Adhithya Bhaskar

Hi there! I am a PhD candidate at the University of Southern California in the Viterbi School of Engineering’s ISE department.

I design evaluation methods and automated pipelines for extracting evidence, testing research artifacts, and producing transparent, inspectable assessments. My work combines empirical study design, scientific software, text and data pipelines, and evaluation of LLM output consistency and reliability.

My current work on ReproReady develops a local, offline, deterministic tool for statically checking computational research artifacts. It is designed to help researchers understand the manual work required to reproduce reported computational results, rather than predict whether the code will run.

I am seeking full-time Research Scientist, Data Scientist, ML Evaluation, and Applied AI roles. I expect to defend my dissertation in December 2026.

You can find my resume here.

Publications

• Reproscreener: Leveraging LLMs for Assessing Computational Reproducibility of Machine Learning Pipelines
  Adhithya Bhaskar, Victoria Stodden
  ACM REP, 2024
• Learning from reproducing computational results: introducing three principles and the Reproduction Package
  Matthew S. Krafczyk, August Shi, Adhithya Bhaskar, et al
  Phil. Trans. R. Soc. A, 2021
• Scientific Tests and Continuous Integration Strategies to Enhance Reproducibility in the Scientific Software Context
  Matthew Krafczyk, August Shi, Adhithya Bhaskar, et al
  ACM P-RECS, 2019
• Enabling the Verification of Computational Results: An Empirical Evaluation of Computational Reproducibility
  Victoria Stodden, Matthew S. Krafczyk, and Adhithya Bhaskar
  ACM P-RECS, 2018

Awards

• Jenny Wang Excellence in Teaching Award
  Viterbi School of Engineering, 2023 and 2026
• Outstanding Teaching Assistant of the Year
  Daniel J. Epstein Department of Industrial and Systems Engineering, 2023 and 2026