18 papers
Multi-Credit Calibration via Elastically Stopped Lévy Processes
Graeme Baker, Agostino Capponi
We calibrate credit default swaps and index tranches with elastically stopped Lévy processes: each firm defaults when the running supremum of a latent, spectrally positive distress…
Portfolio Choice with Competing Precautionary and Accumulation Goals
Steven Campbell, Agostino Capponi, Ananya Parashar
We study optimal portfolio choice for a household simultaneously managing a random-deadline goal, such as a medical emergency or job loss, and a fixed-deadline goal such as retirem…
No Certificate, No Execution: Certified Traces as a Foundation for Trustworthy AI Agents
Xiao-Yang Liu Yanglet, Xiaodong Wang, Agostino Capponi
We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger…
The Viability of Blockchain Markets under Discrete Clearing and Paid Priority
Agostino Capponi, Ãlvaro Cartea, Fayçal Drissi
This paper develops a model to evaluate the viability of blockchain markets as the sole venue for price formation. Blockchains clear at discrete intervals called block time, and tr…
SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications
Abhinav Goel, Agostino Capponi, Alfio Gliozzo +1
We introduce SmartEval, a benchmark for systematically evaluating the quality of Solidity smart contracts generated by large language models (LLMs) from natural language specificat…
PREFER: Personalized Review Summarization with Online Preference Learning
Millend Roy, Agostino Capponi, Vineet Goyal
Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring the information most relev…