About
The claim. Data-science pieces that start from my own life, built from open data or from data named directly on the web.
The catch. Every analysis is produced by me guiding a large language model. The model writes and runs the code, and I do not re-read it line by line. Nothing here is peer-reviewed.
The reality. Each piece is probably correct, and would be interesting if it were. Uncertainty is part of the story, and every issue ends with a transparency panel that lets you judge for yourself.
Who
I am Riccardo Gallotti. I lead the Complex Human Behaviour (CHuB) unit at Fondazione Bruno Kessler in Trento, Italy. I am a theoretical physicist by training and a complexity and data scientist by trade. My research questions normally go through peer review. This is where the other questions go: the ones that come up on a train or in front of a screen.
How it is made
I work with the model the way I would with one of my interns. I set the question and the framing. It downloads the data, writes the pipeline, draws the figures and drafts the text. Then we iterate: I question its assumptions and results, send it back when a number looks wrong, and decide what goes in and what stays out. The model is named, with its version, in every issue.
What replaces peer review
Disclosure you can check. Every issue ends with cards on the table: which model did what, the real errors found and fixed, the published research on the same question, and open code and data so anyone can rerun it. The pieces measure; they do not recommend. They are not scientific publications. If you need to reference one, cite the DOI of its archived code and data.
Who it is for
Curious people more than credentialed ones, who suspect that small things and serious ones deserve the same care in measuring and the same honesty about what the measure can say. And journalists who may want to pick a finding up, with the cards on the table.