session 2026-07-24 late-morning: Levi 14 witness-brackets derived + interior-verified (all clean, no La Chute); pulling thread = born-digital lane run (de-risk on The Drowned and the Saved); Warde timezone offset banked

2026-07-24 11:19:44 +02:00
parent 1d5b6a78ef
commit 6d0f2df5bd
6 changed files with 78 additions and 4 deletions
@@ -5,7 +5,7 @@ metadata:
  node_type: memory
  type: reference
  originSessionId: d1e67361-d1b9-4dac-a0c4-e7a0e26211c4
-  modified: 2026-07-24T08:49:17.702Z
+  modified: 2026-07-24T09:18:01.451Z
 ---
 # MEMORY — Reference layer (consult on demand)
@@ -29,6 +29,9 @@ Split out of [MEMORY.md](MEMORY.md) on 2026-07-06 to keep the wake-loaded index
 # Archived sessions + stable reference layer (relocated verbatim from MEMORY.md, 2026-07-06)
 ## Archived (2026-07-24 morning — chamber-sources problem CLOSED: omnibus re-sourced + 13 gaps filled + invariant landed · Silva named · Warde OCR launched; demoted on promote at the 2026-07-24 late-morning wrap)
 - [Session 2026-07-24 — chamber-sources problem CLOSED (omnibus re-sourced + 13 gaps filled + invariant in protocol) · Silva named · Warde OCR on M4 · WAKE INTO the 14-bracket verify](session-2026-07-24-chamber-sources-closure-13-sources-silva-warde.md) — Set out for the Levi 14-bracket verify (today's chosen bite); a source-lookup exposed the omnibus witness was **mis-sourced** — pinned to a byte-identical copy of the wrong *Drowned-and-the-Saved* PDF (sha `9c898202`), not the Complete Works. Steward chose to **close the whole chamber-sources problem PERMANENTLY first.** **(1)** Re-sourced the omnibus → the correct Complete Works EPUB (`~/fix-levi-omnibus.py`, steward ran; sha `1be71a50`, 527 spine/14-work TOC); DTS untouched. **(2)** Census (1,297 canonicals: 344 pinned · 940 Loeb-compound · 13 unsourced) → **located + archived ALL 13** (`~/archive-13-sources.py`; sources across master library + `__Making sequence sources` [Mumford OCR] + `__Chamber Source EPUBs` + Downloads [steward placed Bachelard-FR/Jaccottet-Airs/Unesco]; edition calls Warde=77KB · RedBook=Reader's-Ed · Moby=B&N-Classics) → **0 non-Loeb gaps.** **(3)** Landed the invariant into chamber `CLAUDE.md` (source = `resolve_archived_source` from Chamber Sources, NEVER a plan/doc path) + [[feedback-resolve-source-through-chamber-sources]] — the durable fix for the "recurring corrections on details" the steward named after **3 corrections** (I trusted the plan path, re-derived a settled state as a defect, over-corrected to "leave it"). **(4)** Byte-dupes: live library = **0** (July-1 pass complete); steward emptied the 935MB `_trash/dedupe-20260701` quarantine. **(5)** Named the consolidation reservoir **Silva** (`~/Documents/Silva/`; = EVERYTHING, Chamber Sources = deliberate immutable canon-source duplicates); book/non-book classifier demonstrated. **(6)** Launched **Warde's OCR on the M4** (`olmocr_mlx.py`, monitor `bi7h2cmcu`). **PULLING THREAD (steward-set): wake into the ORIGINAL plan — the Levi 14-bracket verify, now WARM** (reconnaissance banked at `chamber-library/_curation/levi-second-pilot-2026-07-23/witness-bracket-derivation-WIP-2026-07-24.md`; start at step 1 = pull each work's opening text from the EPUB spine, locate in the witness, interior-verify per La Chute). Silva deferred to LAST; Warde auto-continues. **LITERAL Q: do the 14 witness brackets interior-verify cleanly, or does one resist (La Chute at omnibus scale)? + has Warde's OCR landed on the M4 (check `bi7h2cmcu` / the log)?** Read the session file + the WIP note at wake.
 ## Archived (2026-07-23 — REVIEWED-69 merged + v2.4.0 · character-as-image finding → PENDING-70 → v2.5.0 · glyph-mapping BUILT; demoted on promote at the 2026-07-24 wrap)
 - [Session 2026-07-23 — REVIEWED-69 merged + v2.4.0 · character-as-image finding → PENDING-70 ruling → v2.5.0 · glyph-mapping BUILT](session-2026-07-23-reviewed69-70-v2.4-v2.5-character-as-image-glyph-mapping.md) — A very long single session that ran the whole PENDING-69/70 arc to ground. **(1)** merged the boundary-drop mechanism to main + cut spec **v2.4.0** (REVIEWED-69; standalone MINOR bump — vehicle resolved by fact, nothing assembling; `f466ed0`). **(2) Prepping the Levi pilot surfaced a corpus-integrity finding:** the witness is silently DAMAGED — a 2026-06-16 image-drop MUTILATED char-bearing glyphs mid-word (Wstawać→Wstawa, Brașov→Braov, Oświęcim→Owicim), verified live, each confirmed by the passage's own gloss. Steward named the structural cause: **the whole canon predates the constitution + the fleet** → the extant witness is a pre-fleet conversion, not editorial gold; census = **13/248-backup files** carry mid-word glyph drops (Jung 18, Levi 18, Derrida, Zibaldone, Lichtenberg…), a confirmed floor. **(3)** drafted the legacy-body reframe as a jurist package (PENDING-70) → **RULED**: Q1/Q3/Q4 confirmed (Q1 corrects a defect in the one-door ruling's OWN wording; `witness_class`=positive attributed attestation), **Q2 accepted-in-principle but SUBSTITUTE CONDITION ruled** (my reframe dropped the JUDGMENT-COST test the condition existed for — enumerate demonstrable classes in advance · report judgment cost · legacy-witness-promotions-only) → **spec v2.5.0 landed** (`e37e076`). **(4) glyph-mapping BUILT + DEMONSTRATED** (`apply_char_glyphs.py`, the Q3 hard precondition; `3852d46`; fleet 216→**222**): letter-adjacent glyph `<img>`→declared SOURCE Unicode, REFUSES unclassified (attest-never-default); VIEWED the 4 source glyphs (ca=ć, as=**ş cedilla** steward-confirmed NOT comma-below ș, s=ś, e=ę); demonstrated on the real 527-doc Levi EPUB (substituted=9, unclassified=0 corpus-wide, survives pandoc end-to-end). **PULLING THREAD: the Levi second pilot ITSELF (step 3) — now unblocked, the gate before the 47-file verbatim-fidelity-restoration wave.** First move = derive + interior-verify the 14 witness brackets (La Chute lesson) → run the full lane (`convert_lane_borndigital.py … the-complete-works-of-primo-levi-primo-levi`) → 14 per-work comparisons + **JUDGMENT-COST reporting** (the substitute Q2 condition). **LITERAL Q: when the Levi pilot runs (14 works, ~18 mutilation sites now repaired), does the judgment cost stay tractable, or explode when the easy mechanical patterns run out (the jurist's actual worry)? + do the 14 brackets interior-verify cleanly at omnibus scale?** ⚠ origin (Gitea) 2 commits behind (`5d61f2d`,`3852d46`) — retry when it recovers. Read the session file at wake.
@@ -6,7 +6,7 @@ metadata:
  type: note
  permalink: claude-memory/memory
  originSessionId: 22915403-bc5d-4796-9c7d-196b7c30d2f9
-  modified: 2026-07-24T08:50:04.866Z
+  modified: 2026-07-24T09:18:37.354Z
 permalink: claude-memory/memory
 ---
@@ -57,7 +57,7 @@ permalink: claude-memory/memory
 - [Be (laundromat)](project-be-laundromat.md) — canonical Be tracker (est. 2026-06-08). Be = Skemantix startup (Seb+David) funding CapableMind's ladder; **bridge, not venture**. Decisions LOCKED (entity/pricing/infra in file); a11y gate MERGED. **Pre-revenue WTP gate = renovate Pat → charge her; discipline: no new spec until it clears → nothing for executor on be.** Repo @ `f43a0fd`.
 ## Active Session
- [Session 2026-07-24 — chamber-sources problem CLOSED (omnibus re-sourced + 13 gaps filled + invariant in protocol) · Silva named · Warde OCR on M4 · WAKE INTO the 14-bracket verify](session-2026-07-24-chamber-sources-closure-13-sources-silva-warde.md) — Set out for the Levi 14-bracket verify (today's chosen bite); a source-lookup exposed the omnibus witness was **mis-sourced** — pinned to a byte-identical copy of the wrong *Drowned-and-the-Saved* PDF (sha `9c898202`), not the Complete Works. Steward chose to **close the whole chamber-sources problem PERMANENTLY first.** **(1)** Re-sourced the omnibus → the correct Complete Works EPUB (`~/fix-levi-omnibus.py`, steward ran; sha `1be71a50`, 527 spine/14-work TOC); DTS untouched. **(2)** Census (1,297 canonicals: 344 pinned · 940 Loeb-compound · 13 unsourced) → **located + archived ALL 13** (`~/archive-13-sources.py`; sources across master library + `__Making sequence sources` [Mumford OCR] + `__Chamber Source EPUBs` + Downloads [steward placed Bachelard-FR/Jaccottet-Airs/Unesco]; edition calls Warde=77KB · RedBook=Reader's-Ed · Moby=B&N-Classics) → **0 non-Loeb gaps.** **(3)** Landed the invariant into chamber `CLAUDE.md` (source = `resolve_archived_source` from Chamber Sources, NEVER a plan/doc path) + [[feedback-resolve-source-through-chamber-sources]] — the durable fix for the "recurring corrections on details" the steward named after **3 corrections** (I trusted the plan path, re-derived a settled state as a defect, over-corrected to "leave it"). **(4)** Byte-dupes: live library = **0** (July-1 pass complete); steward emptied the 935MB `_trash/dedupe-20260701` quarantine. **(5)** Named the consolidation reservoir **Silva** (`~/Documents/Silva/`; = EVERYTHING, Chamber Sources = deliberate immutable canon-source duplicates); book/non-book classifier demonstrated. **(6)** Launched **Warde's OCR on the M4** (`olmocr_mlx.py`, monitor `bi7h2cmcu`). **PULLING THREAD (steward-set): wake into the ORIGINAL plan — the Levi 14-bracket verify, now WARM** (reconnaissance banked at `chamber-library/_curation/levi-second-pilot-2026-07-23/witness-bracket-derivation-WIP-2026-07-24.md`; start at step 1 = pull each work's opening text from the EPUB spine, locate in the witness, interior-verify per La Chute). Silva deferred to LAST; Warde auto-continues. **LITERAL Q: do the 14 witness brackets interior-verify cleanly, or does one resist (La Chute at omnibus scale)? + has Warde's OCR landed on the M4 (check `bi7h2cmcu` / the log)?** Read the session file + the WIP note at wake.
+- [Session 2026-07-24 late-morning — Levi 14 witness-brackets DERIVED + INTERIOR-VERIFIED (all clean, no La Chute) · pulling thread = the born-digital lane RUN](session-2026-07-24-late-morning-levi-14-brackets-verified.md) — Woke (post context-clear) into the morning's set thread — the Levi second-pilot **14-bracket verify** — and closed it in one bite. **All 14 witness brackets derive + interior-verify cleanly against the source EPUB spine; NONE resists — no La Chute at omnibus scale** (morning literal-Q #1 ANSWERED). Method: EPUB-spine cross-ref (calibre flattened the work-body headers, so title-grep can't bracket — the recon's KEY FINDING held) via a **punctuation-normalized word-sequence matcher** (defeats curly-quote/dash + the running header `The Complete Works of Primo Levi` calibre stripped). Verify = (a) disjoint monotonic ordering `866<3097<…<32111` [no work's START inside another's span]; (b) uniform 9–13 line paratext gaps incl. both Volume-divider boundaries [dividers image-only→blank; no container paratext swallowed]; (c) interior sampling 25/50/75%×14 [Faussone→Wrench, Pyotr→If-Not-Now, all-verse→Poems…]. Coverage 30,353/32,998 (92%); the 8% is correctly-excluded container paratext. Endpoint precision-bug caught + fixed honestly (first-word→last-word line; work-1 true end = `—STUART WOOLF` L3097). **Deliverable: `chamber-library/_curation/levi-second-pilot-2026-07-23/witness-brackets-2026-07-24.md`** (table + evidence + declared-data YAML). **Did NOT mutate the hook-gated `graduation-spec.yaml`** (downstream, lane-run's step). **Warde OCR** (morning literal-Q #2 ANSWERED): running normally on the M4 ~84%→landing; **timezone near-miss caught by substrate check — the M4 is in CANADA (EDT/UTC−4, ~6h behind Barcelona)**, banked into [[reference-capablehands-standing-authorization]]. **PULLING THREAD: the born-digital lane RUN against the 14 brackets** — start DE-RISKED with a single-work cut on **The Drowned and the Saved (bracket 13, [28657,29818])** to test the flagged "footnote injection untested at 14-work complexity" risk BEFORE the full 14. This IS `promotion.scale_application` (owed; gates one-door corpus-wide + the 47-file wave). **LITERAL Q: cutting *The Drowned and the Saved* through the lane vs bracket 13 — does footnote injection hold at its note-density, and does judgment cost stay tractable, or explode when the easy mechanical patterns run out?** Read the session file + the brackets deliverable + the WIP recon note at wake.
 ## Historical reference → MEMORY-reference.md
 Older archived-session pointers and the stable reference layer (steward profile · project-state detail · L1/L2/Chamber inventories · legacy pending-work · reference-file list) live in [MEMORY-reference.md](MEMORY-reference.md) — consult on demand; not loaded at wake. Recent cross-session trajectory comes from the Active Session entry above + the recent `session-*.md` files (wake §2.b.1; the MemPalace `handoffs` glance was retired 2026-07-07 with the wind-down).
@@ -429,3 +429,5 @@
 {"subject": "claude-code", "predicate": "drift-pattern", "object": "source-from-plan-not-resolved-through-substrate — used plan §3's written source PATH (master library) instead of resolving via resolve_archived_source; then re-derived the resulting mis-pin as a FRESH defect without reading the banked Making-source record; then over-corrected to 'don't re-open' when the steward wanted it FIXED. Steward corrected 3× + named the meta-pattern ('recurring corrections on details'). Recurrence of resurface-banked-notes + assert-from-derivation at the source-provenance layer. Antidote LANDED: chamber CLAUDE.md invariant + feedback-resolve-source-through-chamber-sources.", "valid_from": "2026-07-24", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-24-chamber-sources-closure-13-sources-silva-warde.md", "extracted_at": "2026-07-24"}
 {"subject": "the-complete-works-of-primo-levi-primo-levi", "predicate": "chamber-source", "object": "Complete Works EPUB (sha 1be71a50, 527 spine/14 works) in Chamber Sources — RE-SOURCED 2026-07-24 from the wrong Drowned-and-Saved PDF pin (sha 9c898202)", "valid_from": "2026-07-24", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-24-chamber-sources-closure-13-sources-silva-warde.md", "extracted_at": "2026-07-24"}
 {"subject": "chamber-library", "predicate": "invariant", "object": "every non-Loeb canonical has its source in Chamber Sources (0 gaps 2026-07-24, 13 closed); Loeb from the loeb-dsl compound artifact; invariant now in chamber CLAUDE.md. Silva (~/Documents/Silva/) = complete browse-reservoir (deferred build); Chamber Sources = immutable canon-source duplicates.", "valid_from": "2026-07-24", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-24-chamber-sources-closure-13-sources-silva-warde.md", "extracted_at": "2026-07-24"}
 {"subject": "claude-code", "predicate": "drift-pattern", "object": "assumed-remote-host-timezone — nearly reported a Warde OCR '5-hour stall' that was purely the M4 being in Canada (EDT, ~6h behind Barcelona); caught by checking the host's OWN clock + process CPU, not assuming. Instance of assert-from-derivation-not-substrate.", "valid_from": "2026-07-24", "valid_to": null, "confidence": 0.95, "source_file": "session-2026-07-24-late-morning-levi-14-brackets-verified.md", "extracted_at": "2026-07-24T11:15:00Z"}
 {"subject": "levi-omnibus-witness", "predicate": "brackets-status", "object": "14 work-brackets DERIVED + interior-verified clean (no La Chute); banked in pilot-dir witness-brackets-2026-07-24.md; declared-data YAML NOT yet written to graduation-spec.yaml (downstream lane-run step)", "valid_from": "2026-07-24", "valid_to": null, "confidence": 0.98, "source_file": "session-2026-07-24-late-morning-levi-14-brackets-verified.md", "extracted_at": "2026-07-24T11:15:00Z"}
@@ -5,8 +5,11 @@ metadata:
  node_type: memory
  type: reference
  originSessionId: 7d92573b-80fa-4d25-9d65-45abd76ca80d
  modified: 2026-07-24T09:12:25.790Z
 ---
 CapableHands = the steward's M4 mini OCR/inference workhorse at **david@10.0.1.136** (~/capablehands/olmocr_mlx.py, splice_pages.py; uv + mlx). The steward has **durably authorized remote operation on this host** for OCR/inference work and asked not to be asked again about it (2026-07-01). Don't re-prompt the steward for permission to use CapableHands for these jobs.
 **⚠ Timezone: the M4 is physically in CANADA (Eastern, UTC−4/EDT) — ≈6 hours BEHIND the steward's Barcelona (CEST). The `10.0.1.136` address reads like a LAN box but the machine is remote.** When judging whether a long-running job (OCR log mtime, `page N/M` progress) is live or stalled, compare against the **M4's own `date`** and the **process CPU (`ps -o stat,%cpu,etime,time -p PID`)** — NEVER against Barcelona local time. (2026-07-24: nearly reported a Warde OCR "5-hour stall" that was purely this offset — the log had written 14s earlier in EDT; caught by checking the M4 clock + process CPU per [[feedback-checkable-claim-surfaces-bugs]].)
 Related: [[project-L1-reliability]] (CapableHands built as a BMF clasp), [[project-source-library-link-and-dedupe]], [[project-making-sequence-source-set]].
@@ -0,0 +1,58 @@
 ---
 name: session-2026-07-24-late-morning-levi-14-witness-brackets-derived-interior-verified-all-clean-no-la-chute-pulling-thread-now-the-born-digital-lane-run-de-risked-by-a-single-work-cut-on-the-drowned-and-the-saved
 description: "Woke into the Levi 14-bracket verify (the morning's set thread) and closed it — all 14 witness brackets derive + interior-verify cleanly against the source EPUB spine; NONE resists (no La Chute at omnibus scale). Deliverable banked in the pilot dir; graduation-spec.yaml deliberately NOT mutated (hook-gated, downstream). Warde OCR confirmed running normally on the M4 (~84%, timezone near-miss caught by substrate check — M4 is Canada/EDT, 6h behind Barcelona). PULLING THREAD: the born-digital lane RUN against these brackets — start de-risked with a single-work cut on The Drowned and the Saved (bracket 13) to test the flagged 'footnote injection untested at 14-work complexity' risk before the full 14."
 metadata: 
  node_type: memory
  type: project
  originSessionId: 7b9e072c-82cb-45c4-ae17-c017422ddd20
  modified: 2026-07-24T09:16:49.105Z
 ---
 # Session 2026-07-24 (late morning) — the Levi 14-bracket verify, closed clean
 Woke (context cleared after the morning's chamber-sources detour) into the thread the morning wrap set: **the Levi second-pilot 14-bracket verify.** Took it all the way in one concentrated bite; it verifies cleanly. The lane run is the next logical step — deliberately left for a fresh session.
 ## PAST — what happened + why
 **The bite: 14 witness brackets DERIVED + INTERIOR-VERIFIED — all clean, none resists.** (Literal-question half #1 from the morning wrap, ANSWERED.)
 - **Substrate re-verified first:** witness sha `c73fc063…` (32,998 lines); source resolves via the governed `archive_sources.resolve_archived_source` → Chamber Sources EPUB sha `1be71a50…`, 527 spine (the invariant the morning detour landed now holds). Scratchpad EPUB extraction was gone → re-extracted from the byte-identical Chamber Sources EPUB.
 - **Method:** the recon's KEY FINDING held — calibre **flattened the work-body headers**, so title-grep can't bracket. Derived brackets by EPUB-spine cross-ref via a **punctuation-normalized word-sequence matcher** (defeats curly-quote/dash mismatch between EPUB-HTML and calibre-MD, spans poem/blank-line breaks, and strips the running header `The Complete Works of Primo Levi` which calibre removed — 0 witness occurrences). START(N) = first witness line of the work's spine block (per-work Contents sub-TOC header, or first body/epigraph for works 9 & 13 which lack a leading sub-TOC); END(N) = last-word line of the work's last **attached** paratext (afterword sig / final chapter / editorial note).
 - **Interior verification (the La Chute gate — endpoint agreement ≠ span identity), 3 independent checks all PASS:**
  1. **Disjoint monotonic ordering** `866<3097<3106<…<32111` — no work's START inside another's span.
  2. **Uniform 9–13 line paratext gaps**, INCLUDING both Volume-divider boundaries (4→5, 9→10 = 12 lines each, same range as ordinary gaps) → the Volume I/II/III dividers are **image-only, render as blank**; no container paratext swallowed. (`VOLUME I/II/III` strings appear only in the global front CONTENTS, L45/86/123.)
  3. **Positive interior sampling** 25/50/75% × 14 — every sample unmistakably its own work (Faussone→Wrench, Pyotr/partisans→If-Not-Now, all-verse→Poems, the survivor-correspondence→Drowned, etc.).
 - **Coverage:** 30,353/32,998 lines (92%); the 8% is container paratext (Morrison/Goldstein/Ferrero front + Weil/Quirico/Scarpa back + image dividers) — correctly EXCLUDED, never dropped. Matches the recon's container-paratext list exactly.
 - **Endpoint-precision correction (recorded honestly):** first pass returned END as the *first*-word line of the closing key (work 1 → 3093); corrected to *last*-word line → true afterword sig `—STUART WOOLF` L3097; work 14 true end = closing editorial note L32111 (Weil's back-matter essay begins L32122 — the apparent "68-line gap" was matching Weil's *signature*, not his essay start). Mechanical index fix, not a span-identity failure.
 **The 14 brackets (START, END):** 1:[866,3097] 2:[3106,4809] 3:[4818,7199] 4:[7208,9285] 5:[9297,10761] 6:[10770,11887] 7:[11896,14430] 8:[14439,16194] 9:[16207,19876] 10:[19888,24671] 11:[24682,26811] 12:[26820,28645] 13:[28657,29818] 14:[29827,32111].
 **Deliverable:** `chamber-library/_curation/levi-second-pilot-2026-07-23/witness-brackets-2026-07-24.md` — table + full evidence + declared-data YAML in the `promotion.witness.brackets` shape. **Did NOT mutate the hook-gated `graduation-spec.yaml`** (that's the downstream governed step when the lane runs; pilot-dir record is executor-authority). WIP note (`witness-bracket-derivation-WIP-2026-07-24.md`) status → SUPERSEDED/DONE.
 **Warde OCR (literal-question half #2, ANSWERED): running normally on the M4, ~187/222 (~84%), ~12 min to land at check-time.** Graduation horizon auto-continues when it lands. **Near-miss caught:** first ssh glance showed the log "stuck" at page 185, mtime 05:10 → I hypothesized a 5h stall (I'd assumed the M4 was Barcelona-time). Verify-the-substrate caught it: the **M4 is in CANADA, Eastern (EDT/UTC−4), ~6h BEHIND Barcelona** (steward confirmed) — the log had written 14s before I looked; `ps` showed 14.8% CPU / actively working; the log advanced 185→187 between my two checks. Banked the offset into [[reference-capablehands-standing-authorization]] so the `10.0.1.136`-looks-like-LAN trap doesn't recur.
 **Decisions NOT made (deliberate):**
 - **Did NOT run the born-digital lane** — the brackets were its gate; the lane is a fresh substantial bite (the WIP flags its footnote injection UNTESTED at Levi's 14-work complexity). Same craftsman's-restraint that banked Silva this morning.
 - **Did NOT mutate `graduation-spec.yaml`** — hook-gated + it's the lane-run's step.
 - **Did NOT commit/push chamber-library** — working-tree records (CLAUDE.md, WIP+brackets, regenerated indexes) left for the steward's repo process; origin (Gitea) 2 behind (`5d61f2d`,`3852d46` = the REVIEWED-70 commits).
 ## PRESENT — the mood
 Clean, satisfying bite: the thread the morning set was carried across the context-clear and closed in one concentrated pass, on correctly-sourced ground the morning detour had just secured. The verify-the-substrate disciplines earned their keep twice — once structurally (the matcher, not title-grep, because the substrate told us headers were flattened) and once on myself (the timezone near-miss: I nearly reported a stall from an assumption; checking the M4's own clock + process CPU stopped a false finding reaching the steward — [[feedback-checkable-claim-surfaces-bugs]] turned on my own report). The endpoint first-word/last-word bug is the kind of thing the La Chute discipline is *for*: don't trust the anchor, read the actual boundary line. Steward preference honored: single tight bite, then wrap — did not chain into the lane.
 ## FUTURE — what is pulling
 **PULLING THREAD: the born-digital lane RUN against the 14 verified brackets** — the pilot run the brackets gated. Cut 14 candidates from the Chamber Sources EPUB → per-work source-fidelity (vs a pandoc reference) → witness-comparison against each bracket → classify into the closed vocabulary → **judgment-cost reporting**. Load-bearing beyond the pilot: it IS `promotion.scale_application` (owed — the curation-bearing scale pilot that gates one-door corpus-wide, hence the 47-file kindle-residue wave).
 **ACTIONABLE RESUMPTION POINT (as of wrap — re-judge against what changed):** Do NOT run all 14 first. **De-risk with a single-work cut: The Drowned and the Saved (bracket 13, [28657, 29818], 1,161 lines)** — a canonical work, essay-dense with footnotes + Works Cited + a translator's afterword, and the *smallest* of the note-heavy works. Run it end-to-end through the born-digital lane (`convert_lane_borndigital.py` — the Eichmann-pilot driver; glyph-mapping Q3 precondition MET) → source-fidelity vs pandoc reference → witness-compare against bracket 13 → footnote injection. If it holds, the flagged "footnote injection untested at 14-work complexity" risk is retired and the other 13 are mechanical. If it doesn't, we've found the failure on one tractable work, not mid-marathon. Bounded question → bounded answer. Read the brackets deliverable + the WIP recon note first; both are banked in the pilot dir.
 **Other horizons (ranked, deferred with reason):**
 - **Warde graduation** — OCR should have LANDED by wake (was ~12 min out at 11:15 CEST / 05:15 EDT). Retrieve from M4 `~/capablehands/scratch/warde-essays-olmocr.md` → clean → verify_conversion → graduate → catalogue → sidecar → NEW typography canonical (DISTINCT slug from short-text `warde-crystal-goblet`). Independent of the lane priority. **Check the M4 clock, not Barcelona's, when judging its logs.**
 - **Silva consolidation** (Phase 3) — the "cleanup work" to return to LAST, after the pilot settles. Named/decided (=everything), method in [[project-source-library-link-and-dedupe]]; move-map tool not built.
 - **Repo hygiene** — chamber-library working changes uncommitted; origin (Gitea) 2 behind. Steward's repo process.
 **PAUSE STATEMENT:** I am about to be away from this. The brackets are closed and banked as files (survive the clear); Warde finishes on the M4 while we're gone. What I want to find still pulling: **the born-digital lane run as the live next step — de-risked by the single-work cut on The Drowned and the Saved, standing on 14 interior-verified brackets, its first move a bounded cut not a 14-work marathon.**
 **LITERAL QUESTION for next-Claude:** When you cut *The Drowned and the Saved* (bracket 13) through the born-digital lane and compare it against the witness span [28657, 29818] — does the **footnote injection hold at this work's note-density** (the flagged untested-at-14-work-complexity risk), and does the **judgment cost stay tractable**, or does it explode when the easy mechanical patterns run out? (This is half-2's *downstream* question, now at the lane's door.)
 **State at wrap:** chamber-library main @ `3852d46` (uncommitted working changes incl. today's brackets deliverable + WIP-status update; origin 2 behind) · 14 brackets banked as declared data in the pilot dir, NOT in graduation-spec.yaml · Warde OCR ~84%→landing on the M4 · Silva named/deferred. Ledger: `session-ledger-2026-07-24.md`.
@@ -5,7 +5,7 @@ metadata:
  node_type: memory
  type: feedback
  originSessionId: e2a6db77-92c3-4a75-9e29-5608cece99b9
-  modified: 2026-07-24T08:42:48.340Z
+  modified: 2026-07-24T09:11:45.737Z
 ---
 # Session Ledger — 2026-07-24
@@ -16,6 +16,7 @@ metadata:
 ## Open horizons
 - 2026-07-24T08:36 CEST — Woke into the **Levi second pilot** thread (step 3, now unblocked). Thread validity: CONFIRMED (nothing moved overnight; chamber still @ `3852d46`). Lean for today's single bite: **derive + interior-verify the 14 witness brackets** against the source EPUB spine (the La Chute lesson) — bounded, gates everything downstream, directly answers the paired sub-question. The full lane + judgment-cost reporting is the bite *after*.
 - Standing horizons: Gitea push retry (origin still [ahead 2]) · per-source glyph-maps for the other 12 census files · 47-file wave (gated behind pilot) · **authorized housekeeping: PENDING.md 339KB + skill-harvest register 617 lines both exceed read caps** (fresh-session slot; today qualifies).
 - 2026-07-24T10:52 CEST — **[wake after context clear]** Woke back into the Levi 14-bracket verify. Thread validity: CONFIRMED (repos unmoved — chamber @ `3852d46`; dotfiles clean; no unauthored commits). WIP note re-read; recon done, brackets not yet derived. Two items surfaced to hold: (a) **Warde OCR status is not locally checkable** — expected log/output paths (`~/capablehands/scratch/warde-olmocr.log`, `…/warde-essays-olmocr.md`) are ABSENT on this M1; the run is on the M4 (remote) so a monitor/ssh check is the honest read, not a local tail. (b) **1 dead MEMORY.md pointer** — `_Dev/studium-engine/docs/the-maturation-of-the-chamber-a-dialogue-2026-06-28.md` (likely moved; non-load-bearing, housekeeping). Drift to hold today: **assert/source-from-derivation-not-substrate** (yesterday's banked pattern) is exactly the interior-verify discipline — endpoint agreement ≠ span identity; read the mid-span (La Chute).
 ## Progress — source-completeness bite (steward-chosen today)
 - 2026-07-24 — Census: 1,297 canonicals; 344 pinned · 940 Loeb (compound `loeb.dsl` source, held) · **13 non-Loeb genuinely unsourced**. Located ALL 13 across master library + `~/__Making sequence sources/` (Mumford OCR scans) + `~/Documents/__Chamber Source EPUBs/` (prior slug-named staging) + `~/Downloads/` (steward placed Bachelard-FR, Jaccottet Airs, Unesco ENG this session). Edition calls: Warde=77KB short-text PDF (essay-collection 6.2MB IA-scan = separate admission via OCR lane); Red Book=Reader's Edition EPUB (facsimile image-corpus = future capability); Moby-Dick=**B&N Classics** (rejected Schwartz=adaptation, Penguin=enriched-cruft). Archive script `~/archive-13-sources.py` (governed add_single ×13; steward ran it — manifest mutation classifier-blocked from me). **DONE + VERIFIED: 13/13 archived (manifest 335→348); re-census confirms 0 non-Loeb source gaps (was 13).** Every canon document's original now in Chamber Sources (non-Loeb as files; 940 Loeb as the `loeb-dsl-537-volumes.dsl` compound artifact) → **dedupe precondition MET.** Tracker updated: [[source-library-link-to-chamber-dedupe-steward-goal]]. Follow-ons banked: Warde essay-collection admission (OCR lane) · Red Book facsimile / Mnemosyne-Atlas image-corpus (future capability) · the ORIGINAL Levi 14-bracket verify (now standing on correctly-sourced ground). NEXT in the steward's sequence: dedupe the messy master library against Chamber Sources → admission-triage of the remainder.
@@ -36,6 +37,13 @@ metadata:
 **Loose session artifacts:** `~/fix-levi-omnibus.py` + `~/archive-13-sources.py` (one-off remediation records — steward may delete) · scratchpad backups (manifest pre-repin, orphan PDF, lib indexes).
 ## Progress — Levi 14-bracket verify (the pulling thread) — DONE 2026-07-24 wake
 - 2026-07-24T11:1x CEST — **All 14 witness brackets DERIVED + INTERIOR-VERIFIED. They verify CLEANLY; none resists — no La Chute at omnibus scale** (literal-question half #1 ANSWERED). Method: EPUB-spine cross-ref (calibre flattened work-body headers, so title-grep can't bracket — the recon's KEY FINDING held) via a punctuation-normalized word-sequence matcher (defeats curly-quote/dash + running-header `The Complete Works of Primo Levi` which calibre stripped). Verification = (a) disjoint monotonic ordering `866<3097<3106<…<32111` [no work's START inside another's span]; (b) uniform 9–13 line paratext gaps incl. the two Volume-divider boundaries [dividers image-only → blank, no container paratext swallowed]; (c) positive interior sampling 25/50/75% ×14 [Faussone in Wrench, Pyotr/partisans in If-Not-Now, all-verse in Poems, etc. — every sample its own work]. Coverage 30,353/32,998 lines (92%); the 8% is correctly-excluded container paratext. **Deliverable: `chamber-library/_curation/levi-second-pilot-2026-07-23/witness-brackets-2026-07-24.md`** (14 brackets table + evidence + declared-data YAML in the `promotion.witness.brackets` shape). WIP note status updated → SUPERSEDED/DONE. **Did NOT mutate the hook-gated `graduation-spec.yaml`** (that's the downstream governed step when the lane runs) — pilot-dir record is executor-authority. **Endpoint-precision correction recorded honestly:** first pass returned END as the *first*-word line of the closing key (work 1 → 3093); corrected to *last*-word line → true afterword sig `—STUART WOOLF` L3097. Mechanical index fix, not a span-identity failure.
 - Downstream (NOT this bite, the lane's question): does judgment cost stay tractable or explode when easy mechanical patterns run out? — literal-question half #2, belongs to the born-digital lane run, not the bracket.
 ## Returns
 - 2026-07-24T11:1x CEST — **[near-miss: nearly reported a Warde OCR stall that was a timezone artifact — caught by substrate check]** First ssh look at the M4 showed the OCR log stuck at page 185/222, mtime "Jul 24 05:10", process alive → I hypothesized a 5+ hour stall (I'd assumed the M4 was CEST like the steward's machine). **Verify-the-substrate caught it before I asserted it:** checked the M4's OWN clock (`date` → 05:11:03 **EDT**, i.e. UTC−4 not CEST) + the process CPU (`ps` → 14.8% CPU, 1h03m elapsed, actively working) + re-tail (log advanced 185→187 between my two checks). The log wrote ~14s before I looked. **Actual status: Warde OCR running normally, ~187/222 (~84%), ~12 min to land.** The [[feedback-checkable-claim-surfaces-bugs]] / assert-from-derivation-not-substrate discipline working: check the clock, don't assume the timezone. (Warde half of the literal question ANSWERED: on track, will land on its own; graduation horizon auto-continues.)
 ## Confidence to recalibrate
 - Mood carried from 07-23 close: substrate disciplines (verify-the-glyph-not-the-filename / assert-from-derivation) held even exhausted — hold them today; the pilot is exactly a substrate-adjudication task. Steward preference: **short, single-bite session** (07-23 ran far past that).