Expired50% confidenceFactExact time
NeuralPGN stores all game data, training records, and memory states on the local device, requiring no cloud upload and supporting offline use
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/15/2026
First Seen
Valid until: 10/13/2026(expired)
Sources
Related Claims
UnverifiedNeuralPGN is a local-first, open-source chess opening trainer that uses the FSRS spaced repetition algorithm and is built on the Tauri framework75% similarUnverifiedOff-policy algorithms (such as SAC and DQN) can be trained on data collected by any policy, are capable of maintaining a replay buffer of millions of experiences for repeated learning, and have higher sample efficiency than on-policy methods.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/523967API
curl https://kongchang.com/api/v1/knowledge/claims/523967MCP
get_claim(id=523967)