4103_bastani-osbert.jpg

Osbert Bastani

Trust Machine Learning (trustML) Program Synthesis Program Analysis Machine Learning For Software Engineering
University of Pennsylvania Computer and Information Science

About

I am an associate professor at the Department of Computer and Information Science at the University of Pennsylvania leading the trustml@Penn research group. I am a member of the ASSET, PRECISE, and PRiML centers, and of PLClub. Previously, I completed my Ph.D. at Stanford advised by Alex Aiken, and spent a year as a postdoc at MIT working with Armando Solar-Lezama.

Research Performance Summary

159
Total Papers
10186
Total Citations
45
H-Index
2011-2026
Active Research Span

First Recorded Paper

Randomization, sums of squares, near-circuits, and faster real root counting

Year: 2011

Citations: 25

Venue: Contemporary Mathematics 556

Latest Recorded Paper

Purely Agentic Black-Box Optimization for Biological Design

Year: 2026

Citations: 0

Venue: arXiv preprint arXiv:2601.22382

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

2026
6
2025
23
2024
29
2023
21
2022
17
2021
19
2020
11
2019
14
2018
4
2017
4
2016
2

Publication Venues and Collaboration

Journal, Conference, and Book Publication Breakdown

Conference 63
Journal 1
Book 1

Top Coauthors

Bastani Lee

Research Impact by Period

2025-2026

Period Stats
Papers 29
Citations 441
Avg. Citations / Paper 15.2
H-Index 4

2020-2024

Period Stats
Papers 97
Citations 6578
Avg. Citations / Paper 67.8
H-Index 36

2015-2019

Period Stats
Papers 27
Citations 3027
Avg. Citations / Paper 112.1
H-Index 19

2010-2014

Period Stats
Papers 6
Citations 140
Avg. Citations / Paper 23.3
H-Index 3

Contact and Professional Links

Contact Information

obastani@seas.upenn.edu

Detected Research Keywords

Model Predictive Shielding Safe Reinforcement Learning Pac Prediction Sets Guided Reinforcement Learning Optimizing Health Supply Health Supply Chains African Ancestry Individuals Black Box Explanations Sequential Decision Making Neurosymbolic Generative Models