Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
Building a correct-by-design lakehouse: Data contracts, versioning, and transactional pipelines for humans and agents
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
GitLake lifts Iceberg snapshots into lakehouse-wide commits, branches, and merges so agents develop in isolation and multi-table pipelines publish atomically via temporary-branch merges.
Proposes an AI-augmented hub-and-spoke architecture on lakehouses with staged ownership transfer and LLM-driven governance automation to improve on pure data mesh implementations.
citing papers explorer
-
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
-
GitLake: Git-for-data for the agentic lakehouse
GitLake lifts Iceberg snapshots into lakehouse-wide commits, branches, and merges so agents develop in isolation and multi-table pipelines publish atomically via temporary-branch merges.
-
Beyond the Data Mesh Illusion: Designing Modern AI-augmented Lakehouses to Bridge the Gap Between Theory and Practice
Proposes an AI-augmented hub-and-spoke architecture on lakehouses with staged ownership transfer and LLM-driven governance automation to improve on pure data mesh implementations.