docs(governance): census 02 — has each instrument ever fired? + PENDING-95..98

Closes the scope gap census 01 declared for itself: the seven instruments it
named as uncensused. Pre-registered before any source or config was read,
with predictions and a discrimination condition.

Census 01 asked whether an instrument had a real negative instance — a
question about CAPABILITY. Census 02 asks whether it has ever engaged in
real life. Those come apart exactly at the drift-checker's shape, and
2026-08-04 found the gap six times (retrieval_count = 0 across 19,915 nodes
for four months; two replay modules that have never processed an event).

VERDICT: every instrument a human runs by hand has a rich firing record;
every instrument that runs by itself has none — and the two guarding the
engine's output have no consumer at all. The record divides by whether a
human is in the invocation path, not by age, quality, or importance.

verify-before-compose fired exactly twice (2026-07-17, 2026-07-18), evidence
surviving only in harness transcripts; and it CANNOT fire on 31 of 59 guarded
files, including the live constitution, because it folds the existing file's
contents into its search for the attestation. audit_cruft, verify_conversion
and apply_char_glyphs are exemplary. resolve_archived_source is healthy at
349/349 and has zero log entries. studium verify-quote and
fidelity_equivalence@2 have no production call site at all.

Prediction 5 inverted for the second census running, for a new reason.
Census 01: decay, not construction, is the failure mode. Census 02: the
recording is attached to the human, so an instrument's record vanishes the
moment it is automated — which is when it starts running often enough to
matter.

Two of my own candidate findings died to their controls and are recorded as
such: probing the resolver with engine source_ids against the chamber's
canonical_slug key space (one sentence from "the resolver is inert"), and
reading character_as_image at the wrong YAML nesting (nearly "zero glyph
maps declared"; there are two sources and a 63-item census).

Filed together: PENDING-95 [HARDENING] the hook cannot fire on the
constitution · PENDING-96 [HARDENING] "SILENCE — ✓ warranted" certifies the
index and claims the answer · PENDING-97 [PROPOSAL] FTS AND-s bare tokens
with no semantic layer, recall dies as questions lengthen · PENDING-98
[HARDENING] firing history exists only where a human invokes.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WuMjg3ipEVa3n8CoSzoyvc
This commit is contained in:
David F Glidden
2026-08-04 17:10:40 +02:00
co-authored by Claude Opus 5
parent 9c2a7c985c
commit 3a1790dcd6
4 changed files with 209 additions and 0 deletions
+45
View File
@@ -802,3 +802,48 @@ Measured against the register itself before acting. Four corrections; the item's
**Falsifier, already run:** any restart with `min cursor > 0`, or any `kind: catch-up`. **13/13 restorations report `min cursor: 0`; 6/6 replay classifications report `rebuild`; catch-up has never executed.**
**Files affected:** `src/core/keystone/readiness/replay-coordinator.ts:300/319/340/368`, `src/modules/base.ts:134`. **None touched.**
**Awaiting:** Steward authorization before any change; then Seb, as L1 core.
## PENDING-95 — `verify-before-compose` cannot fire on the constitution it exists to protect
**Date:** 2026-08-04
**Tag:** [HARDENING]
**Summary:** The hook folds the *existing file's* contents into its search for the grounding attestation, so any artifact that already carries `GROUNDED-IN:` anywhere is permanently un-gateable — 31 of 59 guarded files, including `chamber-library-specification.md`.
**Rationale:** The gate is the structural mitigation for the `re-derived-from-training` failure, adopted 2026-07-17 *because session-start prose had failed ≥4 times*. It works: exercised directly today with presence and absence controls, it blocks a new ungrounded amendment (exit 2) and passes a grounded one. But an ungrounded Edit payload aimed at the **live constitution** passes (exit 0), because five prior `GROUNDED-IN:` blocks sit in that file's body. Coverage therefore decays monotonically toward zero as artifacts accumulate markers, and it reached zero on the most load-bearing file some time before today. The design is honest at the header ("or the existing file"; "a speed-bump… not a guarantee"); the *consequence* appears in no doc, and the chamber CLAUDE.md's own clause states flatly that such a write "is **DENIED** unless the artifact carries" the attestation — which is true only for artifacts that do not yet carry one.
**Countervailing evidence, recorded because it cuts the other way:** all 28 guarded files lacking a marker are dated ≤ 2026-07-17, and every constitutional artifact created after the hook landed carries one. The gate has plausibly shaped behaviour even where it can no longer block. Filename dates are a proxy; creation dates are not git-verified.
**Options:** (a) test the attestation against the **write payload only**, never the existing file — every write re-grounds; (b) require the attestation to name a `(read YYYY-MM-DD)` within N days of the write, so a stale marker stops counting; (c) require a marker whose cited version matches the file's current version, so a supersession must re-ground; (d) leave as designed and document the decay honestly in the chamber CLAUDE.md clause and the hook header.
**Recommendation:** (c), with (d) regardless. (a) is the strongest but would fire on every routine edit to a 170KB spec and would be worked around within a week — a gate that is always in the way stops being read. (c) binds the check to the thing that actually changes (the version being amended), which is exactly when re-grounding is owed. (d) is owed under Constitutional Constraint #4 whatever else is chosen: the current state is a gate reporting protection it does not provide.
**Confidence:** ~0.95 on the mechanism (directly exercised, five controls). ~0.5 on which remedy is right — this is a judgment about how the steward and executor will actually behave under friction, not a fact about the code.
**Files affected:** `~/.claude/hooks/verify-before-compose.sh:38-44`; `~/_Dev/chamber-library/CLAUDE.md` (the grounding clause). **None touched.**
**Awaiting:** Steward authorization.
## PENDING-96 — The engine's `SILENCE — ✓ warranted` certifies the index and claims the answer
**Date:** 2026-08-04
**Tag:** [HARDENING]
**Summary:** When retrieval returns nothing, the engine reports *"No match — this is genuine silence, not a gap"* on the strength of a check that only establishes the index is complete and current — it cannot establish that retrieval reached what is there.
**Rationale:** Asked `grey zone`, the engine returns certified silence. The corpus holds **ten** matches for `gray zone`, **all ten in `levi-drowned-and-saved`**. The corpus is American-spelled; the steward is Canadian-spelled. This is the shape census 01 was opened to catch — a passing check certifying a property of the code while claiming a property of the result — now at the engine's consuming end, and wearing a checkmark that makes it *more* credible than an ordinary empty result. It bears directly on the telos: a voice that says "I have nothing on the grey zone" about Primo Levi is not a cautious voice, it is a confidently wrong one, and confident wrongness is the exact failure v1 was retired for.
**Falsifier, already run:** the probe *"the quality without a name"* returns the same certified silence and is **correct** — *The Timeless Way of Building* is not among the 13 sources. The warrant is not always wrong; it is unable to tell its two cases apart, which is the defect.
**Options:** (a) restrict the warrant's wording to what it checks — "the index is complete and current as-of X; no match was found" — and drop "genuine silence, not a gap"; (b) additionally report the retrieval method and its known blindnesses on every silence, so the reader can judge; (c) make silence conditional on a second, differently-implemented probe agreeing (differently-biased checkers applied to retrieval).
**Recommendation:** (a) immediately — it costs one string and removes a false assurance today. (b) next. (c) is the durable answer and is entangled with PENDING-97; it should not be designed before the retrieval decision is taken.
**Files affected:** `~/_Dev/studium-engine/engine/retrieve.py` (the silence branch and its warrant string). **None touched.**
**Awaiting:** Steward authorization.
## PENDING-97 — Engine retrieval AND-s bare tokens and has no semantic layer: recall collapses as the question lengthens
**Date:** 2026-08-04
**Tag:** [PROPOSAL]
**Summary:** `retrieve.py` passes the user's normalized string straight to `drawers_fts MATCH`, where FTS5 bare terms are conjunctive, so a natural-language question must have **every** token co-occur in one drawer — and the corpus has no vector index at all.
**Rationale:** Measured on the real index: `gray` → 51 hits · `gray zone` → 10 · `levi the gray zone` → **0** · `what does levi mean by the gray zone` → **0**. The engine's stated purpose is discourse with a library; a question phrased as a question is the normal case and it returns nothing, certified (PENDING-96). `embed_spike.py` and `rerank_spike.py` exist but remained spikes; `sqlite_master` holds no vector or embedding table. This is a data-model and retrieval-architecture decision, not a bug fix — which is why it is PROPOSAL and not HARDENING. It is also the engine-side twin of the L1 finding: the ingest half is elaborate and governed, the consuming half has never been exercised against a real question, so nobody noticed it does not answer.
**Options:** (a) query-construction only — OR the tokens with BM25 ranking, add phrase handling and an orthographic fold (British/American, œ/oe, accents) at index and query time; (b) (a) plus a semantic layer — embed the 5,685 drawers, retrieve hybrid, rerank; (c) treat retrieval as out of scope for V1 and instead constrain the engine to accept only quoted-phrase queries, making its narrowness explicit rather than silent.
**Recommendation:** (a) first and separately, because it is cheap, reversible, and measurable against the very probes above — and because until it lands, no judgment about semantic retrieval rests on a clean baseline. Then (b) as its own decision with its own gate. (c) is worth naming because it is *honest*, and honest narrowness beats silent breadth — but it forecloses the telos, so it should be rejected deliberately rather than by default.
**Confidence:** ~0.95 on the mechanism (measured, six queries, monotone). Low on the remedy — the orthographic question in particular (whose spelling is canonical when the reader and the corpus differ?) is a curatorial decision, not an engineering one, and it is the steward's.
**Files affected:** `~/_Dev/studium-engine/engine/retrieve.py:99-103`, `engine/store.py` (index build), `corpus/index.db` (would require a rebuild). **None touched.**
**Awaiting:** Steward authorization.
## PENDING-98 — Firing history is recorded only where a human is in the invocation path
**Date:** 2026-08-04
**Tag:** [HARDENING]
**Summary:** Census 02 classified all seven remaining instruments; the record divides cleanly by whether a person invokes the tool, not by the tool's age, quality, or importance.
**Rationale:** Where `tool-evolution-log.md` reaches, the record is the best in the system — dated, artifact-named, `PASS-BUT-FALSELY` treated as the priority signal, patch and reason cross-referenced (`audit_cruft`: 160 corpus files found that the old gate was blind to; `verify_conversion`: 948/952 with 4 genuine fails; `apply_char_glyphs`: Levi, 527 docs, 0 unclassified). Where it does not reach, nothing records at all: `verify-before-compose` fired twice and the evidence survives only in Claude Code session transcripts, a harness artifact with unknown retention; `resolve_archived_source` runs on **every graduation**, is healthy at 349/349, and has **zero** entries in the log because no human invokes it; studium `verify-quote` and `fidelity_equivalence@2` are called by nothing but their own CLI and test suite. The log's own rule — *"after **every** use — success or failure"* — is in practice *after every use a human initiates*. Automatic use is invisible to it by construction, and automatic use is precisely the use that becomes frequent enough to matter.
**Rationale, second order:** this is the same class as the 2026-08-03 governor findings and the 2026-08-04 replay finding, one level up. There the controls existed and never engaged; here the *recording* of engagement is the thing that never engaged. An instrument with no firing history cannot be audited, cannot be retired for disuse, and cannot be shown to have decayed — which is how census 01's 71 uncited ladder entries got there.
**Options:** (a) have automatic gates append a one-line firing record to a machine log (path, verdict, timestamp) — cheap, but a log nobody reads is the `Recall canary FAILED` pattern, which fired 8 times unread; (b) (a) plus a wake-digest line that surfaces *counts* — "verify-before-compose: 0 firings in 30 days" — so absence becomes visible rather than silent; (c) extend the tool-evolution discipline explicitly to automatic tools, with a periodic review slot rather than a per-use one; (d) accept and declare that automatic instruments are unrecorded, so no one reads coverage into their silence.
**Recommendation:** (b). (a) alone reproduces the exact failure this census exists to name — a record that exists and is never read is indistinguishable from no record. The wake already reads a digest daily and already reports pointer counts and drift counts; a firing-count line is the same shape and costs one script change. (c) is good practice but relies on a slot that will be skipped under pressure; (d) is honest but gives up something recoverable cheaply.
**Files affected:** `~/dotfiles/scripts/wake-digest.py`; `~/.claude/hooks/verify-before-compose.sh`; `~/_Dev/chamber-library/_curation/tool-evolution-log.md` (the discipline statement). **None touched.**
**Awaiting:** Steward authorization.
@@ -0,0 +1,68 @@
# Census 02 — Has each instrument ever produced a positive result?
**Pre-registered:** 2026-08-04, before reading any of the seven instruments' source or config.
**Origin:** the literal question left by the 2026-08-04 wrap, closing the scope gap census 01 declared for itself.
---
## The question
Census 01 asked: *does each instrument have a real negative instance to test against, and is its absence recorded?* That is a question about the instrument's **capability**.
2026-08-04 found something one level more basic, six times over: an instrument can pass every check ever run against it while never having fired at all. `retrieval_count = 0` across 19,915 nodes for four months. `coherence_evaluated = 0` of 813,178 chains. `ANALYZE` never run in four months. Three of five `governance-drift-check.py` families inert. Two L1 replay modules that have never processed a single event — pinning the resume floor at zero and making every restart a full rebuild.
So, of each instrument: **has it ever produced a positive result — ever actually fired, matched, blocked, or caught something in real use — and does a record exist that could tell us either way?**
An instrument can be DEMONSTRATED at build time (census 01's gold standard) and inert ever since. That is not a hypothetical; it is precisely the drift-checker's shape.
## Unit of census
The seven instruments census 01 explicitly declared **out of scope**, censused entire:
1. `verify-before-compose` (the PreToolUse hook)
2. `audit_cruft`
3. `verify_conversion`
4. `resolve_archived_source`
5. `apply_char_glyphs`
6. studium-engine `verify-quote` V1
7. `fidelity_equivalence@2`
## The test applied to each
**Two independent axes, recorded separately.** Conflating them is the error this census exists to avoid — "it works" and "we can tell that it works" are different claims.
- **Axis A — engagement.** Is the instrument currently reachable? Does its trigger condition still match the substrate as the substrate now stands? Answerable from source and config.
- **Axis B — firing record.** Does any durable record exist that would show a positive firing? Answerable by grep. A session transcript is not a durable record; a governance file, a log, a committed artefact is.
Four outcomes:
- **FIRED-RECORDED** — a durable record names a real occasion on which it fired.
- **FIRED-UNRECORDED** — it demonstrably *can* fire and prose or memory attests that it did, but no durable record exists.
- **INERT** — its trigger cannot currently match. It reports success by never engaging.
- **UNDETERMINED** — cannot be settled on either axis. Reported as unclassifiable, not dropped.
## Predictions (recorded before the read)
1. **`verify-before-compose` is currently LIVE and has fired at least once.** ~0.75. Basis: `MEMORY.md` carries the standing preference *"Don't fight the block"* — which reads as a lesson earned by being blocked. That is prose attestation, not a record.
2. **No durable firing record exists for `verify-before-compose`.** ~0.85. A PreToolUse hook blocks by exit code and stderr; the trace lands in a session transcript, which nothing reads.
3. **At least one of the seven is INERT** — its trigger has drifted from the substrate it watches. ~0.6. Basis: census 01's prediction-5 inversion (decay, not construction, is the failure mode) compounded by six instances found on 2026-08-04.
4. **The chamber-library tools (`audit_cruft`, `verify_conversion`, `apply_char_glyphs`) are FIRED-RECORDED**, via `_curation/tool-evolution-log.md`. Only ~0.5 — *the log exists* and *the log records firings* are different claims and I have checked neither.
5. **Overall skew: FIRED-UNRECORDED dominant.** The instruments work; the record of their working does not exist.
## The census's own discrimination condition
A single instrument cannot discriminate anything. This census discriminates only if, across the seven, **both** a FIRED-RECORDED and an INERT (or FIRED-UNRECORDED) instance appear.
If all seven land in one bucket, the census has discriminated nothing and must be reported as such rather than as a result.
If the skew comes out opposite to prediction 5 — mostly FIRED-RECORDED — **the first hypothesis to test is that I accepted a weak record as a firing record**, not that our instruments are unusually well recorded.
## Falsifier for the central claim
For any instrument reported as having fired: **name the occasion and the artefact.** If I cannot name them, the verdict is FIRED-UNRECORDED at best. *"I remember it firing"* is not a record — it is the thing this census is trying to tell apart from a record.
## Stopping rule
Complete when all seven are classified on both axes. Unclassifiable members reported as unclassifiable.
**Order of execution:** `verify-before-compose` first — it is the only one of the seven that gates *steward-facing writes*, so silent inertness is worst there.
@@ -0,0 +1,77 @@
# Census 02 — RESULT
**Run:** 2026-08-04. Pre-registered at `census-02-have-they-ever-fired-PREREGISTRATION.md` before any instrument's source or config was read.
**Question:** has each instrument ever produced a positive result — ever actually fired — and does a record exist that could tell us either way?
---
## Verdict in one line
**Every instrument that a human runs by hand has a rich firing record. Every instrument that runs by itself has none — and the two that guard the engine's output have no consumer at all.**
The census discriminated (both buckets populated, per the pre-registered condition), so it is reportable as a result rather than as nothing.
---
## The seven, censused entire
| # | Instrument | Axis A — engagement | Axis B — firing record | Verdict |
|---|---|---|---|---|
| 1 | `verify-before-compose` | **LIVE**; blocks a new ungrounded artifact (exit 2, produced today). **Cannot fire on 31 of 59 guarded files**, including the live constitution | 2 firings — 2026-07-17 09:44:34 (Write), 2026-07-18 11:55:44 (Edit). Recoverable **only** from Claude Code session transcripts | **FIRED-UNRECORDED** |
| 2 | `audit_cruft` | LIVE, wired, fleet-tested | Dense: 2026-06-16 `PASS-BUT-FALSELY` ×2 → **160 corpus files carrying residue the old gate was blind to** (95 image embeds, 64 raw svg, 8 `U+FFFD`); 2026-07-19 kindle-residue class | **FIRED-RECORDED** |
| 3 | `verify_conversion` | LIVE, wired, fleet-tested | 2026-06-16 calibration — **948/952 pass on the known-clean Loeb tier, 4 genuine truncated stubs**; false-failed a clean Loeb Aeschylus → fixed; 2026-06-28 `PASS-BUT-FALSELY` in the gate itself | **FIRED-RECORDED** |
| 4 | `resolve_archived_source` | **LIVE and healthy** — 349/349 manifest entries keyed; positive-controlled: real slugs resolve and the files exist on disk | **Zero mentions in `tool-evolution-log.md`.** It runs on every graduation and has never once been reviewed after use | **FIRED, UNLOGGED** |
| 5 | `apply_char_glyphs` | LIVE, fleet-tested, REFUSE teeth intact; 2 sources mapped, 63-item census | 2026-07-23 — Levi, **527 docs, 0 unclassified, 0 residual glyph `<img>`**, recorded in both the log and the spec's declared data | **FIRED-RECORDED** |
| 6 | studium `verify-quote` V1 | Functional — **42/42** deliberate-mismatch checks pass | **No production call site anywhere.** Only its own CLI `main()` and its test suite | **NO RECORD CAN TELL** |
| 7 | `fidelity_equivalence@2` | Shipped and correct (`FIDELITY_VERSION = "fidelity_equivalence@2"`) | Imported by `verify_quote` alone — it fires exactly as often as #6 does, which is unrecorded | **NO RECORD CAN TELL** |
---
## The finding
**The tool-evolution log is the only mechanism in this system that successfully records firing history — and it only reaches tools a human runs by hand and then reviews.**
Where the discipline reaches (#2, #3, #5), the record is exemplary: dated, artifact-named, `PASS-BUT-FALSELY` recorded as the priority signal, tool patched and the reason logged. This is the strongest instrument record anywhere in the system, stronger than the verification ladder's and stronger than `fool/`'s.
Where it does not reach, nothing records:
- `verify-before-compose` fires inside the harness, so no human is present to log it. Its two firings survive only because Claude Code happens to retain transcripts — an accident of tooling with unknown retention, not a designed record.
- `resolve_archived_source` runs inside `graduate_to_canonical` on every graduation. Because a human never *invokes* it, nobody ever *reviews* it. Zero log entries for a function that has run hundreds of times.
- `verify-quote` and `fidelity_equivalence@2` are invoked by nothing at all.
The rule the log states — *"after **every** use — success or failure — we review how the tool actually behaved"* — is in practice **after every use a human initiates.** Automatic use is invisible to it by construction.
## Two structural findings, beyond the record
**1. `verify-before-compose` is disarmed on the artifact it exists to protect.** Lines 40–41 fold the *existing file's* contents into the search for the grounding attestation. Once a file contains `GROUNDED-IN:` anywhere, no future write to it can ever be gated. **31 of 59 guarded files are in that state**, including `chamber-library-specification.md`, every versioned spec v2.1.0–v2.9.0, and `graduation-spec.yaml`. The behaviour is documented ("or the existing file"; "a speed-bump… not a guarantee"); the *consequence* — coverage decaying monotonically to zero, and already zero on the constitution — is documented nowhere.
Countervailing evidence, recorded because it cuts the other way: **all 28 guarded files lacking a marker are dated ≤ 2026-07-17; every constitutional artifact created after the hook landed carries one.** Consistent with the gate having shaped behaviour even where it cannot now block. Filename dates are a proxy; creation dates are not git-verified.
**2. The engine's `SILENCE — ✓ warranted` certifies index currency and presents it as an answer about the corpus.** Asked `grey zone`, the engine replies *"No match — this is genuine silence, not a gap."* The corpus holds **ten** matches for `gray zone`, **all ten in `levi-drowned-and-saved`**. The warrant checks that the index is complete and current; it cannot check that retrieval reached what is there. This is verbatim the shape that opened census 01 — a check certifying a property of the code while claiming a property of the result — now at the engine's consuming end and wearing a checkmark.
Mechanism, and it is wider than spelling: `retrieve.py:103` passes the normalized user string straight to `drawers_fts MATCH`, where bare terms are **AND-ed**. Recall collapses as the question lengthens — `gray` 51 hits, `gray zone` 10, `levi the gray zone` **0**, `what does levi mean by the gray zone` **0**. Natural-language questions — precisely what *"enter into discourse with my library"* means — return certified silence by default. There is no vector table; `embed_spike.py` / `rerank_spike.py` remained spikes.
Discrimination held here too: the probe *"the quality without a name"* is **correctly** silent — *The Timeless Way of Building* is not among the 13 sources. One real defect and one real correct silence, side by side.
## Residual findings
- **No `.glyph-manifest.json` has ever been written anywhere.** The two-sided manifest (REVIEWED-74) is the input to `resolve_added`'s added-side fabrication check; its wiring is exercised only by a synthetic fixture in `test_tools.py`. The check has never seen a real manifest.
- **The engine's `source_id` and the chamber's `canonical_slug` are disjoint key spaces for the same works** (`levi-drowned-and-saved` vs `the-drowned-and-the-saved-primo-levi`), with nothing joining them. A 7th instance of the shared-name/two-senses class the chamber CLAUDE.md counts.
- `engine/verify_quote.py:7` names `fidelity_equivalence@1` in prose while the shipped constant is `@2`. Stale docstring; `[FIX]` class.
## Two of my own claims died to their controls — recorded, because that is the census working
- I probed `resolve_archived_source` with engine `source_id`s and got `None` three times, including for the nonsense control. Reporting "the resolver is inert" was one sentence away. The positive control — resolving real slugs *drawn from the manifest itself* — showed it healthy at 349/349. **The instrument was mine, and it was wrong.**
- I read `character_as_image` at the YAML top level, got nothing, and nearly reported "zero glyph maps declared." It is nested at `promotion.character_as_image` and holds **2 sources and a 63-item census**.
Both are the day's own failure class (a number from an uncontrolled instrument), and both died to a control run before the claim left the workspace.
## Predictions, graded
1. `verify-before-compose` LIVE and fired ≥ once (~0.75). **Held** — exactly twice, both dated.
2. No durable firing record for it (~0.85). **Held.**
3. At least one of the seven INERT (~0.6). **Reframed, not held.** None is inert in the drift sense — every one still engages what it was built to engage. The real shapes were *disarmed-by-accumulation* (#1) and *no-consumer* (#6, #7), neither of which I anticipated.
4. Chamber tools FIRED-RECORDED via the log (~0.5). **Held and stronger than predicted** for #2/#3/#5 — and **wrong for #4**, which is a chamber tool with zero log entries because no human invokes it.
5. Overall skew FIRED-UNRECORDED dominant. **Wrong.** The skew is not by age or by quality; it is by **whether a human is in the invocation path**.
Prediction 5 has now inverted twice, in two censuses, for two different reasons. Census 01: decay, not construction, is the failure mode. Census 02: **the recording discipline is attached to the human, not to the instrument** — so an instrument's record vanishes the moment it is automated, which is exactly when it starts running often enough to matter.
@@ -70,3 +70,22 @@ metadata:
## Sub-agent dialogues
## Bypasses
---
# Second sitting — 2026-08-04 (post-clear)
## Returns
- **2026-08-04T13:40 CEST — corrected the inherited resumption path rather than following it.** The wrap named `chamber-library/_curation/fool/census-01-negative-instances-RESULT.md`; that directory does not exist. The census lives at `~/dotfiles/claude/governance/fool/` (RESULT + PREREGISTRATION). Found by `find`, not assumed. A wrap-authored path is a claim like any other; the cheapness of the check is the point.
## Confidence to recalibrate
- **Standing, inherited and unchanged:** *a number that matches a constant is not a cause* — four refutations yesterday, all resting on arithmetic agreement with a code constant. And *knowing the name of a failure class confers no immunity to it*. Both bear directly on today's thread, which is precisely about instruments that report success without ever having engaged.
- **Not yet substrate-checked:** the 13 open PENDING items were carried from the wake digest, not re-verified against their own disposition. Three were filed today (92/93/94) and are verified by authorship. The other ten are **unverified — last confirmed at filing**.
## Open horizons
- **PULLING THREAD (inherited, confirmed):** census 01 against the seven uncovered chamber/engine gates — `verify-before-compose` · `audit_cruft` · `verify_conversion` · `resolve_archived_source` · `apply_char_glyphs` · studium `verify-quote` · `fidelity_equivalence@2`. Question: has each ever produced a positive result, and does a record exist that could tell us either way?
- Parked hard: the 2.32 events/min rate (needs a controlled measurement, four theories lost).
- Awaiting steward: PENDING-92 annotation before its local 3-commit branch moves.