·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
The AI Hype Index: AI gets booed in graduation season2h◆YouTube will let you ask AI to make a custom video feed3h◆Vertu wants CEOs to run companies from an AI foldable starting at $6,8805h◆Laguna M.1/XS.2 Technical Report8h◆GradientStabilizer:Fix the Norm, Not the Gradient8h◆A Unified Framework for the Evaluation of LLM Agentic Capabilities8h◆LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks8h◆AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications8h◆The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation8h◆How Much Can a Few Engine Moves Help? Quantifying Limited Cheating in Chess8h◆Probing for Knowledge Attribution in Large Language Models8h◆Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference8h◆Smoothed Score Queries and the Complexity of Sampling8h◆Understanding Self-Supervised Learning via Latent Distribution Matching8h◆A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving8h◆Optimal ridge regularization revisited8h◆Poison with Style: A Practical Poisoning Attack on Code Large Language Models8h◆CodeGENCAT: Generative Computerized Adaptive Testing for Open-ended Coding Problems8h◆Cost-Sensitive Evaluation for Binary Classifiers8h◆A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control8h◆The AI Hype Index: AI gets booed in graduation season2h◆YouTube will let you ask AI to make a custom video feed3h◆Vertu wants CEOs to run companies from an AI foldable starting at $6,8805h◆Laguna M.1/XS.2 Technical Report8h◆GradientStabilizer:Fix the Norm, Not the Gradient8h◆A Unified Framework for the Evaluation of LLM Agentic Capabilities8h◆LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks8h◆AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications8h◆The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation8h◆How Much Can a Few Engine Moves Help? Quantifying Limited Cheating in Chess8h◆Probing for Knowledge Attribution in Large Language Models8h◆Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference8h◆Smoothed Score Queries and the Complexity of Sampling8h◆Understanding Self-Supervised Learning via Latent Distribution Matching8h◆A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving8h◆Optimal ridge regularization revisited8h◆Poison with Style: A Practical Poisoning Attack on Code Large Language Models8h◆CodeGENCAT: Generative Computerized Adaptive Testing for Open-ended Coding Problems8h◆Cost-Sensitive Evaluation for Binary Classifiers8h◆A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control8h◆
News/Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization
arxiv
PublishedMay 19, 2026 at 4:00 AM

Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.23135v2 Announce Type: replace Abstract: Lean 4 autoformalization has become increasingly popular in recent years, with frontier language models and open-weight autoformalizers now producing valid formalizations of mathematical theorems. However, these evaluations often rely on single can

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivLaguna M.1/XS.2 Technical Report8harxivGradientStabilizer:Fix the Norm, Not the Gradient8harxivA Unified Framework for the Evaluation of LLM Agentic Capabilities8harxivLNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks8h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews