10 KiB
name, description, metadata
| name | description | metadata | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 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 | 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. |
|
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 governedarchive_sources.resolve_archived_source→ Chamber Sources EPUB sha1be71a50…, 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 Leviwhich 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:
- Disjoint monotonic ordering
866<3097<3106<…<32111— no work's START inside another's span. - 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/IIIstrings appear only in the global front CONTENTS, L45/86/123.) - 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.).
- Disjoint monotonic ordering
- 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 WOOLFL3097; 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-textwarde-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.