Cross-provider planted-twin safety-regression evaluation for LLMs. Paired CLEAN/PLANTED twin suites, receipt-replay CI, Anthropic + OpenAI + Groq. Apache-2.0.
-
Updated
Aug 13, 2026 - Python
Cross-provider planted-twin safety-regression evaluation for LLMs. Paired CLEAN/PLANTED twin suites, receipt-replay CI, Anthropic + OpenAI + Groq. Apache-2.0.
CI-native planted-twin regression harness for the x402 agentic-payments settlement threat model. Reference facilitator deployed and exercised on Base mainnet + Sepolia; receipts in docs/basescan/. Apache-2.0.
To associate your repository with the planted-twin topic, visit your repo's landing page and select "manage topics."