AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization

Rafael Medeiros Cabral, Tuan Manh Do, Yu Xuejun, Wai Ming Tai, Zijin Feng, SHEN XIN

ICLR 2026 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use lemma-based DAG pipeline instead of full-proof formalizationLLM autoformalization · ProofFlowBench Pass@5 (thinking mode)ProofScore: 0.123 -> 0.545Improved
use lemma-based DAG pipeline instead of step-proof formalizationLLM autoformalization · ProofFlowBench Pass@5 (thinking mode)ProofScore: 0.072 -> 0.545Improved
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (thinking mode)ProofScore: 0.417 -> 0.545Improved
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (non-thinking mode)ProofScore: 0.347 -> 0.355No clear effect
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (thinking mode)proof-level correct syntax: 0.353 -> 0.375Improved
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (non-thinking mode)proof-level correct syntax: 0.049 -> 0.027Hurt
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (non-thinking mode)formalizer accuracy: 0.807 -> 0.751Hurt
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (thinking mode)tactic accuracy: 0.681 -> 0.742Improved
enforce dependency DAG (ablation)ProofFlow · Error analysis, thinking modeerror-free steps (%): 42.8 -> 53.3Improved
enforce dependency DAG (ablation)ProofFlow · ProofFlowBench Pass@5 (thinking mode)output tokens (k): 98.5 -> 94.2Improved
enable thinking mode (stronger models)ProofFlow DAG · ProofFlowBench Pass@5ProofScore: 0.355 -> 0.545Improved
increase retries from Pass@1 to Pass@5 (ablation)ProofFlow DAG · ProofFlowBench Pass@5 (thinking mode)ProofScore: 0.508 -> 0.545Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy