Vanderbilt Data Science Institute
Official@vanderbilt-data-science
Vanderbilt established the Data Science Institute to accelerate data-driven research, promote collaboration, and train future leaders.
Agent Skills by Vanderbilt Data Science Institute
Showing 10 vetted skills indexed across 1 GitHub repositories.
vanderbilt-data-sciencegenerating-learning-materials
Generate learning modules from a knowledge graph and student identifier.
vanderbilt-data-scienceplanning-adaptive-instruction
Generate adaptive classroom session plans from class-wide knowledge state data.
vanderbilt-data-sciencevalidating-knowledge-structure
Validate knowledge graph constraints and schema conformance with PASS/WARN/FAIL reports.
vanderbilt-data-sciencedecomposing-learning-objectives
Decomposes learning objectives into atomic, testable knowledge items using multiple taxonomies and ECD validation.
vanderbilt-data-sciencemapping-concepts-and-competences
Organize knowledge item relationships into competence-based concept maps.
vanderbilt-data-scienceupdating-knowledge-domain
Update knowledge graphs by adding, removing, merging, or splitting items and competences.
vanderbilt-data-scienceassessing-knowledge-state
Diagnose student knowledge states via BLIM, PoLIM, and MOCLIM adaptive assessments on graphs/*.json files.
vanderbilt-data-sciencebuilding-surmise-relations
Identify prerequisite relationships between knowledge items using the QUERY algorithm.
vanderbilt-data-scienceconstructing-knowledge-space
Derive feasible knowledge states, fringes, and learning paths from a surmise relation.
vanderbilt-data-scienceextracting-knowledge-items
Decompose course materials into atomic knowledge items and candidate competences.
Frequently Asked Questions About Vanderbilt Data Science Institute
FAQPage SchemaWhat specific tasks can be performed using these knowledge modeling capabilities?▼
These capabilities enable the decomposition of course materials into atomic knowledge items, the construction of surmise relations to define prerequisite structures, and the execution of adaptive assessments. Users can validate knowledge graph schemas and generate personalized instructional plans based on diagnosed student knowledge states.
Who is the target persona for these knowledge engineering methodologies?▼
The primary target personas include educational data scientists, curriculum architects, and learning engineers. These professionals utilize the provided methodologies to map complex competences, validate structural constraints within knowledge graphs, and implement data-driven instructional design for higher education environments.
What are the prerequisites for implementing these knowledge assessment models?▼
Implementation requires structured knowledge items and competence definitions formatted as JSON graphs. Users must define surmise relations to establish prerequisite dependencies and provide student identifier data to execute adaptive assessment models like BLIM, PoLIM, or MOCLIM for diagnostic reporting.