Shared knowledge for condensed matter physics
What one lab learns should help every other lab
My goal is a condensed matter physics where what one lab learns helps every other lab. What was tried, what didn't work and which simple explanations were already ruled out should be easy to find, and AI should help researchers work through it. This is an open science effort, built on open-source tools made for data that labs want to keep private.
- Phase 1 Now
An agentic research assistant
Open-source tools that run on any AI model. Before a paper is submitted, they list the known lookalikes for a signal (artifacts and simpler explanations), raise simple explanations and package the data. A sibling tool helps referees.
- Phase 2 Next
A record of what's been tried
A quick, citable way to share the results that rarely become a paper, so the field can see what has been tried and by whom. Labs that want to can log every run.
- Phase 3 Later
Shared knowledge for the field
The run log as the field default, controls pooled across labs, credit for careful work, and models trained on measured data, failures included.
Dig in
Each part opens into its own page. Sources sit in the margin, each one labeled: Human-checked means I've read it and confirmed the claim myself; AI only means an AI found and summarized it and I haven't confirmed it yet. This is a draft.
- 1
- 2
- 3
- 4
- 5
- A
Tell me where this is wrong
Write to me at david@sendorai.com. The questions I most want answered are in What am I missing?