Minnesota NLP · University of Minnesota

How does real science actually get done?
Help us record it.

We are building open datasets of scientific work — from single computational tasks to entire multi-month research projects — so that AI agents can learn to understand, assist, and eventually carry out research. Three complementary efforts are recruiting participants and collaborators right now.

Across UMN: Chemistry · Biology · Medicine · Aerospace · Civil & Environmental · Materials Science · Electrical & Computer Eng. · Robotics · & more Three time horizons: tasks → sessions → projects · Open data, co-authorship for contributing labs

One question, three scales of data

Each project captures scientific work at a different granularity. Together they span the full arc of research — what a scientist does in an hour, and what unfolds over half a year. They share a participant pool and recording infrastructure across departments.

Short · computational
1–2 hour simulation & analysis tasks → SciHarbor
Short · hands-on
1–2 hour physical lab sessions → Lab Workflows
Long · longitudinal
6–12 month full research projects → ResearchWorkflow

The three projects

Pick the one that matches how your lab works.

ShortComputationalSimulation

SciHarbor

Lead: Young-Jun Lee · 1–2 hr per task

If your lab works with simulators or computational tools, contribute well-specified tasks that become a public benchmark for AI agents on real scientific software.

What we collectA task description, its expected outcome, and the metrics that decide success — across chemistry, biology, aerospace, civil, and materials science.

Step 1
Scope
A short interview to scope the tasks your lab cares about.
Step 2
Submit
Specify each task — description, expected outcome, evaluation metrics — as a YAML manifest.
Step 3
Benchmark
We run agents against your tasks and post results to a public leaderboard.
Co-authorshipAll participants are invited as co-authors

ProducesSciHarbor — a benchmark evaluating AI agents on real simulators (OpenFOAM, GROMACS, AlphaFold, Ansys, SAP2000, OpenRocket…). 300+ tasks in Phase 1, MIT-licensed, with an open leaderboard.

Phase 2 extends to physical workflows once robotic arms are installed.

ShortHands-onVideo

Lab Workflows

Lead: Karin de Langis · 1–2 hr per session

If your lab is running physical experiments, record short sessions so models can learn the goals behind each action.

What we collectHead-mounted video with think-aloud narration; the participant's intent is annotated as the prediction target.

Step 1 · 30 min
Interview
Orientation, instructions, and scheduling.
Step 2 · 2 hr
Recording
Record two ~1-hour sessions in the lab.
Step 3 · 30 min
Reflection
Interview about actions, intentions, and goals.
Compensation$150 per participantup to $50 / hour

ProducesA dataset of hands-on lab workflows for benchmarking how well AI connects actions to scientific goals and intentions.

Long-horizonLongitudinalDigital

ResearchWorkflow

Lead: Khanh Chi Le · 6–12 months

If you are running a long-term project in digital tools, let us record how it unfolds from inception to publication.

What we collectKeystrokes, screen video, meeting notes, and documents — gathered passively as you work.

Step 1 · 1 hr
Onboarding
Set up recording and connect your tools.
Step 2 · 12 mo
Record & collect
Auto-records sessions and collects research files.
Step 3 · 3 × 1 hr
Reflection
Interviews about your research reasoning and decisions.
Compensation$150 per team / 4 monthsup to $600 total

ProducesA longitudinal dataset of how research unfolds — to study how early actions shape later ones, and to build better AI research assistants.

Contact: Khanh Chi Le ↗

How to get involved

Participate

Contribute your own scientific work — a couple of hours of lab recording, a set of computational tasks, or passive recording of a project you're already running. We handle setup, scheduling, and equipment.

For graduate students & lab members

Collaborate

Bring your lab into one or more of the projects. PIs help define what "correct" looks like in their domain and open the door for their students to participate.

For PIs & research groups across departments

Co-authorship and contribution opportunities are available for participating PIs and lab members across all three projects.

This initiative — and the team behind it — is featured in the Minnesota NLP Lab project portfolio, alongside our other work on expert workflows in science, law, education, and journalism.

Contact the project leads

Reach out to the lead for the study that fits your lab. For general inquiries or cross-project collaboration, contact the PI.

SciHarbor

Young-Jun Lee

Computational & simulation tasks

Email Young-Jun ↗
Lab Workflows

Karin de Langis

Hands-on lab video

Email Karin ↗
ResearchWorkflow

Khanh Chi Le

Longitudinal research process

Email Chi ↗

General inquiries & collaboration: Dongyeop Kang (PI) — dongyeop@umn.edu