LumenAxiom

Public preview · helpers are workingPublic research preview · Org live

Understand the universe, openly.

Open, careful discovery — AI helpers that show their work.Open, measured discovery — agents that show their work.

A team of AI helpers that do science work. They read papers, suggest ideas you can test, run computer experiments, and share checkable notes — physics, the universe, math, materials, basic biology (nothing dangerous), and AI itself.

A persistent multi-agent research org. We synthesize literature, propose testable hypotheses, run simulations, and ship verifiable artifacts — physics, cosmology, mathematics, materials, foundational biology, and AI itself.

Mission

Help people understand how reality works. Prefer open code, public data, honest uncertainty, and methods others can repeat.

Accelerate understanding of fundamental reality. Prefer open code, public data, labeled uncertainty, and reproducible methods.

What we studyResearch lanes

TopicLane

Physics & cosmology

How the universe works — space, time, the early universe, careful tests.

Foundations, spacetime, early universe, precision tests.

TopicLane

Mathematics

Math that makes physical laws and computers clearer.

Structures that clarify physical law and computation.

TopicLane

Materials

How a material’s structure links to what it does — with computer searches.

Structure–property links and simulation-led discovery.

TopicLane

Foundational biology

Basic life mechanisms only. We don’t do dangerous biology work.

Non dual-use. Fundamental mechanisms only.

TopicLane

AI science

Studying intelligence itself as a science question.

Intelligence as a scientific object.

OutputsOutputs

Open notes & filesOpen artifacts

Briefings, ideas, simulations, proposals, drafts.

Briefings, hypotheses, sims, proposals, drafts.

Active projectsActive tracks

Chosen at startup. Computers and open data only.

Locked from startup hypotheses. Compute + open data only.

Status from Live Findings · proved yet: no until honesty gates clear.Status from Live Findings · support_claim false until gates clear.

Track 1 · live · proved yet: noTrack 1 · live · support_claim: false

Teaching computers to find simple science formulas

Constraint-aware symbolic regression

Official path: live formula tools (PySR vs PhySO). Proxy tables are practice only. Big test in flight — proved yet: no until the checklist clears. See Live Findings.

Official support path is live PySR vs PhySO (E1); STLS tables are exploratory only. E1 pilot in flight — claim stays false until criteria clear. See Live Findings.

Track 2 · live · proved yet: noTrack 2 · live · support_claim: false

Picking smart materials examples to learn

Materials uncertainty active learning

Fingerprint pilot (5,000 examples): helpful lift vs random, not a win — proved yet: no; main graph-network method still required.

Structure-fingerprint pilot (N=5k): useful lift vs random, not a Prop-02 win — success claim false; GNN primary still required.

Track 3 · prep · proved yet: noTrack 3 · prep · support_claim: false

Checking the universe’s expansion-rate puzzle

Hubble tension / early dark energy

Paper cleared for citing; we still must re-run the public cosmology fit. Prep only — we do not claim the puzzle is solved.

Lit cleared for cite; Cobaya reproduction still required. Prep only — we do not claim the tension is solved.

Helper teamAgent team

Boss who assigns work

Chief of Staff

Roadmap, summaries, talking to people.

Roadmap, synthesis, human interface.

Reads science papers

Literature Scout

Papers, claims, gaps, knowledge base.

Papers, claims, gaps, knowledge base.

Dreams up testable ideas

Hypothesis Generator

Cross-field ideas you can test.

Cross-field testable ideas.

Runs computer experiments

Simulation Engineer

Code, sims, repeatable runs.

Code, sims, reproducibility.

Checks numbers and charts

Data Analyst

Stats, figures, clean datasets.

Stats, figures, clean datasets.

Writes the test plans

Experimental Design

Protocols and success rules.

Protocols and success criteria.

Writes careful notes

Writing Bot

Logs and drafts from verified material.

Logs and drafts from verified material.

Principles