# Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories

arXiv: https://arxiv.org/abs/2610.02673 · HTML: https://mlsanity.com/paper/2610.02673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 132 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [The effectiveness of feature attribution methods and its correlation with automatic evaluation scores](https://mlsanity.com/paper/2105.14944/) (2021)
- [What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play](https://mlsanity.com/paper/1810.09648/) (2018)
- [LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions](https://mlsanity.com/paper/2411.05025/) (2024)
- [AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation](https://mlsanity.com/paper/2402.14978/) (2024)
- [IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback](https://mlsanity.com/paper/2410.04025/) (2024)
- [Visual correspondence-based explanations improve AI robustness and human-AI team accuracy](https://mlsanity.com/paper/2208.00780/) (2022)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking](https://mlsanity.com/paper/2308.07517/) (2023)
- [Ai2 Scholar QA: Organized Literature Synthesis with Attribution](https://mlsanity.com/paper/2504.10861/) (2025)
- [A Computational Inflection for Scientific Discovery](https://mlsanity.com/paper/2205.02007/) (2022)
- [Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literature](https://mlsanity.com/paper/2208.03455/) (2022)
- [Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering](https://mlsanity.com/paper/2509.19125/) (2025)
- [AI Reliance and Decision Quality: Fundamentals, Interdependence, and the Effects of Interventions](https://mlsanity.com/paper/2304.08804/) (2023)
- [Is Trust Correlated With Explainability in AI? A Meta-Analysis](https://mlsanity.com/paper/2504.12529/) (2025)
- ["The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation](https://mlsanity.com/paper/2503.16791/) (2025)
- [Generating Literature-Driven Scientific Theories at Scale](https://mlsanity.com/paper/2601.16282/) (2026)
- [LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape](https://mlsanity.com/paper/2604.02600/) (2026)

## Abstract (arXiv)

A theory draws many independent observations into one framework with novel hypotheses. A researcher building such a theory must synthesize observations scattered across many papers, each describing related concepts but often in different terms. Which concepts matter most also depends on their preferences and research questions. Recent approaches scale theory synthesis with LLMs, but automate away choices and intuitions from researchers. We present Asterism, which extracts observations from hundreds of papers as concept-relation triples, with concepts unified in a hierarchical ontology. Researchers curate an evidence graph using the ontology and aggregate observations at different levels of granularity to focus theory formation on specific phenomena of interest. In a field deployment (n=10), researchers worked from observations to theories, and kept concepts and hypotheses fitting their preferences. In two case studies, teams of immunology and agriculture researchers discovered mechanisms outside their standard analyses and constructed hypotheses worth follow-up experiments.