Search papers, labs, and topics across Lattice.
This paper introduces the Scientific Data Skill (SciDSK), a novel agent-ready representation designed to enhance the autonomous discovery, interpretation, and invocation of scientific datasets. By integrating comprehensive dataset descriptions, operational guidance, and provenance information, SciDSK addresses the limitations of existing dataset representations that are fragmented and primarily human-centric. Evaluation results demonstrate that SciDSK significantly improves agent-driven dataset discovery and interpretation, highlighting its potential to streamline scientific data utilization in AI applications.
SciDSK transforms how AI agents interact with scientific datasets, enabling more effective discovery and interpretation through a structured, reusable skill representation.
Scientific data are increasingly used by AI agents, yet existing dataset representations provide limited support for autonomous discovery, interpretation, and invocation. This limitation stems from the fragmentation of scientific data across heterogeneous repositories and from dataset representations designed primarily for human use. To address this limitation, we introduce the Scientific Data Skill (SciDSK), an agent-ready representation that packages dataset-specific knowledge and operational guidance as a reusable agent skill. A SciDSK integrates dataset descriptions, scientific context, file organization, usage procedures, quality checks, and provenance information while retaining the underlying data in its original repository. We define a structured SciDSK specification and develop a systematic construction pipeline that grounds each SciDSK in authoritative dataset records and associated supporting materials. We further establish the Scientific Data Skill Bank, a unified platform that publishes SciDSK resources across six scientific disciplines and supports package access, persistent identification, and traceability to source datasets. We evaluate SciDSK through a retrieval benchmark for dataset discovery and controlled cases for dataset interpretation. The results show that SciDSK improves agent-driven dataset discovery and provides more precise and actionable support for dataset interpretation. These findings support the value of organizing dataset-specific knowledge in an agent-ready representation.
