.md @@ -125,15 +125,17 @@ Read the thread, confirm it still holds, and then *do what the steward asks for ``` 0. Everything committed and pushed. studium-engine b1dc459; dotfiles 87673f5. Fleet 9/285 green. 27 open authorization items. Governance drift-check clean in all four checks. -1. OWED BY THE STEWARD, first thing when this line resumes: place - `## REVIEWED-121 — AMENDMENT 1 (2026-08-14)` in ~/REVIEWED.md. The draft is in the 2026-08-14 - transcript, conformed to the ONE heading form the register-integrity check can see - (`##` + em-dash + the word AMENDMENT; `###` and `· ADDENDUM` are both invisible — PENDING-139). -2. THEN, executor, one commit tagged REVIEWED-121-A1: land A3's three defeater counts in - corpus/v2-stratum-tags.yaml — the latch plus `defeater_dispositions_recorded` and - `defeater_population` (named, NOT a number: fixing the denominator from a point-in-time read is - the error the field exists to prevent). ⚠ NOT before placement — building against an unplaced - ruling is the ruled/placed/discharged confusion this arc has been correcting. +1. ✅ DONE 2026-08-17 — AMENDMENT 1 placed by the steward (~/REVIEWED.md L1813) and A3 executed + (`a3be778`, tagged REVIEWED-121-A1). The heading form worked: the register-integrity check now + sees TWO amendments where it saw one. +2. ⚠ OWED BY THE STEWARD — THE PLACED AMENDMENT IS TRUNCATED. It ends at A3's YAML block. + MISSING: A3's binding rule (*the latch may not be read without the count and the population in + the same read; a report may carry all three or none*), A4 entirely (the phantom-test citation + correction), and the closing disposition. The full draft is in the 2026-08-14 transcript, which + was cleared — ⚠ SO THE ONLY SURVIVING COPY OF THE BINDING RULE IS THE COMMENT IN + `corpus/v2-stratum-tags.yaml`, recorded there explicitly as the executor's draft awaiting + placement and NOT as ratified text. A4's substance survives in this file's "What was corrected" + and in commit `966168b`. Re-derive from those, or rule afresh. 3. WHEN THIS LINE RESUMES PROPERLY: the fence, or the 532-span exposure. NOT another ruling. ```