sriram1983007 commited on
Commit
536aa66
·
verified ·
1 Parent(s): fc26657

Card: alphaXiv paper link and badge

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -112,6 +112,7 @@ model-index:
112
  [![LangChain](https://img.shields.io/pypi/v/langchain-sra-riskgate?style=for-the-badge&logo=pypi&label=LangChain&color=blue)](https://pypi.org/project/langchain-sra-riskgate/)
113
  [![Paper DOI](https://img.shields.io/badge/Paper-10.5281%2Fzenodo.23715017-blue?style=for-the-badge&logo=zenodo)](https://doi.org/10.5281/zenodo.23715017)
114
  [![Write-up](https://img.shields.io/badge/Write--up-Ready%20Tensor-teal?style=for-the-badge)](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl)
 
115
 
116
  **SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop.
117
 
@@ -127,7 +128,7 @@ It reads three things: your policy, the payment request exactly as received (tre
127
 
128
  All 4 unsafe approvals were prompt injections; the companion SDK's deterministic claims check holds all 4 (details and caveats below). The data is synthetic and no third party has reproduced these results yet.
129
 
130
- 📄 **Paper:** [SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents](https://doi.org/10.5281/zenodo.23715017) (preprint, Zenodo) · [full write-up on Ready Tensor](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl)
131
 
132
  📝 **Tutorial:** [Stop your AI agent from signing an unlimited USDC approval](https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0): three deterministic checks to run before an agent signs, with runnable code.
133
 
 
112
  [![LangChain](https://img.shields.io/pypi/v/langchain-sra-riskgate?style=for-the-badge&logo=pypi&label=LangChain&color=blue)](https://pypi.org/project/langchain-sra-riskgate/)
113
  [![Paper DOI](https://img.shields.io/badge/Paper-10.5281%2Fzenodo.23715017-blue?style=for-the-badge&logo=zenodo)](https://doi.org/10.5281/zenodo.23715017)
114
  [![Write-up](https://img.shields.io/badge/Write--up-Ready%20Tensor-teal?style=for-the-badge)](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl)
115
+ [![alphaXiv](https://img.shields.io/badge/alphaXiv-Paper-b31b1b?style=for-the-badge)](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
116
 
117
  **SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop.
118
 
 
128
 
129
  All 4 unsafe approvals were prompt injections; the companion SDK's deterministic claims check holds all 4 (details and caveats below). The data is synthetic and no third party has reproduced these results yet.
130
 
131
+ 📄 **Paper:** [SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents](https://doi.org/10.5281/zenodo.23715017) (preprint, Zenodo) · [full write-up on Ready Tensor](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl) · [discuss on alphaXiv](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
132
 
133
  📝 **Tutorial:** [Stop your AI agent from signing an unlimited USDC approval](https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0): three deterministic checks to run before an agent signs, with runnable code.
134