Extreme Event AI

I want to evaluate and, if it fits, integrate a technique from recent AI research into my project.

## Technique: Extreme Event AI
Extreme Event AI: Reliability Calibration for RAG on Edge-Case Queries

The paper finds that AI weather models (Aurora, GenCast, Pangu, GraphCast) that achieve strong *average* performance are systematically less reliable on extreme precipitation events — the tail of the distribution where calibration and overconfidence matter most. RAG analogy: Retrieval strategies that look good on average benchmarks can be poorly calibrated on extreme queries — rare vocabulary, very long/short inputs, out-of-distribution phrasing. This tab quantifies that gap using Expected Calibration Error (ECE) and reliability diagrams split by normal vs. extreme query sets. Normal queries = common vocabulary, average length Extreme queries = rare terms (high IDF), OOV tokens, length outliers

## Reference implementation (Vector Ridge Labs, POC-011)
- Live demo: https://osoman2-gradio-pocs.hf.space/?poc=POC-011
- Source code: https://huggingface.co/spaces/osoman2/Gradio_pocs/tree/main/extreme_event_ai

## My project
<Describe your stack, the problem you want to solve and where this technique would sit. Example: "Python FastAPI RAG service over 50k PDFs, Postgres + pgvector, OpenAI embeddings, p95 latency budget 800 ms.">

## What I need from you
1. Read the reference source code and explain in at most 5 bullets how the technique works and what it would change compared to my current approach.
2. Decide whether it fits my case. If it does not, say why and stop there.
3. Propose the smallest viable integration: files or modules to touch, new dependencies, configuration.
4. Implement it behind a flag or as a separate function so it can be compared side by side with what I have today.
5. Add an evaluation script that measures agreement of the new metric with human judgement on a sample of my outputs, before and after, on my own data.
6. List the risks (latency, cost, failure modes) and what to monitor once it is in production.

Constraints: keep my existing stack and conventions, avoid heavy dependencies unless the gain is clear, and reference the file in the demo source whenever you reuse its logic.