CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
CausalDS is a benchmark for evaluating causal reasoning in data-science workflows that combines synthetic causal structures with realistic observational data and natural-language s…
Hugging Face · Daily Papers
·Andrej Leban, Yuekai Sun
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Andrej Leban, Yuekai Sun
- 3 upvotes da comunidade
- Temas: structural causal model, observational data, natural-language story, Pearl's rungs, causal reasoning, data-science workflows
Resumo
Resumo original (em inglês), extraído do paper:
CausalDS is a benchmark for evaluating causal reasoning in data-science workflows that combines synthetic causal structures with realistic observational data and natural-language stories across Pearl's three rungs of causal inference.
