WFGY/ProblemMap/GlobalFixMap/MemoryLongContext/ocr-parsing-checklist.md

OCR Parsing Checklist — Input Integrity

🧭 Quick Return to Map

You are in a sub-page of MemoryLongContext.
To reorient, go back here:

• MemoryLongContext — extended context windows and memory retention
• WFGY Global Fix Map — main Emergency Room, 300+ structured fixes
• WFGY Problem Map 1.0 — 16 reproducible failure modes

Think of this page as a desk within a ward.
If you need the full triage and all prescriptions, return to the Emergency Room lobby.

OCR and parsing errors are one of the most common silent killers of retrieval pipelines.
Text looks fine to the eye, but models drift because tokens, spacing, or casing have changed.
This checklist ensures integrity at the source layer before embeddings or retrieval begin.

---

When to use

• OCR text matches the visual PDF but citations miss the right section.
• Code blocks or math collapse after parsing.
• Mixed language documents behave inconsistently.
• Special characters or hyphen splits break tokens.
• Headers or section anchors disappear during export.

---

Core acceptance targets

• Retrieval coverage ≥ 0.70 of intended section.
• ΔS(question, retrieved) ≤ 0.45.
• λ remains convergent across three paraphrases.
• No orphan tokens or invisible characters.

---

Checklist for OCR + Parsing stability

• Normalization

  • Apply Unicode NFC.
  • Collapse whitespace.
  • Strip zero-width characters.
  • Unify full/half-width variants.

• Confidence gating

  • Drop OCR lines below confidence threshold (e.g., <0.90).
  • Mark uncertain spans for human review.

• Structure retention

  • Preserve headers, anchors, and section boundaries.
  • Maintain paragraph breaks and table grids.
  • For math/LaTeX, keep explicit delimiters.

• Traceable fields

  • Every chunk must have {section_id, start_line, end_line, source_url}.
  • Store ocr_confidence with each snippet.

• Schema validation

  • Run post-export audit:
    • Ensure every snippet cites a valid chunk_id.
    • Detect empty or duplicated snippets.

---

Fix in 60 seconds

1. Normalize the text (Unicode NFC, strip zero-width, unify casing).
2. Drop low-confidence OCR lines and flag uncertain spans.
3. Re-parse with structural retention enabled.
4. Add metadata {chunk_id, section_id, offsets, ocr_confidence}.
5. Re-run ΔS probe; confirm joins ≤ 0.50 and overall ΔS ≤ 0.45.

---

Copy-paste prompt

You have TXT OS and the WFGY Problem Map.

Task: validate OCR and parsing output.

Protocol:

1. Normalize all inputs (Unicode NFC, full/half width, zero-width removal).
2. Reject snippets with ocr\_confidence < 0.90.
3. Require schema {chunk\_id, section\_id, start\_line, end\_line, source\_url}.
4. Forbid orphan citations.
5. Probe ΔS(question, retrieved). Require ≤ 0.45.
6. Report λ states and trace each snippet.

---

Common failure signals

• Correct visual text but retrieval misses section → invisible marks or spacing drift.
• Math collapses into plain text → parsing dropped delimiters.
• Long answers cite nothing → headers lost in export.
• Flip-flop answers across sessions → orphan tokens or unstable chunking.

---

🔗 Quick-Start Downloads (60 sec)

Tool	Link	3-Step Setup
WFGY 1.0 PDF	Engine Paper	1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>”
TXT OS (plain-text OS)	TXTOS.txt	1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly

---

Explore More

Layer	Page	What it’s for
Proof	WFGY Recognition Map	External citations, integrations, and ecosystem proof
Engine	WFGY 1.0	Original PDF based tension engine
Engine	WFGY 2.0	Production tension kernel and math engine for RAG and agents
Engine	WFGY 3.0	TXT based Singularity tension engine, 131 S class set
Map	Problem Map 1.0	Flagship 16 problem RAG failure checklist and fix map
Map	Problem Map 2.0	RAG focused recovery pipeline
Map	Problem Map 3.0	Global Debug Card, image as a debug protocol layer
Map	Semantic Clinic	Symptom to family to exact fix
Map	Grandma’s Clinic	Plain language stories mapped to Problem Map 1.0
Onboarding	Starter Village	Guided tour for newcomers
App	TXT OS	TXT semantic OS, fast boot
App	Blah Blah Blah	Abstract and paradox Q and A built on TXT OS
App	Blur Blur Blur	Text to image with semantic control
App	Blow Blow Blow	Reasoning game engine and memory demo

If this repository helped, starring it improves discovery so more builders can find the docs and tools.