More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918409418047488 |
|---|---|
| author | Sivaraman, Venkatesh Vossler, Patrick Perer, Adam Hong, Julian Feng, Jean |
| author_facet | Sivaraman, Venkatesh Vossler, Patrick Perer, Adam Hong, Julian Feng, Jean |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24877 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes Sivaraman, Venkatesh Vossler, Patrick Perer, Adam Hong, Julian Feng, Jean Human-Computer Interaction Artificial Intelligence 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. |
| title | More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2603.24877 |