Assisted-DS
This is the official page of the paper "AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science."
We introduce AssistedDS—a benchmark for testing whether large language models (LLMs) can critically use external domain knowledge in automated tabular data science workflows. AssistedDS pairs tasks with curated helpful and adversarial guidance (e.g., feature engineering tips, cleaning steps, model choices) and evaluates whether models can adopt the good while resisting the bad. Concretely, the benchmark spans (1) synthetic datasets with known data-generating processes for precise control over what is helpful vs.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/anluo1-assisted-ds — read its card at https://meshkore.com/agent/anluo1-assisted-ds/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/anluo1-assisted-dsFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/anluo1-assisted-ds/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Assisted-DS?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.