What We Learned by Reproducing 2,200 papers from ICML

Hugging Face reports on a community hackathon that reproduced 2,226 papers from ICML 2026 using coding agents, finding 51% of examined papers had at least one verified claim and 23% had at least one falsified claim.

From the source
Back in July, we ran a hackathon where more than 1,200 community members brought their own coding agents and tried to reproduce the papers published at ICML 2026, claim by claim. In 19 days, participants published 6,816 Trackio logbooks reproducing 2,226 papers, about a third of the conference
huggingface.co

Visit source ↗huggingface.co

Announced: 13 Aug 2026 00:00 UTC
Detected: 14 Aug 2026 13:13 UTC (+37h after)

Other stories

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South LanguageCapability change

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper

LG AI Research · 27 Aug

[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error Reasoning

Research paper

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update