Lacuna: A Research Map for Machine Learning
A living map that turns machine-learning papers into linked summaries, research directions, and testable proposals.
Finding a useful paper often leaves you with more questions: what does it connect to, which claims hold up, and where could you contribute?
We built Lacuna to make those connections easier to follow. Researchers and agents can move from papers to ideas, research directions, and candidate questions, then trace each step back to its sources.
How it works
The pipeline reconciles scholarly records, creates readable paper summaries, extracts granular concept elements, and clusters those elements into research directions. Every generated layer preserves links back to the records and papers that support it.
Papers
Reconcile scholarly records and produce readable, source-linked summaries.
Concepts
Extract granular methods, findings, and observations from each paper.
Directions
Cluster recurring concepts into coherent threads across the literature.
Proposals
Surface underexplored questions and hypotheses for researcher review.
What to keep in mind
Generated summaries, directions, and proposals remain research aids rather than substitutes for the primary literature.
Coverage and map quality depend on the scholarly sources, identity reconciliation, and models used to build each release.
Start with a question, follow the evidence
The paper walks through automated theorem proving: from a broad topic to a scoped research question with supporting evidence and limitations.
Results at a glance
| System | Citation F1 | Reference hits | RACE / 10 |
|---|---|---|---|
| Lacuna Deep Research | 0.052 | 99 | 7.82 |
| GPT-Researcher | 0.039 | 72 | 5.24 |
| STORM | 0.015 | 21 | 2.90 |
| LangChain Open Deep Research | 0.007 | 13 | 7.42 |
ReportBench-ML covers 25 survey tasks. Reference hits measure overlap with expert bibliographies; RACE is a model-judged quality score. Systems use different model and retrieval setups. See the paper for the evaluation details.
Source: Lacuna v1, Tables 4–5 and Appendix D.3People behind the work
Listed in the paper’s author order.
Martin Weiss
Tiptree Systems · Mila · Polytechnique Montréal
Builds tools that connect the literature, research questions, and the people working on them. Also studies peer-review verification and agent decision-making.
Contributed to
LacunaThe Alien Space of ScienceAI Meta-ReviewingLLM Micro-Rationality
Miles Q. Li
Tiptree Systems · McGill University
Coauthor of Lacuna, connecting machine-learning papers through summaries, concepts, and research directions that people and agents can explore.
Contributed to
Alejandro H. Artiles
Tiptree Systems · Max Planck Institute for Human Development · Max Planck Institute for Intelligent Systems
First author of The Alien Space of Science. Now studies cognition–action tradeoffs in language agents through TextCraft.
Contributed to
LacunaThe Alien Space of ScienceTextCraft
Yacine Mkhinini
Tiptree Systems
Works on research infrastructure at Tiptree. Coauthor of Lacuna, our map of papers, concepts, and open research questions.
Contributed to
Christopher Pal
Polytechnique Montréal · Mila · Canada CIFAR AI Chair
Canada CIFAR AI Chair at Polytechnique Montréal. Scientific advisor and coauthor of Lacuna and The Alien Space of Science.
Contributed to
Hugo Larochelle
Scientific Director, Mila · Université de Montréal · McGill University
Scientific advisor and coauthor of Lacuna and Alien Science. Also collaborates on the behavioural economics of LLM agents.
Contributed to
LacunaThe Alien Space of ScienceLLM Micro-Rationality
Nasim Rahaman
Tiptree Systems
Brings a background in theoretical physics and machine learning to scientific discovery. Coauthor of Lacuna and The Alien Space of Science.
Contributed to
Read, reuse and cite
The paper and its artifacts, and a citation ready for your reference manager.
Paper and project resources
- Paper PDFFull manuscript · v1
- arXiv recordAbstract, authors, and version history
- DOIPersistent identifier for citing this paper
- Explore LacunaThe live map built by this project: papers, directions, and research questions
- Markdown interfaceText versions of the map’s pages for agents and developer workflows
Paper: CC BY 4.0
Cite this work
Copy this entry into your .bib file or import it into your reference manager.
@misc{weiss2026lacuna,
title = {Lacuna: A Research Map for Machine Learning},
author = {Weiss, Martin and Li, Miles Q. and Artiles, Alejandro H. and Mkhinini, Yacine and Pal, Chris and Larochelle, Hugo and Rahaman, Nasim},
year = {2026},
publisher = {arXiv},
doi = {10.48550/arXiv.2606.26246},
url = {https://arxiv.org/abs/2606.26246}
}
Read the full paper
Open the PDF or preview it here.
Have a question worth working on?
We work with researchers on scientific discovery, agent evaluation, and tools for navigating the literature. Tell us what you are exploring.