The Semantic Precision for AI Retrieval of Knowledge (SPARK) PubMed/PMC Challenge
The SPARK PubMed/PMC Challenge from NIH Challenges seeks AI systems that generate citation-backed, synthesized answers to complex biomedical queries using PubMed and PMC data.
Funder: NIH Challenges
Due Dates: January 31, 2027: Submissions Close
Funding Amounts: $250,000 total prize pool; up to $100,000 for first place per track, $25,000 for second place per track
Summary: Challenge for AI-driven systems that deliver citation-backed, synthesized answers to complex biomedical queries using PubMed and PMC literature.
Key Information: U.S. citizenship/permanent residency or U.S.-based entity required for prize eligibility; non-U.S. collaborators may participate but cannot receive prize money.
Description
The Semantic Precision for AI Retrieval of Knowledge (SPARK) PubMed/PMC Challenge seeks innovative AI-powered solutions to transform how biomedical researchers interact with the vast and complex literature indexed in PubMed and PubMed Central (PMC). The challenge, led by NIH Challenges and the National Library of Medicine, aims to move beyond traditional keyword search by inviting the development of systems that can return citation-backed, context-aware answers and actionable follow-up suggestions to complex biomedical questions. Solutions must generate responses strictly grounded in PubMed/PMC citations, synthesize information into coherent and accurate outputs, and propose relevant next steps for researchers. The initiative is designed to reduce the cognitive and time burden of literature exploration, accelerating scientific discovery and cross-disciplinary insight.
