session 2026-07-12: PENDING-56 (canonical-format decision, jurist-ratified) + in-flight sidecar build report + session memory/ledger/REVIEWED-drafts

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015jYS1tpR4P4NBxui4FSgfv

claude/memory/MEMORY.md

@@ -55,7 +55,7 @@ permalink: claude-memory/memory
 - [Be (laundromat)](project-be-laundromat.md) — canonical workstream tracker established 2026-06-08 (Seb-relay of locked decisions). Be = Skemantix startup (Seb+David) funding CapableMind's funding-ladder; **bridge, not venture**. Decisions LOCKED: entity/exit (CapableMind decoupled, grant-funded), pricing (Living $12.99/mo · Archive $69.99/yr · Memorial $49.99/yr · Renovate ~$199 · $8.99 floor), CF Self-Serve Agency + versioned-template-package infra. **a11y gate MERGED (Pat 100/100/100).** Pre-revenue: the WTP gate = renovate Pat → charge her. **Discipline: stop adding spec until the gate clears → nothing for executor on be until then.** Repo @ `f43a0fd`.
 
 ## Active Session
-- [Session 2026-07-11→12 — footnote arc closed → program open-work register → into A1](session-2026-07-12-footnote-arc-closed-program-register-into-A1.md) — Closed the EPUB footnote recognizer + built the **END-TO-END VERIFY** (guarantee now *by verification, not by construction*; jurist-ratified FIX): after injecting, pandoc runs on original+injected, body-words compared, ANY non-marker change refuses+deletes. Executed the whole jurist ruling (**Q1a** ratify · **Q1b** mandatory+retroactive · **Q1c** POSITIONAL marker-exclusion, `e8eeea7` · **Q2** nested-block RETRACTED — pairs-but-converts-dirty, honest-refuse). Built (b) inner-anchor (916 notes +0/−0); **nagarjuna/nested-block/i-ching honest-refused** (PASS-BUT-FALSELY caught by the verify). **Q1b RETROACTIVE SWEEP:** 87 covered source EPUBs · 42 CLEAN · **45 DIRTY** (29 catastrophic false-pairing, 16 marker-adjacency) — **corpus SAFE (0 graduated)**; recognizer's reliable coverage ≈42/87. **THE BIG PIVOT:** steward named I'd lost the forest for the trees → built the canonical **Chamber→Gold→Engine OPEN-WORK REGISTER** (`chamber-library/docs/chamber-program-open-work.md`) from a 3-agent evidence census. Findings: **engine is fenced-to-verified-subset → NOT blocked on reprocess (parallel, ruled);** 1,284 canonical (mostly frontmatter-debt not corruption); keystone = enforce `body_word_conservation`. Steward corrected: **reconversion precedes frontmatter** (Loeb Region 4 subsumes ~952 of it). All chamber work pushed (`abada64`). **⚠ PULLING THREAD: A1 — the general `body_word_conservation` verbatim gate. START WITH THE ACCEPTANCE CRITERION** (distinguish legit front/ToC/index drops from real loss; consider comparing candidate vs a REFERENCE pandoc conversion, not the raw source) → build in `verify_graduation.py` → prove → surface as PROPOSAL. Small closeable: wire mandatory-at-graduation; register hygiene. **Steward owes:** place REVIEWED-55; the recognizer-maturity decision. Read `docs/chamber-program-open-work.md` (the standing forest view) at wake.
+- [Session 2026-07-12 — A1 → Docling adoption + canonical-format decision (PENDING-56) → in-flight sidecar build](session-2026-07-12-A1-to-docling-adoption-and-format-decision.md) — Woke into A1 (`body_word_conservation` gate); built `verify_body_conservation.py` (shingle-coverage; difflib→shingle pivot on scale). **Steward challenged the framing TWICE** → THE PIVOT: the conversion/format/citation SUBSTRATE is a **solved, adoptable domain** (Docling/GROBID/TEI/DTS) and we'd spent ~6 weeks rebuilding it — **the answer was already in our own tooling-register (2026-05-27)**. Ran a 4-tier **Docling trial** (M4+M1): cleans EPUB (0 cruft), rich structure+provenance on PDF, **CROSSES the A3 OCR frontier** on scanned French (104 footnotes) — but is a *converter, not a verifier* (feeds our gates). **Steward DECIDED (AskUserQuestion) + jurist RATIFIED PENDING-56: Option A** = MD-canonical + **TEI-mirroring `.meta.json` structural sidecar**; **adopt Docling** as front-end. Jurist closed 2 schema-gating Qs: **recognizer REPOSITIONED (not retired)** as the sidecar note-layer; **CARDINAL PRINCIPLE: preserve source typing, never flatten** (→ TEI-migration mechanical). Aligns with engine's already-ruled **D-2** (MD+sidecar). **In-flight autonomous build (8 tasks):** sidecar **schema DRAFT** + `build_sidecar.py` v0 (proven montaigne/jacobs; honest join-limit → real fix = **Docling-per-spine-file**); updated runbook (M4/M1 split) + both CLAUDE.mds; report `in-flight-report-2026-07-12.md`. **⚠ PULLING THREAD: lock the DRAFT schema (Q-A) + confirm the Docling-per-spine-file architecture (Q-B) → build the WIRED extractor.** Schema is curator-locked (steward+jurist), NOT executor-locked. **Steward owes:** file **REVIEWED-55 + REVIEWED-56** (`REVIEWED-drafts-for-filing-2026-07-12.md`). All chamber/studium/CM-AI work UNCOMMITTED (no-push guardrail). Read `in-flight-report-2026-07-12.md` + `docs/chamber-program-open-work.md` 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).