A laboratory built around questions.

Aldan Jay

I am Aldan Jay, a researcher and PhD student at Universitat Jaume I. I work in R&D and innovation at Semanticbots and am a member of the Temporal Knowledge Bases Group (TKBG). I started BullSAI Lab as an independent initiative.

These are personal affiliations. BullSAI Lab is my personal research website, with no commercial activity, and is independent of those organisations. Publications retain their original authorship and affiliations.

The software I publish will be open source.

Rules for new experiments

These rules are mandatory for new experiments. They are prospective commitments; earlier papers are presented with their own methods and limitations.

Hypotheses before results

State the question, evaluation measures and protocol before running the experiment.

A simple reference

Compare each system with a relevant, simple baseline. For a trading policy, include a passive reference.

Costs and frictions

Include fees and slippage when evaluating market operations, and state the assumptions. Report computational demands separately.

Evaluation held apart

Separate development from evaluation, state the periods and freeze the protocol before the final test.

Negative results count

Report failures and explain abandoned experiments, as well as favourable outcomes.

Make verification possible

Link to the paper, code or data where permitted. State missing materials and restrictions on sharing.

Work with us

We welcome collaboration on evaluation protocols, financial language, agent decision-making and independently checkable explanations. A useful starting point is a specific question, an available dataset and a simple comparison.