Unverified50% confidenceReleaseExact time
The LeanZero team packaged all row data, per-round build scores, inference costs, and replay links from its agentic coding benchmark into a public dataset released on Hugging Face, and built a leaderboard Space.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedThe authors have publicly released the code, experimental data, and 105 checkpoints covering 36 shapes with training configurations, with models hosted on Hugging Face.68% similarUnverifiedHugging Face has introduced a model security scanning mechanism on the Hub that automatically detects pickle code execution risks in uploaded models and marks them with warnings.65% similarUnverifiedIn Hugging Face filtering tasks, the more explicit the prompt and rules, the more reliable the results, and it is recommended to verify results using the official API.64% similarUnverifiedLeanCopilot is a tool that auto-completes proof steps in Lean/Coq environments.62% similarUnverifiedWhen obtaining models from platforms such as HuggingFace, their provenance, integrity, and potential risks should be thoroughly assessed.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059577API
curl https://kongchang.com/api/v1/knowledge/claims/1059577MCP
get_claim(id=1059577)