mirror of
https://github.com/onestardao/WFGY.git
synced 2026-04-28 19:50:17 +00:00
7.5 KiB
7.5 KiB
Retrieval Drift — Guardrails and Fix Pattern
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
| Module | Description | Link |
|---|---|---|
| WFGY Core | WFGY 2.0 engine is live: full symbolic reasoning architecture and math stack | View → |
| Problem Map 1.0 | Initial 16-mode diagnostic and symbolic fix framework | View → |
| Problem Map 2.0 | RAG-focused failure tree, modular fixes, and pipelines | View → |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | View → |
| Semantic Blueprint | Layer-based symbolic reasoning & semantic modulations | View → |
| Benchmark vs GPT-5 | Stress test GPT-5 with full WFGY reasoning suite | View → |
| 🧙♂️ Starter Village 🏡 | New here? Lost in symbols? Click here and let the wizard guide you through | Start → |
👑 Early Stargazers: See the Hall of Fame — Engineers, hackers, and open source builders who supported WFGY from day one. ⭐ WFGY Engine 2.0 is already unlocked. ⭐