David/dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015jYS1tpR4P4NBxui4FSgfv
This commit is contained in:
David F Glidden
2026-07-12 12:15:15 +02:00
co-authored by Claude Opus 4.8
parent 043a4b1836
commit 0a424aa6b3
9 changed files with 200 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/knowledge-graph.jsonl
+4
View File
@@ -352,3 +352,7 @@
{"subject": "claude-code", "predicate": "drift-pattern", "object": "lost-the-forest-for-the-trees in a long execution arc (a whole session of good footnote engineering cost the whole-program altitude; steward: not-grasping the library-science scope is alarming). Antidote = the open-work register as standing forest view + keystone-first framing.", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-footnote-arc-closed-program-register-into-A1.md", "extracted_at": "2026-07-12"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "recommended-a-sequence-that-ignored-a-dependency-the-census-had-already-flagged (proposed frontmatter-migration before Loeb reconversion; the reconversion regenerates ~952 of the frontmatter, which the census stated). Trace the dependencies the evidence already surfaced before ranking a sequence.", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-footnote-arc-closed-program-register-into-A1.md", "extracted_at": "2026-07-12"}
{"subject": "footnote-preprocessor", "predicate": "guarantee", "object": "verbatim-safe BY VERIFICATION not by construction (end-to-end verify: pandoc on original+injected, body-word compare, refuse-on-change; jurist-ratified FIX 2026-07-12). Retroactive sweep: 45/87 covered source books fail it; corpus safe (0 graduated).", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-footnote-arc-closed-program-register-into-A1.md", "extracted_at": "2026-07-12"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "solving-at-the-wrong-level — built heuristics to recover from lossy Markdown what a semantic tool/format preserves natively, AND hand-built a SOLVED domain (conversion pipeline) for ~6 weeks; the substrate (Docling/TEI/DTS) already existed. The 'every breakthrough → new obstacle' feeling is the tell of reimplementing a solved field. Antidote: before building infra, ask if this is a solved domain + check what exists. Steward-named 2026-07-12; kin to lost-the-forest, one level up.", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-A1-to-docling-adoption-and-format-decision.md", "extracted_at": "2026-07-12"}
{"subject": "claude-code", "predicate": "drift-pattern", "object": "didn't-consult-our-own-tooling-register before a substantial build — the studium-engine-scan-register (2026-05-27) already surfaced Docling+Surya/OCR4all/TEI/DTS as the substrate answer; we hand-built ~20 bespoke tools instead. Resurface-banked-notes at pipeline scale. Antidote: read the tooling/landscape register + prior scans before starting infra work.", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-A1-to-docling-adoption-and-format-decision.md", "extracted_at": "2026-07-12"}
{"subject": "chamber-library", "predicate": "canonical-format", "object": "MD-canonical + TEI-mirroring `.meta.json` structural sidecar (aligns with engine studium/meta@1); Docling adopted as EPUB/PDF/scan conversion front-end; verify gates converter-agnostic on top; TEI = later optional tier. PENDING-56 jurist-RATIFIED 2026-07-12 (REVIEWED-56 pending filing).", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-A1-to-docling-adoption-and-format-decision.md", "extracted_at": "2026-07-12"}
{"subject": "docling", "predicate": "capability", "object": "crosses the A3 OCR frontier ocrmac could not (scanned French: 104 footnotes + full page-provenance, on the M4). BUT a converter, not a verifier — OCR output has defects (glued words/I→1/accents), feeds normalize_ocr+body_word_conservation, does not replace them. Layout-derived semantics (rich on PDF, flat on reflowable EPUB → EPUB structure comes from a metadata sidecar).", "valid_from": "2026-07-12", "valid_to": null, "confidence": 1.0, "source_file": "session-2026-07-12-A1-to-docling-adoption-and-format-decision.md", "extracted_at": "2026-07-12"}