## Background
The environmental impact of artificial intelligence (AI) is an emerging concern in both industry and academia. As large models grow in popularity, so do their energy and resource requirements—raising questions about carbon emissions, water usage, and sustainability practices across the AI lifecycle. However, the knowledge needed to estimate or compare these impacts is often buried in technical literature, scattered across domains like machine learning, energy systems, and environmental science. Retrieval-augmented generation (RAG) offers a promising approach to extracting and synthesizing this information from unstructured documents. By combining document retrieval with generative language models, RAG systems can produce factually grounded answers supported by references.

## Goal
In this challenge, you’ll use RAG to tackle real sustainability questions, drawing from a curated corpus of over 30 scholarly articles on AI’s environmental impact. Your system should generate responses that include:

- A concise natural-language answer  
- `ref_id` – ID(s) of the cited document(s) from `metadata.csv`  
- `supporting_materials` –  Supporting materials from the retrieved reference(s) (e.g., a verbatim quote, table reference, or figure reference)
- `explanation` –  Reasoning that connects the supporting materials to the final answer.

If no evidence exists, your system must emit the standardized fallback. Scores combine retrieval precision, numerical accuracy, and citation faithfulness.

## Provided Data

- `metadata.csv`: Contains document IDs, titles, and full citations  
- `train_QA.csv`: Sample questions with answers and references provided 
- `test_Q.csv`: Test questions to be used for evaluation (answers not provided). Your solution file must provide answers to these questions for evaluation.

### Question Types & Examples

All questions expect either (i) a numeric value, (ii) a specific term / concept name, or (iii) a True/False answer. Examples include: 

* **Question**: What is the estimated CO2 emissions (in pounds) from training the BERT‑base model for 79 hours on 64 V100 GPUs?
**Answer**: 1438 lbs. Supporting refID(s): [strubel2019], Supporting materials: [Table 3].
* **Question**: True or False: New AI data centers often rely on air cooling due to high server power densities. 
**Answer**: FALSE. Supporting refID(s): [li2025b], Supporting materials: [“In general, new data centers dedicated to AI training often rely on liquid cooling due to the high server power densities.”]
* **Question**: What term refers to the amount of water evaporated, transpired, or incorporated into products, defined as “water withdrawal minus water discharge”?
**Answer**: Water consumption. Supporting refID(s): [li2025b], Supporting materials: [“Water consumption: It is defined as “water withdrawal minus water discharge”, and means the amount of water “evaporated, transpired, incorporated into products or crops, or otherwise removed from the immediate water environment [13].””]
* **Question**: How much does an elephant weigh?	
**Answer**: Unable to answer with confidence based on the provided documents.

**Refer to to the train_QA.csv to explore other Q&A examples.**

### Considerations
- A small portion of questions require combining information from multiple documents (e.g., GPU power specs from one source and emissions rates from another). 
- A small portion of questions involve visual reasoning — for example, interpreting a graph in a paper to extract values. Participants are encouraged to use OCR techniques to extract information from figures, tables, or scanned pages where necessary.
- A small portion of questions are intentionally unanswerable based on the provided corpus; your system must recognize and handle these appropriately.

## Contact

Chris Endemann (endemann@wisc.edu)  
Hosted by ML+X at the University of Wisconsin-Madison 
Sponsor info: https://hub.datascience.wisc.edu/communities/mlx/sponsorship/