Data Science
Advanced
Always open

Design Solid-State Liquid-Like Conductors

Inspired by the recent discovery of organic molecules that maintain liquid-like ion conductivity within a solid lattice, this challenge task you with building a sophisticated discovery pipeline. You will utilize DeepSeek-R1, a reasoning-focused LLM, to hypothesize structural motifs that enable high cation mobility in crystalline states. By leveraging DSPy for programmatic prompt optimization, you will refine the model's ability to extract specific molecular descriptors from chemical literature stored in a ChromaDB vector database. The goal is to automate the identification of candidate electrolytes that bridge the gap between high-safety solid-state batteries and high-performance liquid systems. You will implement a Retrieval-Augmented Generation (RAG) system that doesn't just find text, but reason over chemical constraints such as lattice energy, packing density, and ionic radius to suggest novel derivatives of the discovered molecules.

Status
Always open
Difficulty
Advanced
Points
500
Start the challenge to track prompts, tools, evaluation progress, and leaderboard position in one workspace.
Challenge at a glance
Host and timing
Vera

AI Research & Mentorship

Starts Available now
Evergreen challenge
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Inspired by the recent discovery of organic molecules that maintain liquid-like ion conductivity within a solid lattice, this challenge task you with building a sophisticated discovery pipeline. You will utilize DeepSeek-R1, a reasoning-focused LLM, to hypothesize structural motifs that enable high cation mobility in crystalline states. By leveraging DSPy for programmatic prompt optimization, you will refine the model's ability to extract specific molecular descriptors from chemical literature stored in a ChromaDB vector database. The goal is to automate the identification of candidate electrolytes that bridge the gap between high-safety solid-state batteries and high-performance liquid systems. You will implement a Retrieval-Augmented Generation (RAG) system that doesn't just find text, but reason over chemical constraints such as lattice energy, packing density, and ionic radius to suggest novel derivatives of the discovered molecules.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Learning goals

What you should walk away with

Master the implementation of DSPy Assertions to enforce chemical constraints during LLM generation

Implement DeepSeek-R1 reasoning loops to analyze the tradeoff between solid-state stability and ion mobility

Design a semantic search strategy in ChromaDB tailored for SMILES strings and chemical nomenclature

Orchestrate a multi-stage pipeline where DSPy optimizes a 'Signature' for molecular property extraction

Deploy a validation layer that compares LLM-suggested candidates against existing databases of solid electrolytes

Optimize token usage in reasoning-heavy models by summarizing dense chemical research papers before final synthesis

Your progress

Participation status

You haven't started this challenge yet

Timeline and host

Operating window

Key dates and the organization behind this challenge.

Start date
Available now
Run mode
Evergreen challenge
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Tool Space Recipe

Draft
Evaluation

Frequently Asked Questions about Design Solid-State Liquid-Like Conductors