CITATION.cff

cff-version: 1.2.0
message: "If you use jx in your work, please cite it as below."
title: "jx: an agent-composable marimo notebook catalog for scientific data exploration"
abstract: >
  jx is an experiment in agent-driven scientific data exploration. It pairs a catalog of runnable marimo notebooks — each embodying a real analysis use case and exposing reusable pure functions — with a thin skill file that lets an AI agent compose new analyses from existing notebooks in response to a user's question. The catalog is simultaneously documentation, working code, and a compositional substrate for agents, without the maintenance overhead of a separate library. The initial instantiation targets a large public morphological profiling dataset, but the pattern is dataset-agnostic.

type: software
authors:
  - family-names: Munoz
    given-names: Alan F.
    affiliation: "Broad Institute of MIT and Harvard"
    orcid: "https://orcid.org/0000-0001-8698-5477"
  - family-names: Gogoberidze
    given-names: Nodar
    affiliation: "Broad Institute of MIT and Harvard"
    orcid: "https://orcid.org/0000-0002-9395-4676"
  - family-names: Singh
    given-names: Shantanu
    affiliation: "Broad Institute of MIT and Harvard"
    orcid: "https://orcid.org/0000-0003-3150-3025"
repository-code: "https://github.com/broadinstitute/jx"
url: "https://github.com/broadinstitute/jx"
license: BSD-3-Clause
keywords:
  - agentic AI
  - AI agents
  - scientific notebooks
  - marimo
  - reproducible research
  - computational workflows
  - skill libraries
version: 0.0.2
date-released: "2026-04-15"
identifiers:
  - type: doi
    value: 10.5281/zenodo.19598884
    description: Concept DOI (all versions) on Zenodo