publications

a growing list of my published works and working papers.

working papers

  1. Incentives shape how humans co-create with generative AI
    Nathanael Jo, and Manish Raghavan
    Working Paper, 2026
    arXiv
  2. Alignment has a Fantasia Problem
    Nathanael Jo, Zoe De Simone, Mitchell Gordon, and Ashia Wilson
    Working Paper, 2026
    arXiv
  3. The Subjectivity of Monoculture
    Nathanael Jo, Nikhil Garg, and Manish Raghavan
    Working Paper, 2026
    arXiv
  4. ODTlearn: A Package for Learning Optimal Decision Trees for Prediction and Prescription
    Patrick Vossler, Sina Aghaei, Nathan Justin, Nathanael Jo, Andrés Gómez, and Phebe Vayanos
    Working Paper, 2025
    arXiv HTML

journal articles

  1. Drop a Line, Submit on Time? Randomized Tailored Reminders Improve Pollution Reporting Timeliness
    Elinor Benami, Nathanael Jo, Beth Ragnauth, and Daniel E Ho
    Journal of the Association of Environmental and Resource Economists, Jul 2026
    HTML Code
  2. Learning Optimal Prescriptive Trees from Observational Data
    Nathanael Jo, Sina Aghaei, Andrés Gómez, and Phebe Vayanos
    Management Science, Jun 2026
    arXiv Code
  3. Not (Officially) in My Backyard: Characterizing Informal Accessory Dwelling Units and Informing Housing Policy with Remote Sensing
    Nathanael Jo, Andrea Vallebueno, Derek Ouyang, and Daniel E Ho
    Journal of American Planning Association, Jun 2024
    Press: CBS News;  Local Housing Solutions
    HTML

conference papers

  1. Position: AI Evaluations Should be Grounded on a Theory of Capability
    Nathanael Jo, and Ashia C Wilson
    In International Conference on Machine Learning Position Paper Track, Jul 2026
    arXiv HTML
  2. Homogeneous algorithms can reduce competition in personalized pricing
    Nathanael Jo, Kathleen Creel, Ashia Wilson, and Manish Raghavan
    In Advances in Neural Information Processing Systems, Dec 2025
    arXiv HTML
  3. Estimating and Implementing Conventional Fairness Metrics With Probabilistic Protected Features
    Hadi Elzayn, Emily Black, Patrick Vossler, Nathanael Jo, Jacob Goldin, and Daniel E Ho
    In IEEE Conference on Secure and Trustworthy Machine Learning, Apr 2024
    arXiv HTML Code
  4. Learning Optimal Fair Classification Trees: Trade-offs Between Interpretability, Fairness, and Accuracy
    Nathanael Jo, Sina Aghaei, Andrés Gómez, and Phebe Vayanos
    In AAAI/ACM AI, Ethics, and Society, Aug 2023
    arXiv PDF Code
  5. Fairness in Contextual Resource Allocation Systems: Metrics and Incompatibility Results
    Nathanael Jo, Bill Tang, Kathryn Dullerud, Sina Aghaei, Eric Rice, and Phebe Vayanos
    In AAAI Conference on Artificial Intelligence, Aug 2023
    HTML PDF