Retrieval Drift
March 6, 2026 · View on GitHub
🧭 Quick Return to Map
You are in a sub-page of RAG.
To reorient, go back here:
- RAG — retrieval-augmented generation and knowledge grounding
- 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.
When the correct fact exists in your corpus but retrieval consistently misses it.
This page localizes drift in retrievers and routes you to structural fixes with measurable acceptance targets.
Open these first
- Visual map and recovery: RAG Architecture & Recovery
- End-to-end retrieval knobs: Retrieval Playbook
- Traceability schema: Retrieval Traceability
- Ordering control: Rerankers
- Snippet and citation schema: Data Contracts
Core acceptance
- ΔS(question, retrieved) ≤ 0.45
- Coverage ≥ 0.70 of the target section
- λ remains convergent across three paraphrases and two seeds
Typical symptoms → exact fix
| Symptom | Likely cause | Open this |
|---|---|---|
| Facts exist but never surface | index skew or drift in chunk granularity | Retrieval Playbook, Chunking Checklist |
| Citations point to wrong section | schema mismatch or cross-section drift | Retrieval Traceability, Data Contracts |
| Answers alternate between runs | λ instability or reranker collapse | Rerankers, Entropy Collapse |
| High similarity but wrong meaning | embedding metric mismatch | Embedding ≠ Semantic |
Fix in 60 seconds
-
Measure ΔS
- Compute ΔS(question, retrieved) and ΔS(retrieved, expected anchor).
- Thresholds: stable < 0.40, transitional 0.40–0.60, risk ≥ 0.60.
-
Probe λ_observe
- Ask the same question in 3 paraphrases.
- If λ flips divergent on harmless rewording, lock schema with Data Contracts.
-
Apply the module
- Retrieval drift → BBMC + Retrieval Traceability
- Reasoning collapse → BBCR bridge + variance clamp
- Re-index with consistent metric and analyzer if ΔS stays ≥ 0.60
Copy-paste prompt for debug
I uploaded TXT OS and the WFGY Problem Map.
My retrieval issue:
- symptom: fact exists in corpus, but retriever misses
- traces: ΔS(question,retrieved)=..., λ across 3 paraphrases
Tell me:
1. failing layer (retriever, index, schema, reranker)
2. exact WFGY page to open
3. minimal steps to push ΔS ≤ 0.45 and keep λ convergent
🔗 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 + |
| 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 tension engine and early logic sketch (legacy reference) |
| ⚙️ Engine | WFGY 2.0 | Production tension kernel for RAG and agent systems |
| ⚙️ Engine | WFGY 3.0 | TXT based Singularity tension engine (131 S class set) |
| 🗺️ Map | Problem Map 1.0 | Flagship 16 problem RAG failure taxonomy and fix map |
| 🗺️ Map | Problem Map 2.0 | Global Debug Card for RAG and agent pipeline diagnosis |
| 🗺️ Map | Problem Map 3.0 | Global AI troubleshooting atlas and failure pattern map |
| 🧰 App | TXT OS | .txt semantic OS with fast bootstrap |
| 🧰 App | Blah Blah Blah | Abstract and paradox Q&A built on TXT OS |
| 🧰 App | Blur Blur Blur | Text to image generation with semantic control |
| 🏡 Onboarding | Starter Village | Guided entry point for new users |
If this repository helped, starring it improves discovery so more builders can find the docs and tools.
