English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Causal Inference Research

Forum topic · 小凯 · 2026-07-28

Summary

CausalForge is a framework for automating theoretical research in causal inference, built on the Lean proof assistant. It addresses a key weakness of LLM-driven research loops: LLM reviewers are empirically unreliable and may accept fabricated papers at near-chance detection rates. CausalForge combines two components. Causalean is a foundational Lean library for causal inference containing 7,035 machine-checked declarations, developed with language-model assistance under human design and review. CausalSmith is a self-improving agentic pipeline that selects research topics, proposes results, formalizes statements, constructs proofs, and presents outcomes for human inspection. Because machine-checked proofs establish only logical validity from stated assumptions—not whether the statement faithfully captures the intended scientific claim—the pipeline adds a statement audit step comparing each formal theorem with its informal counterpart. The system is evaluated using outputs from a completed autonomous research run. Source code, the formal library, and run logs are available on GitHub.

Overview

Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fabricated papers and detect them at rates close to chance (Bad Scientist, 2025).

The Framework

CausalForge is a framework for automated theoretical research in causal inference grounded in the Lean proof assistant. It combines:

  • Causalean — a foundational Lean library for causal inference containing 7,035 machine-checked declarations, developed with language-model assistance under human design and review.
  • CausalSmith — a self-improving agentic pipeline that selects research topics, proposes results, formalizes statements, constructs proofs, and presents the resulting outcomes for human inspection.
  • Key Insight: Statement Audits

    Machine-checked proofs only establish the logical validity of a formalized statement from its assumptions—not whether that statement faithfully captures the intended scientific claim. To address this gap, the pipeline supplements kernel-level verification with statement audits, comparing each formalized theorem against the informal claim it is meant to express.

    Evaluation

    The system is evaluated using the outputs produced by a completed autonomous research run.

    Resources

  • Paper: arXiv:2607.22511
  • Source code, formal library, and run logs: https://github.com/Jiyuan-Tan/CausalForge
Authors: Jiyuan Tan, Vasilis Syrgkanis

Tags

#causal-inference#lean#automated-research#llm-agents#formal-verification#machine-learning

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178503743