On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “unhackable”

Defining and Characterizing Reward Hackingcs.LG

New concept: reward hacking, where optimizing a flawed reward function can hurt performance.

problem Optimizing imperfect reward functions leads to poor performance.

method Formal definition and analysis of reward hacking, examining conditions for unhackability.

result Reward functions are usually hackable, making it hard to align AI with human values.

reward hacking proxy reward unhackable AI alignment reward function

2022-09-27abs ↗pdf ↗

Transaction Confirmation Time Prediction in Ethereum Blockchain Using Machine Learningcs.CR

Paper predicts transaction confirmation time in Ethereum blockchain using machine learning.

problem Estimating transaction confirmation time in Ethereum blockchain.

method Uses machine learning, specifically Random Forest Regressor and Multilayer Perceptron, to predict transaction confirmation time.

result Proposed model shows improved accuracy in predicting transaction confirmation time compared to statistical models.

Ethereum blockchain transaction confirmation machine learning prediction random forest

2019-11-25abs ↗pdf ↗