# More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes

arXiv: https://arxiv.org/abs/2603.24877 · HTML: https://mlsanity.com/paper/2603.24877/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents](https://mlsanity.com/paper/2503.24047/) (2025)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [Interactive Debugging and Steering of Multi-Agent AI Systems](https://mlsanity.com/paper/2503.02068/) (2025)
- [Evaluating Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2512.15567/) (2025)
- [Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies](https://mlsanity.com/paper/2502.08554/) (2025)
- [How Beginning Programmers and Code LLMs (Mis)read Each Other](https://mlsanity.com/paper/2401.15232/) (2024)
- [How Do Analysts Understand and Verify AI-Assisted Data Analyses?](https://mlsanity.com/paper/2309.10947/) (2023)
- [Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis](https://mlsanity.com/paper/2405.05548/) (2024)
- [From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems](https://mlsanity.com/paper/2506.20091/) (2025)
- [How Scientists Use Large Language Models to Program](https://mlsanity.com/paper/2502.17348/) (2025)
- [Tempo: Helping Data Scientists and Domain Experts Collaboratively Specify Predictive Modeling Tasks](https://mlsanity.com/paper/2502.10526/) (2025)
- [AI-Enhanced Sensemaking: Exploring the Design of a Generative AI-Based Assistant to Support Genetic Professionals](https://mlsanity.com/paper/2412.15444/) (2024)

## Built on by (most cited first, 2 of 2)

- [Sanity Checks for Agentic Data Science](https://mlsanity.com/paper/2604.11003/) (2026)
- [Agentic-imodels: Evolving agentic interpretability tools via autoresearch](https://mlsanity.com/paper/2605.03808/) (2026)

## Abstract (arXiv)

Generative artificial intelligence (AI) tools can now help people perform complex data science tasks regardless of their expertise. While these tools have great potential to help more people work with data, their end-to-end approach does not support users in evaluating alternative approaches and reformulating problems, both critical to solving open-ended tasks in high-stakes domains. In this paper, we reflect on two AI data science systems designed for the medical setting and how they function as tools for thought. We find that success in these systems was driven by constructing AI workflows around intentionally-designed intermediate artifacts, such as readable query languages, concept definitions, or input-output examples. Despite opaqueness in other parts of the AI process, these intermediates helped users reason about important analytical choices, refine their initial questions, and contribute their unique knowledge. We invite the HCI community to consider when and how intermediate artifacts should be designed to promote effective data science thinking.