Computer Science · Furman University

Saugat Pandey

Pronounced Saw-gaat Paan-day

Assistant Professor of Computer Science Director, MOCHA Lab

I study how people read, trust, and reason with visual data, and what changes when AI is in the loop. I earned my PhD in Computer Science & Engineering at Washington University in St. Louis, in the VIBE Lab with Alvitta Ottley.

Saugat Pandey smiling over his shoulder, wearing a backpack, with snowfields and glaciers behind him.
Mt. Rainier, Washington

The lab

I direct the MOCHA Lab at Furman and am recruiting undergraduate researchers.

Visit the lab

On air · Nov 2026

WSPA 7News asked me about consumer AI agents and the privacy risks that come with them.

Watch the segment

Open source · Nov 2026

Two of my patches were merged into CPython: one in datetime, one in ctypes.

Read about the fixes

Research

Three questions I keep coming back to

My work sits between data visualization, human perception, and AI. Each thread links to the papers behind it.

  1. 01

    Can people read this chart?

    Measuring visualization literacy quickly and reliably. Mini-VLAT, a 12-item test, won Best Paper at EuroVis 2023, and I've since used these tests to benchmark vision-language models.

  2. 02

    Do they trust what they see?

    What makes a visualization feel trustworthy, which factors build or erode that trust, and how to measure it as more than a single number, from the viewer's side of the chart.

  3. 03

    What happens when AI reads, and makes, images?

    Vision-language models on literacy tests, multi-agent LLM systems that help people design charts, and when detectors can (and can't) tell a generated image from a real one.

Publications

Papers

Newest first. For citation counts and the full list, see Google Scholar.

Under review Titles only, during anonymous review

  1. Déjà VAE: When Do Autoencoder Traces Reveal Generated Images?

    Saugat Pandey

    Under review · 2026

  2. False-Positive Rates of Detectors of AI-generated Chest Radiographs across Held-out Public Datasets

    Saugat Pandey

    Under review · 2026

2025

  1. Estimating PM2.5 Concentrations at Public Schools in North Carolina Using Multiple Data Sources and Interpolation Methods

    Rachel Carroll, Paul Bailey, Saugat Pandey, Dana McCalla, Thomas Snyder

    Scientific Reports 15, 42600

  2. Visualization Literacy or Skillset? Beyond the Analogy to Textual Literacy

    Mara Solen, Saugat Pandey, Firas Moosvi, Alvitta Ottley, Tamara Munzner

    IEEE VIS Workshop on Visualization for Communication (VisComm)

  3. Benchmarking Visual Language Models on Standardized Visualization Literacy Tests

    Saugat Pandey, Alvitta Ottley

    Computer Graphics Forum 44(3) · EuroVis 2025

  4. Trustworthy by Design: The Viewer's Perspective on Trust in Data Visualization

    Oen G. McKinley, Saugat Pandey, Alvitta Ottley

    ACM CHI 2025

2024

  1. Building and Eroding: Exogenous and Endogenous Factors that Influence Subjective Trust in Visualization

    R. Jordan Crouser, Syrine Matoussi, Lan Kung, Saugat Pandey, Oen G. McKinley, Alvitta Ottley

    IEEE VIS 2024

2023

  1. Mini-VLAT: A Short and Effective Measure of Visualization Literacy

    Saugat Pandey, Alvitta Ottley

    Computer Graphics Forum 42(3) · EuroVis 2023

  2. Do You Trust What You See? Toward a Multidimensional Measure of Trust in Visualization

    Saugat Pandey, Oen G. McKinley, R. Jordan Crouser, Alvitta Ottley

    IEEE VIS 2023

  3. User Engagement with COVID-19 Visualizations on Twitter

    Robert Kasumba, Saugat Pandey, Vishesh Patel, Micah Wolfson, Alvitta Ottley

    IEEE VIS Workshop on Visualization for Communication (VisComm)

Open source

Two fixes in CPython

CPython is the main implementation of Python, the one most people install. In November 2026, two of my patches were merged into it.

Merged Lib/datetime·

date.fromisoformat() stopped ignoring trailing characters

I came across this while working with Python's datetime module: a ten-character string like '2020010112' quietly turned into January 1, 2020, with the last two characters thrown away. I sent in a fix for both the C and pure-Python parsers, along with tests. It took a couple of weeks of patience (lol), but it was approved and merged, then backported to Python 3.15 and 3.14. I did the 3.14 backport by hand after the automatic one hit a conflict.

Merged Modules/_ctypes·

Resized ctypes objects no longer read or write out of bounds

After ctypes.resize(), a simple object's buffer is larger than its type. bool() and passing the object to a C function still used the buffer's size, so bool() read past the end of an internal 16-byte buffer, and the call copied the whole buffer into a fixed-size slot, corrupting the heap. The fix uses the type's size instead, matching how the value getter already worked.

News

In the news, and lately

Updates

  1. Two patches merged into CPython: date.fromisoformat() and resized ctypes objects.

    Open source
  2. Talked consumer AI agents, privacy, and prompt injection on WSPA 7News.

    Media
  3. Submitted two papers on detecting AI-generated images, “Déjà VAE” and a study of false-positive rates for chest-radiograph detectors. Both are under review.

    Submitted
  4. Launched The MOCHA Lab, my research group at Furman.

    Lab
  5. Started as Assistant Professor of Computer Science at Furman University in Greenville, SC.

    Career
  6. Defended my PhD dissertation at Washington University in St. Louis.

    Milestone
  7. PM2.5 at North Carolina public schools, published in Scientific Reports.

    Published
  8. “Visualization Literacy or Skillset?” accepted at the IEEE VIS Workshop on Visualization for Communication.

    Accepted
  9. Presented my work benchmarking vision-language models at EuroVis in Luxembourg City.

    Talk
  10. Moved to Seattle for the summer as a Research Scientist Intern at Adobe.

    Internship
  11. Passed my dissertation proposal.

    Milestone
  12. “Benchmarking Visual Language Models on Standardized Visualization Literacy Tests” accepted at EuroVis 2025.

    Accepted
  13. “Trustworthy by Design” accepted at ACM CHI 2025.

    Accepted
  14. Finished co-instructing Introduction to Visualization at WashU, rated 6.67 out of 7.

    Teaching
  15. Paper on what builds and erodes trust in visualization accepted at IEEE VIS 2024.

    Accepted

Contact

Say hello

I'm always glad to hear from prospective students, collaborators, and anyone curious about visualization, perception, or AI. Tell me a little about yourself and I'll get back to you.